Tremendous progress has been made worldwide in child survival in recent decades. Among children under-5, nine percent of children died in 1990 compared to four percent in 2017. The under-five mortality rate fell from 93 deaths per 1,000 live births in 1990 to 39 in 2017 [1].

Despite all this progress, 5.4 million children under-5 still die each year, 80% of them in sub-Saharan Africa and South Asia. Almost half of these deaths occur among malnourished children [2–4]. Malnutrition is a serious public health concern in low- and middle-income countries, and is the focus of the first World Health Organization (WHO) Millennium Development Goal. In its acute form, it affects about 50 million children under-5 worldwide, including 48 million in Africa and Asia [4].

Acute malnutrition is subdivided into 2 categories: (i) Moderate Acute Malnutrition (MAM), defined as mid-upper arm circumference (MUAC) between 115 and 125 mm in children aged 6–59 months; or a weight-for-height/length z-score between –2 and –3 according to the 2006 WHO growth standards; with absence of edema; (ii) Severe Acute Malnutrition (SAM), defined by two distinct clinical entities: (a) non-edematous malnutrition (marasmus), defined as MUAC < 115 mm in children aged 6–59 months; or a weight-for-height/length z-score < –3 according to the 2006 WHO growth standards; (b) edematous malnutrition (kwashiorkor), defined by bilateral pitting edema [5].

SAM is further classified according to the presence or absence of medical complications. Uncomplicated SAM is defined as SAM with no apparent signs of infection nor other signs requiring hospitalization, and with adequate appetite. Complicated SAM is defined as SAM with clinical signs of infection, metabolic disorders, severe edema, hypothermia, vomiting, severe dehydration, profound anemia or lack of appetite [5].

SAM impairs life, cognitive and neurodevelopmental prognosis of children, especially in in low- and middle-income countries. The shorter-term prognosis of SAM depends on the type of malnutrition. In uncomplicated SAM, the mortality rate is < 5% while it varies from 10 to 40% in complicated SAM [6]. Further, previous reports have shown high post-discharge mortality following in-hospital management of diarrhea-SAM, HIV infection-SAM and pneumonia-SAM comorbidities respectively [7–9]. The FuSAM (Follow Up of Severely Acute Malnourished Children) study reported a mortality rate of 25% over a year after the SAM treatment among children followed in inpatient-based SAM treatment centre in Blantyre (Malawi). The risk of mortality after hospital discharge was fourfold higher for HIV-SAM compared with HIV-negative children with SAM [10]. In addition, ChroSAM (Chronic disease Outcomes after Severe Acute Malnutrition) study, which followed Malawian children with SAM, seven years post-discharge in the same centre, reported that children had poorer growth, body composition and physical function compared with siblings and community controls. These parameters are all risk factors of future cardiovascular and metabolic disease [11].

According to World Food Program (WFP), more than 6 million people are in a situation of acute food insecurity and livelihood crisis in the Democratic Republic of Congo (DRC) [12]. The combination of persistent violent armed conflicts, massive populations displacements, poor or inexistent infrastructures and widespread deterioration of productive assets have significantly affected food security in the DRC, and particularly in Eastern provinces, over the past two decades [12]. The impact of all these on children under-5 in the South Kivu province are alarming: the stunted rate of 48%, the wasting rate of 3% and the under-5 mortality rate of 4% [13].

Since 2000, joint efforts of the WHO and the United Nations Children’s Fund (UNICEF) allowed the standardization of the management of acute malnutrition which improved outcomes and prevented complications [14, 15]. Following these recommendations, the Ministry of Public Health of DRC has implemented the Integrated Management of Acute Malnutrition programme (Prise en Charge Intégrée de la Malnutrition Aigüe, PCIMA) [16]. PCIMA approach encompasses three components: (i) community outreach and mobilization; (ii) outpatient management of SAM without medical complications; and (iii) inpatient management of SAM with medical complications. Children with complicated SAM are managed in Intensive Therapeutic and Feeding Unit, which is one of the units of the pediatric department.

This study aimed to describe the treatment outcomes and to identify risk factors associated with mortality for a cohort of children admitted with SAM in a Nutritional Center located in the South Kivu province of DRC.

We analyzed medical records of 633 severely malnourished children admitted to SJNC during study period. Their characteristics are summarized in Table 1. SAM was more prevalent among children aged 6 to 59 months (512/625; 81.9%) compared to those combined under 6 months and over 59 months (p<0.05). Three hundred and thirty-two (51.2%) children were male and the sex-ratio (M/F) was 1.1. More than half of the severely malnourished children (358/618; 58.0%) came from urban areas. Overall, edematous malnutrition was the most prevalent form of SAM, found in 408 (65.3%) children.

Four hundred (63.2%) children were brought to health facility for consultation more than 2 weeks after the onset of main external malnutrition signs (thinning, edema or yellow-coloured hair). The median time between the onset of main external malnutrition signs and the referral to health facilities was 36 days (range: 7–85). It was more important for children coming from rural areas (42 days) than those coming from urban ones (22 days) (p<0.05).

The anthropometric parameters of children late referred to the health facility (more than one month) were severely deteriorated (MUAC < 110 mm for non-edematous malnutrition and edema +++ for edematous malnutrition), compared to those of children early referred to the health facility (p<0.05).

Four hundred and twenty (74.0%) children had received antimicrobials before admission to SJNC, including 175 (30.9%) at home. As shown in Fig 1, ampicillin and gentamycin were the most commonly administered antimicrobials at health centre (26%), while amoxicillin was the most commonly administered antimicrobial at home (14%). No child with uncomplicated SAM received antimicrobials before admission to SJNC.

Fig 2 shows the distribution of main infectious diagnoses of severely malnourished children at SJNC. Overall, respiratory tract infections (16%), bacteremia (6%), infectious diarrhea (5%) and malaria (5%) accounted for 32% of confirmed diagnosis.

The average daily weight gain was 9.2 g/kg/day, higher in children with marasmus (10.3g/kg/day) than in children with kwashiorkor (8.2g/kg/day) (p<0.05). The median length of stay was 17 days (range: 8–28), longer in children with kwashiorkor (20 days) than in those with marasmus (11 days) (p < 0.05). Fifty-eight (9.2%) children died. As shown in Table 2, SJNC outcomes variables were comparable with that of international sphere standard (p> 0.05).

Variables associated with mortality at multivariable logistic regression included time between the onset of main external malnutrition signs and first consultation, MUAC and HIV infection. Severely malnourished children with delayed presentation to the health facilities (> 14 days) after the onset of main external malnutrition signs were 2.03 times higher odds of death than those referred less than 14 days [AOR = 2.03 at 95%CI (1.12, 3.68)]. The odds of death was 1.91 times higher for children with MUAC < 115 mm than for those with MUAC ≥ 115 mm [AOR = 1.91 at 95% CI (1.05, 3.50)]. Severely malnourished children infected with HIV were 3.90 times more likely to die compared to their counterparts [AOR = 3.90 at 95% CI (2.80, 9.41)] (Table 3).

The findings of this study provide preliminary data on factors associated with the mortality of severely malnourished children admitted as inpatients in the context of a food security crisis. Despite the unavailability of therapeutic supplies (RUTF, F-75 and F-100) at SJNC and their substitution by whole milk / MASOSO-vegetal oil-sugar preparations, the average daily weight gain of our study population was comparable with that of international sphere standard.

Several recent studies showed the non-inferiority of cereal-based formulas (maize, sorghum, soya) mixed with vegetable oil and sugar, in comparison to WHO conventional preparation, in the diet of severely malnourished children. A study conducted in North Kivu (Eastern DRC) comparing the efficacy and safety of two recipes (cow milk with porridge made of maize, soybean, vegetal oil and sugar versus WHO conventional preparation) among two groups of severely malnourished children, reported no significant difference between the two groups in terms of weight changes, edema resolution, gastrointestinal tolerability and clinical outcome over 21 days (p > 0.05) [27].

A non-inferiority, randomized controlled clinical trial was conducted in a rural area of South Kivu (Eastern DRC) to compare the efficacy of soya-maize-sorghum RUTF with that of standard peanut paste–based RUTF for treating SAM. Intention-to-treat and per-protocol analyses showed non-inferiority of soya-maize-sorghum RUTF compared with peanut paste–based RUTF for the recovery rate, weight gain and length of stay in children < 24 months of age [28].

Another non-inferiority individually randomized controlled efficacy clinical trial was conducted in Malawi to compare the efficacy of milk-free soya, maize, and sorghum enriched with crystalline amino acids to the standard peanut and milk RUTF. Intention-to-treat and per-protocol analyses showed non-inferiority for recovery rates and length of stay in children aged 24–59 months and 6–23 months between these two RUTFs [29].

The nutrient density of peanut and milk RUTF equivalent to WHO F-100 milk [14] ensures high rates of recovery and weight gain and low fatality rates [30, 31]. Nevertheless, peanut and milk RUTF high milk content (25%) makes it very expensive for sustainable use in low-and middle-income countries. About 50% of peanut and milk RUTF is still produced in high-income countries and imported into low-and middle-income countries where it is needed. The high cost of current standard RUTF (47$ USD for each child treated) remains, therefore, the main reason it is unavailable in resource-poor settings [32, 33]. The recipes based on soya, maize, and sorghum, vegetable oil and sugar has shown great promise and has the potential to provide a substantially lower-cost alternative, with adequate nutritional recovery.

The death rate found in our study was close to what is observed in similar settings. It remains, however, high compared to the PCIMA standards. Indeed, in non-emergency situations, PCIMA defines a mortality rate < 5% as an acceptable threshold [16]. This high death rate could be due to several barriers, often described in rural areas of low-and middle-income countries, including delayed referral to health facilities, mothers' lack of awareness of the signs of malnutrition, self-medication, or difficulties in accessing the health centre due to lack of transport. WHO often attributes infant or maternal mortality in low-and middle-income countries to the phenomenon known as "three delays": (i) delay in deciding to seek care, (ii) delay in identifying and reaching health facility, and (iii) delay in receiving adequate and appropriate treatment [34].

As in this study, MUAC as predictor of mortality in children with SAM has been described elsewhere [35–39]. Several studies [40–44] showed that MUAC may be used in preference over weight-for-height z-score for predicting the risk of death in under-5 children. In addition, these studies documented that use of MUAC < 115 mm alone may be better than weight-for-height z-score < -3 in identifying children at high risk of death. Recent evidence based on meta-analysis highlights that children with a weight-for-height z-score < -3 have about the same or higher risk of death as children with a MUAC < 115 mm. They both are at substantial risk of death, and neither should be omitted from protocols aimed at diagnosis and treatment of all SAM cases [45].

Our data showed a negative influence of HIV-malnutrition comorbidity on mortality. Delayed diagnosis and antiretroviral treatment (ART) initiation are factors that worsen these children's life-threatening prognosis. Indeed, for most mothers and children admitted to SJNC, HIV status is often unknown before admission. Secondly, almost all health facilities in Eastern DRC do not yet have early virologic diagnostic tests for HIV infection. HIV infection diagnosis is established either on the basis of positive HIV serology after 18 months of age or on the basis of clinical signs suggesting HIV infection before 18 months of age, according to WHO classification for children born to HIV-positive mothers. Finally, when HIV infection is diagnosed, ART is started only after these children have been stabilized nutritionally, according to the guidelines of the national AIDS care programme in DRC.

Recent WHO guidelines recommend early ART for all children, regardless of their clinical and immune status [46]. The rationale behind early ART for all children is that (i) early ART decreases significantly the mortality rate and improves better growth response than deferred ART (waiting for the CD4 count falls below 15%) [47]; (ii) early ART mitigates the negative effects of HIV infection on growth and pubertal and nervous system development [48–54] and (iii) it promotes immune recovery [55].

About 50% of admission diagnoses were not confirmed by radiography or laboratory tests. This is a major handicap in the framework of epidemiological surveillance. Where available, laboratory confirmation of clinical diagnoses is important to improve the accuracy of surveillance systems. In addition, although tuberculosis (TB) is common in immunodeficiency situations, including malnutrition, no children had a confirmed diagnosis of TB. In SJNC, treatment for TB is guided by a presumptive diagnosis based on the Keith-Edward score [56]. The factors contributing to uncertainties concerning incidence of tuberculosis in severely malnourished young children is related to the challenge in confirming a diagnosis: (i) difficulties in obtaining high quality specimens; (ii) children commonly have a poor bacillary count and many are negative on culture; (iii) the lack of mycobacterial culture facilities in settings where tuberculosis and malnutrition are endemic [57]. The Xpert MTB/RIF assay, a recent, rapid diagnostic test for the detection of M. tuberculosis and rifampicin resistance, has demonstrated encouraging results in the diagnosis of pulmonary tuberculosis in children [58]. Unfortunately, it is the appanage of only a few countries in low-income countries.

Our study reflects the current nutritional situation of the South-Kivu province in DRC, with a high burden of children affected by malnutrition. Particular emphasis should be placed on partnering with communities to improve recognition of the signs of malnutrition and on the critical importance of early entry into the health system. While HIV incidence in DRC is still low (0.21%) [59], its impact on mortality among severely malnourished children is increased due to the limited access to HIV testing and antiretroviral therapy.