PLoS ONEplosplosonePLOS ONE1932-6203Public Library of ScienceSan Francisco, CA USA10.1371/journal.pone.0283141PONE-D-22-23228Research ArticleMedicine and health sciencesClinical medicineClinical immunologyAllergiesAllergic diseasesFood allergiesBiology and life sciencesImmunologyClinical immunologyAllergiesAllergic diseasesFood allergiesMedicine and health sciencesImmunologyClinical immunologyAllergiesAllergic diseasesFood allergiesMedicine and health sciencesClinical medicineClinical immunologyAllergiesAnaphylaxisBiology and life sciencesImmunologyClinical immunologyAllergiesAnaphylaxisMedicine and health sciencesImmunologyClinical immunologyAllergiesAnaphylaxisPhysical sciencesMathematicsApplied mathematicsAlgorithmsMachine learning algorithmsResearch and analysis methodsSimulation and modelingAlgorithmsMachine learning algorithmsComputer and information sciencesArtificial intelligenceMachine learningMachine learning algorithmsMedicine and health sciencesClinical medicineClinical immunologyAllergiesAllergensBiology and life sciencesImmunologyClinical immunologyAllergiesAllergensMedicine and health sciencesImmunologyClinical immunologyAllergiesAllergensMedicine and health sciencesEpidemiologyMedical risk factorsComputer and information sciencesArtificial intelligenceMachine learningMedicine and health sciencesDiagnostic medicineMedicine and health sciencesHealth careHealth care providersPhysiciansPeople and placesPopulation groupingsProfessionsMedical personnelPhysiciansFood anaphylaxis diagnostic marker compilation in machine learning design and validationFood anaphylaxis diagnostic marker compilation in machine learning design and validationhttps://orcid.org/0000-0002-1049-5647RandhawaInderpal S.ConceptualizationData curationFormal analysisSupervisionWriting – original draftWriting – review & editing*GroshenkovKirillData curationSoftwareSigalovGrigoriVisualizationWriting – original draftFood Allergy Institute, Long Beach, California, United States of AmericaAsghari JafarabadiMohammadEditorTabriz University of Medical Sciences, ISLAMIC REPUBLIC OF IRAN
The authors have declared no competing interests exist.
* E-mail: docrandhawa@tpirc.org5420232023184e028314119820222320232023Randhawa et alThis is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.Background
Traditional food allergy assessment of anaphylaxis remains limited in accuracy and accessibility. Current methods of anaphylaxis risk assessment are costly with low predictive accuracy. The Tolerance Induction Program (TIP) for anaphylactic patients undergoing TIP immunotherapy produced large-scale diagnostic data across biosimilar proteins, which was used to develop a machine learning model for patient-specific and allergen-specific anaphylaxis assessment. In explanation of construct, this work describes the algorithm design for assignment of peanut allergen score as a quantitative measure of anaphylaxis risk. Secondarily, it confirms the accuracy of the machine learning model for a specific cohort of food anaphylactic children.
Methods and results
Machine learning model design for allergen score prediction utilized 241 individual allergy assays per patient. Accumulation of data across total IgE subdivision served as the basis of data organization. Two regression based Generalized Linear Models (GLM) were utilized to position allergy assessment on a linear scale. The initial model was further tested with sequential patient data over time. A Bayesian method was then used to improve outcomes by calculating the adaptive weights for the results of the two GLMs of peanut allergy score prediction. A linear combination of both provided the final hybrid machine learning prediction algorithm. Specific analysis of peanut anaphylaxis within one endotype model is estimated to predict the severity of possible anaphylactic reaction to peanut with a recall of 95.2% on a dataset of 530 juvenile patients with various food allergies, including but not limited to peanut allergy. Receiver Operating Characteristic analysis yielded over 99% AUC (area under curve) results within peanut allergy prediction.
Conclusions
Machine learning algorithm design established from comprehensive molecular allergy data produces high accuracy and recall in anaphylaxis risk assessment. Subsequent design of additional food protein anaphylaxis algorithms is needed to improve the precision and efficiency of clinical food allergy assessment and immunotherapy treatment.
The authors received no specific funding for this work.Data AvailabilityThe complete codes and data necessary to reproduce our calculations and verify our findings are available on GitHub (https://github.com/TPIRC/ai_paper_2022).Introduction
Food allergy and anaphylaxis remain a high prevalence disorder in developed countries [1]. With an estimated 6% of children diagnosed with food anaphylaxis, the diagnosis burden encompasses both patients and families [2]. The cost of living with food anaphylaxis is $24.8 (95% CI, $20.6-$29.4) billion annually ($4184 per year per child) [3]. Of greater concern, the incidence of food allergy is increasing in both developed and developing countries [4].
Proper diagnosis of food anaphylaxis has evaded singular test methods. The classical method of skin prick testing at best maintains 50–60% positive predictive value [5]. Serum Immunoglobulin E (sIgE) testing via older RAST (radioallergosorbent test) methods or more recent Immunocap technology maintains over 50% false positivity in food allergy diagnosis [6]. In the last two decades, component resolved diagnostic testing held promise in greater anaphylaxis predictive accuracy. However, large studies reveal limitations in any improvement of accuracy of sIgE [7]. The gold standard of diagnosis remains the double-blind placebo controlled food challenge (DBPCFC). Interestingly, even patients who pass a DBPCFC are able re-develop anaphylaxis to that “passed” food challenge protein [8].
Our institute has developed a novel approach to the predictive diagnosis of food anaphylaxis followed by induction of sustained unresponsiveness of primary food allergens. The Tolerance Induction Program (TIP) involves utilization of large-scale data analytics assessing hundreds of pro allergic markers (skin prick testing, component resolved diagnostics, immunocap specific IgE, histamine release assay, peripheral eosinophil count) as well as tolerance markers (cytokine profiles, IgG4 specifics, total IgG4, total IgG) across collected patient cohorts since 2007. The machine learning process organizes an incoming patient’s specific markers against the molecular groupings of the database. Once analyzed, the patient’s markers are assessed into an endotype and a subsequent risk assessment of food allergens and biosimilar proteins is organized. This organized “snapshot” of an individual patient is further utilized to build food protein dose exposure cycles based on standardized eliciting doses of food proteins. Repeat marker analysis is monitored to assess the final process of tolerance induction and one-week sustained unresponsiveness for all primary allergens. The TIP model has been previously published [9].
The goal of this study is to overcome the limitations of current food allergy predictive models. The endpoint of TIP is high dose food allergen protein exposure on a minimum of a weekly basis with continued reduction in biosimilar food allergy markers. The severity of allergic reaction is quantitatively characterized by an allergen score. The databases and extracted formats to achieve these results served as the basis for machine learning development. A machine learning algorithm was developed to predict the allergen score using lab test data as features. The described algorithm was built and optimized to achieve > 95% recall. The training and testing data model are further described specific to clinical outcomes defined as sustained unresponsiveness.
Materials and methodsData
Data sets are organized into two primary groups. The first group involves all molecular data which was consistently acquired from each patient enrolled in the program since 2007. The data set includes extended profiles of component resolved diagnostics, skin prick testing, and sIgE to all primary plant and animal protein regardless of the patient’s clinical history. The second data set includes immune system markers consistently acquired from each patient enrolled in the program since 2007. Markers include B cell antibody diversity, cytokine production, basophil indices, eosinophil counts, and lymphocyte counts. The final data set includes the similarity of plant and animal species allergens utilizing data adopted from public domains such as the food allergen datasets Allergen Nomenclature (http://www.allergen.org/index.php, accessed on 9 October 2020) and the Structural Database of Allergenic Proteins (SDAP) (http://fermi.utmb.edu/SDAP/). All datasets have been rigorously screened, and there is no duplication between positive and negative samples.
A machine learning algorithm for allergen score prediction
To provide a physician with a tool for quick and accurate evaluation of the patient’s risk of anaphylaxis and the severity of a possible allergic reaction to peanut, we developed a Machine Learning (ML) algorithm. The algorithm is using a set of lab test data with up to 241 individual tests, as well as the patient’s personal information such as age and weight, as feature candidates. In the process of model optimization and training, relevant features are selected via iterations of a greedy selection algorithm, while features not meeting the standard relevance criteria are dropped. This automatic, data-centric process eliminates a human factor in deciding which test results should or should not be used in the ML model design. The larger set of tests for possible allergic proteins is available, the higher accuracy of the ML algorithm could theoretically be achieved. The relevant features are assigned adoptive weights as the result of model training. The training data set is tabular, based on depersonalized patient data, and will be described in detail below. Once trained, the ML model is used for new (out of set) patients to predict a quantified expected patient’s allergic reaction to peanut. The physician may then consider the predicted value while finalizing the diagnosis and selecting the treatment.
The severity of allergic reaction to peanut in a particular patient is normally classified as Anaphylactic (Ana), Sensitized (Sen), or Tolerant (Tol). Additionally, within each of these three classes, it is characterized by a positive number up to 100 referred to as an allergen score. The larger the number, the stronger the allergic reaction and, consequently, the risk of anaphylaxis. The score is usually rounded so that there could be up to 5 discrete severity levels within each severity class, for example Ana20, Ana40, Ana60, Ana80, Ana100. Since, for example, Sen100 is the highest severity level in the class Sen, and Ana20 is the lowest severity level in the class Ana that is directly above class Sen, it is natural to use a continuous absolute linear scale from 0 to 300 for the allergen score. Scores up to 100 correspond to identical scores within class Tol; scores between 120 to 200 correspond to Sen20 … Sen100; and finally, scores between 220 to 300 correspond to Ana20 … Ana100. These score representations are equivalent, each having its own advantages. In what follows, we will use both notations interchangeably.
To be clear, the ML algorithm is used as an auxiliary recommendation tool to assist a qualified human medical professional, who may consider the algorithm’s prediction in a clinical decision-making process ultimately left to the physician. Given the severity of anaphylaxis, and the fact that it is safer to overestimate rather than underestimate the risk of anaphylaxis, the algorithm is optimized, through its objective function’s design, to have the highest accuracy for class Ana and the upper levels of class Sen, and to err toward higher allergen scores rather than uniformly. In technical terms, positive errors (risk overestimation) have smaller weights in weighted Root Mean Square Error (RMSE) summation than negative errors do.
Dataset and features
For the purposes of this paper, we only focus on peanut allergy for endotype 1 patients. However, the same approach is applicable to other proteins and endotypes (results to be published elsewhere). The selected dataset included 530 patients, out of which 340 had total IgE < 1000 kU/L and 190 had total IgE > 1000 kU/L, thus representing two cohorts with different levels of susceptibility to food allergies. Fig 1 shows the distribution of total IgE values for all patients whose data were used in this study.
10.1371/journal.pone.0283141.g001
Distribution of total IgE values over the selected patient dataset.
The available dataset consists of depersonalized patient profiles along with the results of various laboratory tests performed before and during treatment. Those data provide the (potential) input features (independent variables, also called predictors) for a predictive ML algorithm. For each patient, three types of data are available:
patient’s personal information, including age and weight;
the results of up to 241 blood and skin lab tests performed;
peanut allergy severity classes and scores (feature “Peanut” on the source data table) as determined by a qualified medical professional (these are the dependent variables whose ground truth values are used to train the ML model).
The lab test results are usually represented by a nonnegative number within a certain range, with some notable exceptions. First of all, certain features cannot be measured reliably near the lower and/or upper limits of their range; such results may be shown as “less than” or “greater than” a certain threshold value, with a numerical value in the intermediate range where an accurate measurement is possible. Secondly, some of the tests have Boolean or integer-valued underlying nature and could be better treated as binary, categorical, or ordinal variables, rather than as continuous variables. Lastly, the values for many tests are missing, usually because those tests were deemed (by a physician) redundant or unnecessary, considering the patient’s anamnesis. Thus, only the ML methods that are capable of dealing efficiently with massively missing data should be considered for the algorithm. Fig 2 illustrates the range and distribution of values for some representative features.
10.1371/journal.pone.0283141.g002
Distribution of values for some independent data features.
Algorithm design
As noted above, there are two ways to characterize the allergen score: either as a class (Tol, Sen, Ana) and further as a level 20, 40, …, 100 within that class (e.g., Ana40), or as a continuous variable from 0 to 300, rounded to the nearest 20. The step of 20 is chosen for convenience only and does not affect the algorithm as such. Accordingly, there are two possibilities for the design of a predictive ML algorithm. To reflect the former representation, one could build a cascade of a 3-class classifier and a regression model for the level within the class. For the latter representation, a regression model for the continuous score that spans all three classes could be constructed.
For the former choice, to assign one of the 3 classes, one could take into account the fact that those classes are actually ordered (Tol < Sen < Ana in terms of the severity of the allergic reaction), and thus use ordinal regression. Alternatively, one could ignore that fact and use pure classification into categorical variables, expecting that the ML model would learn on its own to assign classes in the correct order. In what follows, we will generate ML models based on each of those design solutions and compare their outcomes.
We began by creating a regression-based Generalized Linear Model (GLM) with link functions to mimic the nonlinear behavior or a hypothesized type of distribution (normal or Poisson distribution, as indicated by the data analysis) for some of the features. We chose a continuous score ranging from 0 to 300 as the dependent variable and rounded the obtained real-numbered predictions to the nearest 20.
Based on biomedical information, certain features are known a priori to be possibly relevant for peanut allergy prediction. The GLM regression model is initially trained using those a priori features, while estimating their actual relevance. After an automatic feature elimination process via iterations of a greedy algorithm, the relevant features are found to be peanut_ige, peanut_igg4, peanut_spt, arah_1, arah_2, arah_3, arah_8, arah_9. While higher numerical values of these features usually imply a higher peanut allergy score, the dependence of the latter on the features is non-trivial and extremely noisy, as illustrated by Fig 3, and requires an advanced ML model to allow for meaningful prediction.
10.1371/journal.pone.0283141.g003
Correlation between the dependent variable (peanut allergy score) and some relevant predictors.
Absolute peanut allergy scores 120–200 can be interpreted as Sen20 to Sen100, and scores 220–300 as Ana20 to Ana100. By design, arahs = max(arah_1, …, arah_9).
The model generated using the abridged (known a priori) set of features might be improved by considering additional features provided by lab tests for proteins not obviously biosimilar to peanut, and thus not deemed a priori relevant. The model is therefore trained further, trying one additional candidate feature at a time (out of 243 available features, including patient’s age and weight). A feature that improves the model is preserved, and then another iteration over candidate features is performed, until no further improvement can be achieved. Some examples of features that are not directly related to peanut but might still improve the ML model that predicts the peanut allergy score are total_igg4, cyt, and eos (Eosinophil count). Table 1 shows how addition of these non-obvious features, selected automatically through greedy incremental feature testing and addition or rejection, improves the model. The prediction error is estimated using the Leave-One-Out (LOO) cross-validation method. Table 2 shows the top 10 features of the expanded set along with their normalized importance values. I can be seen that this list includes all 8 a priori features, but some of the a priori features are less important than some of new features that are not directly linked to peanut.
10.1371/journal.pone.0283141.t001
Mean absolute error (MAE) of the peanut allergy score prediction in ML models with an abridged (a priori known) set of features and an expanded set of features, each optimized to include only relevant features.
Ground truth values are multiples of 20. LOO cross-validation is used.
Features
class Ana
class Sen
A priori set
8
25.8
Expanded set
7.6
21.7
10.1371/journal.pone.0283141.t002
Top 10 independent features of the expanded set of predictors.
Feature
Importance
arah_2
0.531862
peanut_ige
0.379455
arah_1
0.025432
arah_3
0.012586
arah_8
0.010985
arah_9
0.009214
coconut_ige *
0.008989
coconut_spt *
0.00748
peanut_igg4
0.007411
peanut_spt
0.006586
* Indicates features not present on the a priori set. Importance values are normalized and meant to indicate a relative importance of the features rather than the weights of the variables.
The mean absolute error (MAE) of the above models is well under 20, which is the distance between the adjacent values of the allergy score’s ground truth values. This means that the ML algorithm predicts the allergy severity level to within one step of the ladder, on average. However, it might not always predict the correct class (Ana, Sen, or Tol) when the ground truth level is at or near the boundary between classes (100 or 200). For example, it might predict level Sen100 when the ground truth is Ana20, or vice versa. While the numerical difference between these scores is still only 20, the medical implications of the misclassification (Sen vs Ana) may be serious. We addressed this issue by predicting the class first, and the level within each class second. We compared two approaches for that classification task, one through pure classification and the other through ordinal regression, in which the information about class ordering is used extensively. In both models, we used tree-based methods trained with gradient boosting. The ordinal regression method turned out to be more accurate and was selected for this task. The performance of this method is shown in Table 3. Note that there were no patients tolerant to peanut on the chosen dataset, therefore only classes Ana and Sen are present in the results. However, the ordinal regression method we used is not limited to 2-class classification as it is not a binary or logistic classification by its nature. Classification into 3 (or more, for that matter) classes may be effectively performed using the same method for other food proteins or groups of patients.
10.1371/journal.pone.0283141.t003
Classification model performance in ML models with an abridged (known a priori) and expanded sets of features, each optimized to include only relevant features.
Both models employed ordinal regression and were trained with Gradient Boosting for peanut allergy classification into reaction severity classes. Class Tol is not present in the input dataset.
Features
class Ana
class Sen
Precision, %
Recall, %
Precision, %
Recall, %
A priori set
82.3 (303/368)
98.0 (303/309)
91.2 (125/137)
69.0 (125/181)
Expanded set
83.0 (304/366)
98.3 (304/309)
91.4 (127/139)
70.2 (127/181)
Finally, we trained the GLM regression model described above on the data for each class separately, thus achieving both a more accurate classification and more accurate prediction of the level with the class. However, the original full-range (0 to 300) GLM regression model still could be used to improve the final outcomes, because it is trained on a larger dataset. We combined both GLMs by using a Bayesian method to calculate the adaptive weights for the results of the two methods of peanut allergy score prediction. A linear combination of them provided the final hybrid ML prediction algorithm. Its design is summarized in Fig 4.
10.1371/journal.pone.0283141.g004
The design of the proposed ML algorithm for prediction of the peanut allergy score.
The accuracy of the final ML algorithm was characterized with Receiver Operating Characteristic (ROC) curves. To verify that the algorithm performs well for both highly susceptible and less susceptible patients, we calculated the ROC curves for 340 patients with total IgE < 1000 and 190 patients with total IgE > 1000. The results shown in Fig 5 demonstrate that the proposed ML algorithm could be used as a diagnostic support tool for a physician to evaluate the expected severity of patient’s allergic response to peanut.
10.1371/journal.pone.0283141.g005
ROC curves for the proposed ML algorithm’s prediction that the patient is Anaphylactic (Ana) vs Sensitive (Sen).
(a) patients with total IgE < 1000 kU/L, AUC 0.994; (b) patients with total IgE > 1000 kU/L, AUC 0.997 (AUCs are given for the expanded feature sets).
Discussion
Machine learning algorithm design in modern medicine largely endorses imaging aspects of medical specialties such as radiology and ophthalmology. ML accuracy and recall in imaging associated medical specialties continue to improve as reflected in the regulatory approval of such devices. The specialty of Allergy and Immunology to date has no diagnostic machine learning algorithm published in any of the atopic disease states: eczema, asthma, rhinitis or food anaphylaxis. The Tolerance Induction Program has structured its clinical therapeutic model upon data collection across immunological, phylogenetic and clinical markers. The totality of these markers are organized to study food anaphylaxis patients into specific endotype cohorts. Once identified, the cohort specific analysis utilizes machine algorithms based on aforementioned data sets to determine food protein specific anaphylaxis risk. Furthermore, the risk assessment produced serves as the basis for additional machine learning systems producing food protein-based immunotherapy schedules on a patient specific basis. Ultimately, the risk assessment is re-calculated per annum as the patient progresses through large challenges of food proteins in challenge sequences. Upon completion, the patient consumes between 10–30 grams of food specific protein in one sitting to all of once anaphylactic foods. In subsequent weeks, the consumption of this large amount of food protein occurs on a weekly or biweekly basis thus achieving sustained unresponsiveness while freely consuming once anaphylactic foods.
Our machine learning algorithm is designed utilizing anaphylaxis clinical, diagnostic and eliciting dose data. Such data in an anaphylaxis cohort is critical as it reflects known risk of the disease in a large cohort. We defined a risk score as a continuous variable, which effectively becomes ordinal when rounded. We trained our supervised learning model to predict the risk score and compared the model predictions with the scores assigned by a highly trained medical professional. We found that using an ordinal dependent variable results in a model that is more robust and accurate than multinomial models using categorical variables (unordered risk classes).
The ML algorithm design was further specified to peanut. Focus on peanut was necessary as it was one of the most common food anaphylactic proteins in the study population. The specific analysis of peanut anaphylaxis within this one endotype model was estimated to predict the severity of possible anaphylactic reaction to peanut with an overall recall of 95.2% on a dataset of 530 juvenile patients with various food allergies. The validation of the ML algorithm was characterized with ROC curves. Calculation of ROC curves for 340 patients with total IgE < 1000 kU/L and 190 patients with total IgE > 1000 kU/L yielded over 99% AUC (area under curve) results within peanut allergy prediction. The results demonstrate that the proposed ML algorithm could be used as a diagnostic support tool for a physician to evaluate the expected severity of patient’s allergic response to peanut. Moreover, it supports the accuracy of peanut anaphylaxis assessment in targeted treatment in the Tolerance Induction Program.
Machine learning algorithm design established from comprehensive molecular allergy data produces high accuracy and recall in anaphylaxis risk assessment. Further design of additional food protein anaphylaxis algorithms is needed to improve the precision and efficiency of clinical food allergy assessment and immunotherapy treatment.
ReferencesDatemaM, LyonsSA, Fernández-RivasM, Ballmer-WeberB, et al. Estimating the Risk of Severe Peanut Allergy Using Clinical Background and IgE Sensitization Profiles. Frontiers in Allergy. 2021Jan;2(1):670–789.GuptaRS, WarrenCM, SmithBM, BlumenstockJA, et al. The Public Health Impact of Parent-Reported Childhood Food Allergies in the United States. Pediatrics. 2018Jul;142(6). doi: 10.1542/peds.2018-123530455345GuptaR, HoldfordD, BilaverL, DyerA, et al. The economic impact of childhood food allergy in the United States. JAMA Pediatrics. 2013Dec;167(11):1026–31. doi: 10.1001/jamapediatrics.2013.237624042236TangML, MullinsRJ. Food allergy: is prevalence increasing?Internal Medicine J. 2017Jun; 47(3):256–61. doi: 10.1111/imj.1336228260260Soares-WeiserK, TakwoingiY, PanesarSS, MuraroA, et al. EAACI Food Allergy and Anaphylaxis Guidelines Group. The diagnosis of food allergy: a systematic review and meta-analysis. Allergy. 2014May; 69(1):76–86. doi: 10.1111/all.1233324329961WoodRA, SegallN, AhlstedtS, WilliamsPB. Accuracy of IgE antibody laboratory results. Annals of Allergy, Asthma & Immunology. 2007Nov;99(1):34–41. doi: 10.1016/S1081-1206(10)60618-717650827FoongRX, DantzerJA, WoodRA, SantosAF. Improving Diagnostic Accuracy in Food Allergy. J Allergy & Clinical Immunology. In practice. 2021July;9(1):71–80. doi: 10.1016/j.jaip.2020.09.03733429723FleischerDM, Conover-WalkerMK, ChristieL, BurksAW, et al. Peanut allergy: recurrence and its management. J Allergy & Clinical Immunology. 2004Feb;114(5):1195–1201. doi: 10.1016/j.jaci.2004.08.03515536431RandhawaI.Tolerance Induction Program Effect Explains Variation in Wheal Size, sIgE, and IgG4 in Peanut Allergic Children. J Allergy & Therapy. 2019July;10(2):1–10.10.1371/journal.pone.0283141.r001Decision Letter 0Asghari JafarabadiMohammadAcademic Editor2023Mohammad Asghari JafarabadiThis is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.Submission Version0
24 Oct 2022
PONE-D-22-23228Food Anaphylaxis Diagnostic Marker Compilation in Machine Learning Design and ValidationPLOS ONE
Dear Dr. Randhawa,
Thank you for submitting your manuscript to PLOS ONE. After careful consideration, we feel that it has merit but does not fully meet PLOS ONE’s publication criteria as it currently stands. Therefore, we invite you to submit a revised version of the manuscript that addresses the points raised during the review process.
Please submit your revised manuscript by Dec 08 2022 11:59PM. If you will need more time than this to complete your revisions, please reply to this message or contact the journal office at plosone@plos.org. When you're ready to submit your revision, log on to https://www.editorialmanager.com/pone/ and select the 'Submissions Needing Revision' folder to locate your manuscript file.
Please include the following items when submitting your revised manuscript:
A rebuttal letter that responds to each point raised by the academic editor and reviewer(s). You should upload this letter as a separate file labeled 'Response to Reviewers'.
A marked-up copy of your manuscript that highlights changes made to the original version. You should upload this as a separate file labeled 'Revised Manuscript with Track Changes'.
An unmarked version of your revised paper without tracked changes. You should upload this as a separate file labeled 'Manuscript'.
If you would like to make changes to your financial disclosure, please include your updated statement in your cover letter. Guidelines for resubmitting your figure files are available below the reviewer comments at the end of this letter.
If applicable, we recommend that you deposit your laboratory protocols in protocols.io to enhance the reproducibility of your results. Protocols.io assigns your protocol its own identifier (DOI) so that it can be cited independently in the future. For instructions see: https://journals.plos.org/plosone/s/submission-guidelines#loc-laboratory-protocols. Additionally, PLOS ONE offers an option for publishing peer-reviewed Lab Protocol articles, which describe protocols hosted on protocols.io. Read more information on sharing protocols at https://plos.org/protocols?utm_medium=editorial-email&utm_source=authorletters&utm_campaign=protocols.
We look forward to receiving your revised manuscript.
Kind regards,
Mohammad Asghari Jafarabadi
Academic Editor
PLOS ONE
Journal Requirements:
When submitting your revision, we need you to address these additional requirements.
1. Please ensure that your manuscript meets PLOS ONE's style requirements, including those for file naming. The PLOS ONE style templates can be found at
https://journals.plos.org/plosone/s/file?id=wjVg/PLOSOne_formatting_sample_main_body.pdf and
2. In the Methods section of your revised manuscript, please include the full name of the institutional review board or ethics committee that approved the protocol, the approval or permit number that was issued, and the date that approval was granted.
Please note that PLOS ONE has specific guidelines on code sharing for submissions in which author-generated code underpins the findings in the manuscript. In these cases, all author-generated code must be made available without restrictions upon publication of the work. Please review our guidelines at https://journals.plos.org/plosone/s/materials-and-software-sharing#loc-sharing-code and ensure that your code is shared in a way that follows best practice and facilitates reproducibility and reuse.
3. Please provide additional details regarding participant consent. In the ethics statement in the Methods and online submission information, please ensure that you have specified what type you obtained (for instance, written or verbal, and if verbal, how it was documented and witnessed). If your study included minors, state whether you obtained consent from parents or guardians. If the need for consent was waived by the ethics committee, please include this information.
4. In your Data Availability statement, you have not specified where the minimal data set underlying the results described in your manuscript can be found. PLOS defines a study's minimal data set as the underlying data used to reach the conclusions drawn in the manuscript and any additional data required to replicate the reported study findings in their entirety. All PLOS journals require that the minimal data set be made fully available. For more information about our data policy, please see http://journals.plos.org/plosone/s/data-availability.
"Upon re-submitting your revised manuscript, please upload your study’s minimal underlying data set as either Supporting Information files or to a stable, public repository and include the relevant URLs, DOIs, or accession numbers within your revised cover letter. For a list of acceptable repositories, please see http://journals.plos.org/plosone/s/data-availability#loc-recommended-repositories. Any potentially identifying patient information must be fully anonymized.
Important: If there are ethical or legal restrictions to sharing your data publicly, please explain these restrictions in detail. Please see our guidelines for more information on what we consider unacceptable restrictions to publicly sharing data: http://journals.plos.org/plosone/s/data-availability#loc-unacceptable-data-access-restrictions. Note that it is not acceptable for the authors to be the sole named individuals responsible for ensuring data access.
We will update your Data Availability statement to reflect the information you provide in your cover letter.
5. Please ensure that you include a title page within your main document. You should list all authors and all affiliations as per our author instructions and clearly indicate the corresponding author.
6. Please amend your manuscript to include your abstract after the title page.
7. Please include your full ethics statement in the ‘Methods’ section of your manuscript file. In your statement, please include the full name of the IRB or ethics committee who approved or waived your study, as well as whether or not you obtained informed written or verbal consent. If consent was waived for your study, please include this information in your statement as well.
8. Please include your tables as part of your main manuscript and remove the individual files. Please note that supplementary tables (should remain/ be uploaded) as separate "supporting information" files
Reviewers' comments:
Reviewer's Responses to Questions
Comments to the Author
1. Is the manuscript technically sound, and do the data support the conclusions?
The manuscript must describe a technically sound piece of scientific research with data that supports the conclusions. Experiments must have been conducted rigorously, with appropriate controls, replication, and sample sizes. The conclusions must be drawn appropriately based on the data presented.
Reviewer #1: Yes
Reviewer #2: Partly
**********
2. Has the statistical analysis been performed appropriately and rigorously?
Reviewer #1: Yes
Reviewer #2: No
**********
3. Have the authors made all data underlying the findings in their manuscript fully available?
The PLOS Data policy requires authors to make all data underlying the findings described in their manuscript fully available without restriction, with rare exception (please refer to the Data Availability Statement in the manuscript PDF file). The data should be provided as part of the manuscript or its supporting information, or deposited to a public repository. For example, in addition to summary statistics, the data points behind means, medians and variance measures should be available. If there are restrictions on publicly sharing data—e.g. participant privacy or use of data from a third party—those must be specified.
Reviewer #1: No
Reviewer #2: No
**********
4. Is the manuscript presented in an intelligible fashion and written in standard English?
PLOS ONE does not copyedit accepted manuscripts, so the language in submitted articles must be clear, correct, and unambiguous. Any typographical or grammatical errors should be corrected at revision, so please note any specific errors here.
Reviewer #1: Yes
Reviewer #2: No
**********
5. Review Comments to the Author
Please use the space provided to explain your answers to the questions above. You may also include additional comments for the author, including concerns about dual publication, research ethics, or publication ethics. (Please upload your review as an attachment if it exceeds 20,000 characters)
Reviewer #1: Great topic, very motivating and intriguing.
I have the following comments for authors to consider:
1) what's authors recommendation as to using ordinal regression or using pure classification and let the model decide? I personally think using ordinal regression make better sense, first because the three classes follow increase of severity, i.e. ordinal scale, second using ordinal regression should increase model prediction accuracy and model efficiency with reduced model complexity.
2) I think a lot of readers want to know, out of the 200 features which ones are the most important, e.g. top20, top10? and what's the AUC based on reduced features, such as top 20, top 10 features?
3) which software is the algorithm being built? will they be publicly available?
4) I think a realistic dataset should consist of patients with no peanut allergy and patients with different severity levels of peanut allergy. Can authors confirm their dataset takes this into consideration?
5) how ready is this approach in real world applications? I want to hear about authors' vision on this.
6) If the word limit still allows, I suggest authors expand the manuscript to have more details as appropriate and can be presented more clearly e.g. using bullet points to delineate the major steps
7) I think authors should consider finding a completely independent dataset as a testing dataset, to further evaluate the robustness of the trained model.
Reviewer #2: Question 1
In general, the main elements of the design of the automatic learning model are well listed (data, processing, prediction result). The scientific language can be improved (I noted this in the reviewed manuscript).
The data included in the model are quite clearly specified.
The data processing mode is relatively well specified.
The final result should be, according to the Methods and Results chapter, the prediction of the allergen score using 247 individual allergy analyses per patient. The prediction can be done through various regressions. The authors should specify the form of these predictions. In this way, we could understand to what extent each independent parameter considered (...) influences the allergen score. Therefore, the authors are asked to specify how the allergen score is calculated as a depending on the independent parameters introduced. The authors clearly show how the independent parameters are quantified, but not the regressions for the calculation of the dependent parameter: the allergen score.
The result of the analysis can also be materialized in a support decision, which will suggest to the doctor the probable decision. However, it must be specified how this decision is made by the car. Both types of results must be validated. To describe an algorithm means to give its results and, in order to be credible, the results of its validation must be given.
Question 2
In the Chapter Data and features the independent data used are listed:
• Patient's Personal Information, Including Gender, Age, and Weight;
• The Results of Up to 247 Blood and Skin Lab Tests Performed;
and the dependent data:
• Peanut Allergy Severity Class and Score as determined by a Qualified Medical Professional.
It is not a clear if they are accessible to the reader in gross form, in order to verify the graphic and functional representations.
I could not find in the manuscript received tables 1 and 2, which makes the text less clear, but in the first impossible to publish without these tables.
For example, the chapter Data and features clearly show what are the independent parameters. A problem that would clearly make the author clarified is if the decision tool useful to the allergist doctor consists of a relationship of the type:
- in a decision scheme that, following the introduction of data required in the computer, decides with yes or no whether the patient presents a risk of allergy or not, possibly a value that indicates the intensity of the risk on a numerical scale.
Question 3
In the data chapter, the author specifies two types of data:
d1) All the molecular data that have been constantly acquired from each patient registered in the 2007 program: extended profiles of the component diagnosis, testing of the skin and in all primary plants and animal proteins, regardless of the patient's clinical history, the clinical history of the patient;
D2) Data includes markers of the immune system constantly acquired from each patient registered in the 2007 program: B diversity, cytokine production, basophilic indices, number of eosinophils and number of lymphocytes;
At the end of the given chapter, the author writes about the "final data set", which "includes the resemblance to allergens of plant and animal species that use data adopted from public fields, such as allergen nomenclature." That is understood by the "resemblance" with allergens ...? Then the author gives two databases at two internet addresses.
Unclear is the following: the data from the first two sets of data, are archived in a public database. Specifically, are the data accessed by the ML algorithm archived in the gross form in the public databases? Otherwise, how can this data be accessed by the reading public to verify the statements in the chapter of discussion and conclusions?
More precisely (now I mean the data and features chapter), where the readers can access the independent data listed in the Data and Features chapter:
• Patient's Personal Information, Including Gender, Age, and Weight;
• The Results of Up to 247 Blood and Skin Lab Tests Performed;
• Peanut Allergy Severity Class and Score as determined by A Qualified Medical Professional?
Question 4
In general, the scientific language can be adjusted, so that it is accessible to the non -specialists, at least partially. I noted in the manuscript reviewed some of these problems.
There are some abbreviations that are not explained. Maybe for specialists, it is not necessary, but for the general public (I refer to doctors with specializations of a different type) I think it is good to be explained. I noted in the manuscript reviewed some of these problems.
It is recommended to control the English language with the text publisher and another specialized publisher (for example Grammarly, free or licensed form).
An important problem to make the published article is that of the list of references and their summons in the text. I have not been able to identify in the text the quotation only for reference 9, citation I think, is inadequate as the form. The cities of the other sources must be highlighted, otherwise, they do not have their place on the list. The style of listing and citing the editor's references must be checked (it seems "Vancouver", in this case).
Question 5
The manuscript proposed for publication presents the results of interesting and useful research, with immediate applications, which must be validated over time, as the doctors will use the application.
As the main area of belonging, the research of a very wide category of research and applications, namely: Machine Learning in the Medical Field (Literature is very rich in this scientific field and is of more and more advanced quantification director of medical diagnosis). Originality comes from limiting the problem of allergies and more specific, research is done on patients suffering from allergies to peanuts proteins.
It is proposed to be published after a major review in which the following problems must be solved: 1) inclusion in the text of tables 1 and 2; 2) formatting the list of references to the editor's requirements, including the cities, so that the cities of the works included in the reference list are obvious. The unexpected works in the text are usually not admitted in the list of references; 3) clarification of the independent and dependent variables considered and the shape or shape of the ML results, usable in the practice of medical diagnosis as well as the clarifications required on the databases used for designing the algorithm and training the model; 4) refinement of scientific language; 5) a control of English (UK); 6) Clear explanation of the validation of the proposed algorithm (was done on the data with which the model was built, were other data used?) 7) In conclusions, a forecast should be exposed on the period of time necessary for acquiring the confidence among allergic doctors. Possible continuation directions may include expanding the database and applying the algorithm in other medical fields.
Lucrarea este valoroasă și se propune să fie publicată după o revizuire care răspunde la cele șapte probleme enumerate mai sus.
**********
6. PLOS authors have the option to publish the peer review history of their article (what does this mean?). If published, this will include your full peer review and any attached files.
If you choose “no”, your identity will remain anonymous but your review may still be made public.
Do you want your identity to be public for this peer review? For information about this choice, including consent withdrawal, please see our Privacy Policy.
Reviewer #1: No
Reviewer #2: Yes: Petru Cardei
**********
[NOTE: If reviewer comments were submitted as an attachment file, they will be attached to this email and accessible via the submission site. Please log into your account, locate the manuscript record, and check for the action link "View Attachments". If this link does not appear, there are no attachment files.]
While revising your submission, please upload your figure files to the Preflight Analysis and Conversion Engine (PACE) digital diagnostic tool, https://pacev2.apexcovantage.com/. PACE helps ensure that figures meet PLOS requirements. To use PACE, you must first register as a user. Registration is free. Then, login and navigate to the UPLOAD tab, where you will find detailed instructions on how to use the tool. If you encounter any issues or have any questions when using PACE, please email PLOS at figures@plos.org. Please note that Supporting Information files do not need this step.
Submitted filename: PONE-D-22-23228_reviewer.pdf
10.1371/journal.pone.0283141.r002Author response to Decision Letter 0Submission Version1
7 Dec 2022
All responses to reviewers are included in the uploaded document.
Submitted filename: Response to Reviewers.docx
10.1371/journal.pone.0283141.r003Decision Letter 1Asghari JafarabadiMohammadAcademic Editor2023Mohammad Asghari JafarabadiThis is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.Submission Version1
18 Jan 2023
PONE-D-22-23228R1Food Anaphylaxis Diagnostic Marker Compilation in Machine Learning Design and ValidationPLOS ONE
Dear Dr. Randhawa,
Thank you for submitting your manuscript to PLOS ONE. After careful consideration, we feel that it has merit but does not fully meet PLOS ONE’s publication criteria as it currently stands. Therefore, we invite you to submit a revised version of the manuscript that addresses the points raised during the review process.
Please submit your revised manuscript by Mar 04 2023 11:59PM. If you will need more time than this to complete your revisions, please reply to this message or contact the journal office at plosone@plos.org. When you're ready to submit your revision, log on to https://www.editorialmanager.com/pone/ and select the 'Submissions Needing Revision' folder to locate your manuscript file.
Please include the following items when submitting your revised manuscript:
A rebuttal letter that responds to each point raised by the academic editor and reviewer(s). You should upload this letter as a separate file labeled 'Response to Reviewers'.
A marked-up copy of your manuscript that highlights changes made to the original version. You should upload this as a separate file labeled 'Revised Manuscript with Track Changes'.
An unmarked version of your revised paper without tracked changes. You should upload this as a separate file labeled 'Manuscript'.
If you would like to make changes to your financial disclosure, please include your updated statement in your cover letter. Guidelines for resubmitting your figure files are available below the reviewer comments at the end of this letter.
If applicable, we recommend that you deposit your laboratory protocols in protocols.io to enhance the reproducibility of your results. Protocols.io assigns your protocol its own identifier (DOI) so that it can be cited independently in the future. For instructions see: https://journals.plos.org/plosone/s/submission-guidelines#loc-laboratory-protocols. Additionally, PLOS ONE offers an option for publishing peer-reviewed Lab Protocol articles, which describe protocols hosted on protocols.io. Read more information on sharing protocols at https://plos.org/protocols?utm_medium=editorial-email&utm_source=authorletters&utm_campaign=protocols.
We look forward to receiving your revised manuscript.
Kind regards,
Mohammad Asghari Jafarabadi
Academic Editor
PLOS ONE
Journal Requirements:
Please review your reference list to ensure that it is complete and correct. If you have cited papers that have been retracted, please include the rationale for doing so in the manuscript text, or remove these references and replace them with relevant current references. Any changes to the reference list should be mentioned in the rebuttal letter that accompanies your revised manuscript. If you need to cite a retracted article, indicate the article’s retracted status in the References list and also include a citation and full reference for the retraction notice.
[Note: HTML markup is below. Please do not edit.]
Reviewers' comments:
Reviewer's Responses to Questions
Comments to the Author
1. If the authors have adequately addressed your comments raised in a previous round of review and you feel that this manuscript is now acceptable for publication, you may indicate that here to bypass the “Comments to the Author” section, enter your conflict of interest statement in the “Confidential to Editor” section, and submit your "Accept" recommendation.
Reviewer #1: All comments have been addressed
Reviewer #2: All comments have been addressed
**********
2. Is the manuscript technically sound, and do the data support the conclusions?
The manuscript must describe a technically sound piece of scientific research with data that supports the conclusions. Experiments must have been conducted rigorously, with appropriate controls, replication, and sample sizes. The conclusions must be drawn appropriately based on the data presented.
Reviewer #1: Yes
Reviewer #2: Partly
**********
3. Has the statistical analysis been performed appropriately and rigorously?
Reviewer #1: Yes
Reviewer #2: Yes
**********
4. Have the authors made all data underlying the findings in their manuscript fully available?
The PLOS Data policy requires authors to make all data underlying the findings described in their manuscript fully available without restriction, with rare exception (please refer to the Data Availability Statement in the manuscript PDF file). The data should be provided as part of the manuscript or its supporting information, or deposited to a public repository. For example, in addition to summary statistics, the data points behind means, medians and variance measures should be available. If there are restrictions on publicly sharing data—e.g. participant privacy or use of data from a third party—those must be specified.
Reviewer #1: Yes
Reviewer #2: Yes
**********
5. Is the manuscript presented in an intelligible fashion and written in standard English?
PLOS ONE does not copyedit accepted manuscripts, so the language in submitted articles must be clear, correct, and unambiguous. Any typographical or grammatical errors should be corrected at revision, so please note any specific errors here.
Reviewer #1: Yes
Reviewer #2: (No Response)
**********
6. Review Comments to the Author
Please use the space provided to explain your answers to the questions above. You may also include additional comments for the author, including concerns about dual publication, research ethics, or publication ethics. (Please upload your review as an attachment if it exceeds 20,000 characters)
Reviewer #1: Thanks for addressing the comments. I think the authors should mention in discussion section that their algorithm works for ordinal variable, but might not work well for categorical/multinomial variables according to response to my question 1, so that people from other background who want to try this tool are fully aware of the limitation.
Reviewer #2: 1) Of the 9 works on the reference list, only the work [9] is cited in the text of the manuscript. In general, publishers demand that all the works from references be quoted in the text.
2) Even if the authors of the article state that the article is because they know all the abbreviations, I believe that the following abbreviations should be explained:
AUC, RAST, GLM.
Although the authors show that the article is for specialists who know the terms, you should not remove readers who read the article to try to use the techniques exposed in other scientific fields. However, the article contains specialized terms in biology and computer science. I suppose there are few specialists well familiar with both areas, so an explanation of the main specialized (specific) terms is timely.
**********
7. PLOS authors have the option to publish the peer review history of their article (what does this mean?). If published, this will include your full peer review and any attached files.
If you choose “no”, your identity will remain anonymous but your review may still be made public.
Do you want your identity to be public for this peer review? For information about this choice, including consent withdrawal, please see our Privacy Policy.
Reviewer #1: No
Reviewer #2: Yes: Petru Cardei
**********
[NOTE: If reviewer comments were submitted as an attachment file, they will be attached to this email and accessible via the submission site. Please log into your account, locate the manuscript record, and check for the action link "View Attachments". If this link does not appear, there are no attachment files.]
While revising your submission, please upload your figure files to the Preflight Analysis and Conversion Engine (PACE) digital diagnostic tool, https://pacev2.apexcovantage.com/. PACE helps ensure that figures meet PLOS requirements. To use PACE, you must first register as a user. Registration is free. Then, login and navigate to the UPLOAD tab, where you will find detailed instructions on how to use the tool. If you encounter any issues or have any questions when using PACE, please email PLOS at figures@plos.org. Please note that Supporting Information files do not need this step.
10.1371/journal.pone.0283141.r004Author response to Decision Letter 1Submission Version2
13 Feb 2023
The response is noted in the rebuttal letter.
Submitted filename: Rebuttal letter 2.docx
10.1371/journal.pone.0283141.r005Decision Letter 2Asghari JafarabadiMohammadAcademic Editor2023Mohammad Asghari JafarabadiThis is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.Submission Version2
3 Mar 2023
Food Anaphylaxis Diagnostic Marker Compilation in Machine Learning Design and Validation
PONE-D-22-23228R2
Dear Dr. Randhawa,
We’re pleased to inform you that your manuscript has been judged scientifically suitable for publication and will be formally accepted for publication once it meets all outstanding technical requirements.
Within one week, you’ll receive an e-mail detailing the required amendments. When these have been addressed, you’ll receive a formal acceptance letter and your manuscript will be scheduled for publication.
An invoice for payment will follow shortly after the formal acceptance. To ensure an efficient process, please log into Editorial Manager at http://www.editorialmanager.com/pone/, click the 'Update My Information' link at the top of the page, and double check that your user information is up-to-date. If you have any billing related questions, please contact our Author Billing department directly at authorbilling@plos.org.
If your institution or institutions have a press office, please notify them about your upcoming paper to help maximize its impact. If they’ll be preparing press materials, please inform our press team as soon as possible -- no later than 48 hours after receiving the formal acceptance. Your manuscript will remain under strict press embargo until 2 pm Eastern Time on the date of publication. For more information, please contact onepress@plos.org.
Kind regards,
Mohammad Asghari Jafarabadi
Academic Editor
PLOS ONE
Reviewers' comments:
Reviewer's Responses to Questions
Comments to the Author
1. If the authors have adequately addressed your comments raised in a previous round of review and you feel that this manuscript is now acceptable for publication, you may indicate that here to bypass the “Comments to the Author” section, enter your conflict of interest statement in the “Confidential to Editor” section, and submit your "Accept" recommendation.
Reviewer #1: All comments have been addressed
Reviewer #2: All comments have been addressed
**********
2. Is the manuscript technically sound, and do the data support the conclusions?
The manuscript must describe a technically sound piece of scientific research with data that supports the conclusions. Experiments must have been conducted rigorously, with appropriate controls, replication, and sample sizes. The conclusions must be drawn appropriately based on the data presented.
Reviewer #1: Yes
Reviewer #2: Yes
**********
3. Has the statistical analysis been performed appropriately and rigorously?
Reviewer #1: Yes
Reviewer #2: Yes
**********
4. Have the authors made all data underlying the findings in their manuscript fully available?
The PLOS Data policy requires authors to make all data underlying the findings described in their manuscript fully available without restriction, with rare exception (please refer to the Data Availability Statement in the manuscript PDF file). The data should be provided as part of the manuscript or its supporting information, or deposited to a public repository. For example, in addition to summary statistics, the data points behind means, medians and variance measures should be available. If there are restrictions on publicly sharing data—e.g. participant privacy or use of data from a third party—those must be specified.
Reviewer #1: Yes
Reviewer #2: Yes
**********
5. Is the manuscript presented in an intelligible fashion and written in standard English?
PLOS ONE does not copyedit accepted manuscripts, so the language in submitted articles must be clear, correct, and unambiguous. Any typographical or grammatical errors should be corrected at revision, so please note any specific errors here.
Reviewer #1: Yes
Reviewer #2: Yes
**********
6. Review Comments to the Author
Please use the space provided to explain your answers to the questions above. You may also include additional comments for the author, including concerns about dual publication, research ethics, or publication ethics. (Please upload your review as an attachment if it exceeds 20,000 characters)
Reviewer #1: Thanks for addressing the comments. I think it will have a lot of good impact and keep up the good work.
Reviewer #2: Dear Authors
Referring to:
PONE-D-22-23228R2
In the next table, you have all my observations regarding the article. Essentially it can be published, but please consider the opportunity of the following suggestions.
Suggestions and observation to revision 2 for the paper:
Obs1) We ask the authors to specify if in fig. 1, 2 and 3, on the vertical axis, read the frequency or frequency logarithm. If the frequency logarithm is, please specify the base of the logarithm.
Obs2) It is recommended to control the English language for the entire manuscript because there are still control programs that claim errors and simplest expressions:
1) https://quillbot.com/grammar-check
2) https://www.grammarly.com/gramar-check
Obs3) Plagiaristic check with
https://smallseotools.com/plagiarism-checker/
show that:
1- Introduction 13% - plagiarism. Some sources are specified in references, others are not in the reference list. The sources that are not in references can be included, which would also increase the list of references.
2- Material and Methods, Data 10% plagiarism. A source not included in the references. Can be included.
3- A Machine Learning algorithm for allergen score prediction , 3% plagiarism. . A source not included in the references. Can be included.
Petru Cardei
**********
7. PLOS authors have the option to publish the peer review history of their article (what does this mean?). If published, this will include your full peer review and any attached files.
If you choose “no”, your identity will remain anonymous but your review may still be made public.
Do you want your identity to be public for this peer review? For information about this choice, including consent withdrawal, please see our Privacy Policy.
Reviewer #1: Yes: Shuai Wang
Reviewer #2: Yes: Petru Cardei
**********
Submitted filename: Observation to revision 2.docx
10.1371/journal.pone.0283141.r006Acceptance letterAsghari JafarabadiMohammadAcademic Editor2023Mohammad Asghari JafarabadiThis is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
14 Mar 2023
PONE-D-22-23228R2
Food anaphylaxis diagnostic marker compilation in machine learning design and validation
Dear Dr. Randhawa:
I'm pleased to inform you that your manuscript has been deemed suitable for publication in PLOS ONE. Congratulations! Your manuscript is now with our production department.
If your institution or institutions have a press office, please let them know about your upcoming paper now to help maximize its impact. If they'll be preparing press materials, please inform our press team within the next 48 hours. Your manuscript will remain under strict press embargo until 2 pm Eastern Time on the date of publication. For more information please contact onepress@plos.org.
If we can help with anything else, please email us at plosone@plos.org.
Thank you for submitting your work to PLOS ONE and supporting open access.