We used an application layer that provides online services accessed through the World Wide Web or through mobile applications (Android and iOS). The system was developed using hypertext markup language and JavaScript for the interface and for the usability of the hypertext preprocessor tool employed to analyse user data. Structured query language (SQL) was used for the database and MySQL version 5.0.51, as well as SQLITE for systems management because it requires few hardware resources.

For the user requirements, an HTML 5/CSS 3 compatible browser is required and must be able to navigate in a web environment with a minimum resolution of 1200 x 780 pixels. To use this web software version, no installation is required: the user only has to enter the link www.usp.br/labimph/soped. To run the app, the user needs to have Android 4.3 or higher and to download the application from the same link, in the ‘download our application’. No operating system requirement is made. In both cases, users need Internet access. The software is available in English and Portuguese, but it can be translated into any language. The software was created with the intention of being used independently by a person with DM at his or her own convenience, but also has the potential to be a tool that facilitates primary and secondary health services worldwide.

The software is in its first version. We intend to revise it when including other languages while keeping the software free and public. All access codes and algorithms used in the software are available as supplemental material (S1 Appendix, S2 Appendix).

In the development of this software (Figs 1 and 2), three main aspects were considered: (i) foot care recommendations and information about DM and DPN; (ii) self-assessment of feet according to the main foot alterations of DM and DPN (calluses, cracks, deformities and soft-tissue lesions, among others); and (iii) customised foot–ankle exercises to strengthen muscles, increase range of motion and improve functionality.

A therapeutic exercise protocol was developed (S3 Appendix) to provide autonomy for the individuals during exercise without the need for professional supervision. The protocol is simple, contains clear written instructions (as well as video and audio) and preserves the safety of the target population during exercise. Furthermore, it establishes the training volume, progression criteria and guidelines for discontinuing the protocol.

A singular feature of this tool is that it personalises the progress of a foot–ankle exercise programme based on individual capabilities, which is similar to conventional physiotherapy. To include this feature, we incorporated a visual analogue scale (Fig 1D), which is represented by a ruler that quantifies the level of effort required to perform each exercise so that daily progress can be customised based on one’s results.

To personalise the exercises, a progression algorithm was created from the perceived effort of each user, who could progress in the exercise programme’s difficulty, maintain it or return to the previous stage in accordance with the following criteria: with a 0.0 to 2.0 score in the visual scale, the user progresses to the next level of effort on the following day; from 2.1 to 7.0, the user advances to the next level after 2 days at the present level; from 7.1 to 10, the user returns to the previous level.

The physiotherapeutic foot–ankle exercise protocol is based on previous clinical trials [7,16]. It was designed following three criteria established in a supervised, face-to-face intervention: (a) muscle stretching (20 exercises); (b) strengthening of the intrinsic foot muscles (40 exercises); and (c) strengthening of the extrinsic foot–ankle muscles and functional exercises such as balance and gait training (44 exercises). In total, 39 different exercises were chosen, and when including their sublevels of progression, a total of 104 different exercises can be completed. For each session, only eight exercises are combined to provide the three previously described criteria. The exercises are recommended to be performed twice or three times weekly. To avoid monotony and enhance motivation, the exercises always change from session to session, and the maximum duration of a session is no longer than 20 minutes. Those features also prevent the users from doing excessive effort, because they also limit the uncontrolled progression, as explained: the exercises should only be done twice or three times a week; no more than eight exercises each day is allowed; and the individual difficulty is regulated by the effort scale.

Some exercises have sublevels that correspond to increases in the load, number of repetitions or time duration. However, each exercise is different and may contain only one level or up to five levels of difficulty. For each exercise, the user attributes the effort, and the progression is made for this exercise. So if a session is composed of eight exercises, the user may progress in two of these exercises but may stay at the same level for six of the exercises in the next session. Therefore, individual physical capacities are respected, and one exercise will not block the progression of other exercises that are easier to perform. Therefore, the user’s overall progression is not classified as levels but rather follows the reward system of trophies and items presented in Fig 3.

The following muscle groups are targeted in the protocol: medial-plantar aspect: abductor hallucis, flexor halluces brevis and adductor hallucis; lateral plantar aspect: abductor digiti minimi, flexor digiti minimi brevis and opponens digiti minimi; middle-plantar aspect: flexor digitorum brevis, quadratus plantae, lumbrical muscles, plantar interosseous and dorsal interosseous muscles; dorsal-foot aspect: extensor digitorum brevis and extensor halluces brevis. The following joints are targeted in the protocol: talocrural, tarsometatarsals, interphalangeals and metatarsophalangeals.

The Delphi method was used for validation[28]. The process occurred concurrently with a judging panel of 20 people with DM (Fig 4) and another panel of nine health professionals (Fig 4) specialising in treating people with DM and DPN. The judges had access to the desktop and mobile versions of the software, and their responses were given for both applications. The judges used the software for a period between 30 and 45 days, twice or three times a week. This time period was chosen because at least a usage of 30 days represent one third of the entire protocol, and is representative enough of the functionality of the software. During this time, judges could properly verify all sessions and features of the SOPED that are: fulfill personal information; read all the instructions and information about the disease; fulfill the feet physical inspection; read and practice many exercises; use the effort scale in different situations and with different exercises; verify the progression, maintenance or regression of the exercises according to their individual capacities; use the forum; receive the rewards; verify the safety information; and navigate through different sessions of the SOPED. In addition, all the judges received an attached file with detailed descriptions of all the exercises included in the software, whit their respective training volume and progression, and therefore could analyze all the protocol without the need to perform every exercises for three months.

The panel of users comprised six men (30%) and 14 women (70%) with a mean age of 41.4 years (21–65 years), mean DM diagnosis of 14 years (1–33 years) and normal cognitive performance as assessed by the Mini Mental State Examination (score media of 28.5). Depression level was assessed using Beck’s Depression Inventory, in which one of 20 subjects exhibited a score of 27 (moderate level), six a score of more than 4 (minimum level) and four a score of more than 12 (mild level). Educational level was 20% (4/20) for high school and 80% (16/20) for university level. In addition, 80% (16/20) of the patients were working. There were 12 patients with Diabetes but without neuropathy, confirmed by the Michigan Neuropathy Screening Instrument (MNSI) and 8 patients with previous confirmed diagnostic of neuropathy (MNSI and physical examination from the database of the research center). Other eligibility criteria for users were the following: both sexes: having type 1 or type 2 DM; 18 years old or more: free of tissue injury at the time of execution of the exercises; be able to use the software alone; or have someone to help at all times; and having completed schooling equal to or higher than the fourth year of elementary school.

The panel of specialists comprised nine women, including one psychologist, three physiotherapists (two specialised in clinical diabetes care, one specialised in biomechanics and musculoskeletal function of diabetic neuropathy), one podiatrist nurse (specialised in podiatric care and diabetic foot), one physician/endocrinologist (specialised in diabetic foot), one occupational therapist and two physical education professionals (one specialised in clinical and gait analysis of diabetic foot). The mean age was 45.44 years (35–59 years), and the mean experience in the treatment of people with DM was 18.8 years. For specialist selection, résumés were assessed using an adaptation of the Fehring criteria[29] (Table 1), which allows for a minimum score of 5 points. The mean adapted Fehring score was 9.7 out of 14. The other eligibility criteria for the specialists are described in Table 1 and are based on adapted Fehring criteria.

The first round of assessment consisted of a questionnaire containing 16 items that was based on a 5-point primar scale (I completely agree, I agree, I neither agree nor disagree, I disagree and I totally disagree) in which the comments considered important to each member of the panel were obtained for each item. The instrument that was built to discern the specialists’ opinions addressed the following matters: objective of the web software; fitness of the language to the population; amount and quality of information; contribution of exercises to decreasing foot deficits caused by DM; and whether the tool promoted daily exercise. The instrument that was built to elicit the user’s opinion addressed the same matters, but also aimed to determine whether the user correctly understood the exercise performance.

For the first round, both suggestions from specialists and users were evaluated only by the researchers, and their suggestions and recommended changes were incorporated into the software by the researchers. After incorporating the suggestions, the new version of the software was submitted again, in a second round, to the same panel members who evaluated the modifications in the software. At this stage, the changes should be approved or not, until a minimum of 70% was reached, and then the final version of the web software was determined.

The data were analysed using descriptive statistics, means, relative and absolute frequencies and the content validation index (CVI). The CVI measures the proportion of items that the judges are in agreement. The content validity is determined by the proportion of judges that score items as being relevant or representative[30]. That correspond to a score of 4 or 5 (‘agree’ and ‘strongly agree’) on a Likert scale out of all possible answers (the others being ‘disagree’, ‘strongly disagree’, and ‘don’t agree nor disagree’). The score is calculated by the sum of the agreement of the items marked 4 or 5[31]. The CVI was calculated only for the first round. For the final validation, after the second round, we used a 70% approval consensus criterion for all modifications implemented in the software.

This research was approved by the Research Ethics Committee of the School of Medicine of the University of São Paulo (Approval No. 2.262.357). Informed consent was obtained from all participants included in the design process.