Musa, Ndidiamaka

Objectives: To deploy machine learning tools (random forests) to develop a model that reliably predicts hospital mortality in children with acute infections residing in low- and middle-income countries, using age and other variables collected at hospital admission. Design: Post hoc analysis of a single-center, prospective, before-and-after feasibility trial. Setting: Rural district hospital in Rwanda, a low-income country in Sub-Sahara Africa. Patients: Infants and children greater than 28 days and less than 18 years of life hospitalized because of an acute infection. Interventions: None. Measurements and Main Results: Age, vital signs (heart rate, respiratory rate, and temperature) capillary refill time, altered mental state collected at hospital admission, as well as survival status at hospital discharge were extracted from the trial database. This information was collected for 1,579 adult and pediatric patients admitted to a regional referral hospital with an acute infection in rural Rwanda. Nine-hundred forty-nine children were included in this analysis. We predicted survival in study subjects using random forests, a machine learning algorithm. Five prediction models, all including age plus two to five other variables, were tested. Three distinct optimization criteria of the algorithm were then compared. The in-hospital mortality was 1.5% (n = 14). All five models could predict in-hospital mortality with an area under the receiver operating characteristic curve ranging between 0.69 and 0.8. The model including age, respiratory rate, capillary refill time, altered mental state exhibited the highest predictive value area under the receiver operating characteristic curve 0.8 (95% CI, 0.78–0.8) with the lowest possible number of variables. Conclusions: A machine learning-based algorithm could reliably predict hospital mortality in a Sub-Sahara African population of 949 children with an acute infection using easily collected information at admission which includes age, respiratory rate, capillary refill time, and altered mental state. Future studies need to evaluate and strengthen this algorithm in larger pediatric populations, both in high- and low-/middle-income countries.

Objective: To evaluate whether a focused education program and implementation of a treatment bundle increases the rate of early evidence-based interventions in patients with acute infections. Design: Single-center, prospective, before-and-after feasibility trial. Setting: Emergency department of a sub-Saharan African district hospital. Patients: Patients > 28 days of life admitted to the study hospital for an acute infection. Interventions: The trial had three phases (each of four months). Interventions took place during the second (educational program followed by implementation of the treatment bundle) and third (provision of resources to implement treatment bundle) phases. Measurements and Main Results: Demographic, clinical, and laboratory data were collected at study enrollment; 24, 48, and 72 hours after hospital admission; and at discharge. A total of 1,594 patients were enrolled (pre-intervention, n = 661; intervention I, n = 531; intervention II, n = 402). The rate of early evidence-based interventions per patient during Intervention Phase I was greater than during the pre-intervention phase (74 ± 17 vs. 79 ± 15%, p < 0.001). No difference was detected when data were compared between Intervention Phases I and II (79 ± 15 vs. 80 ± 15%, p = 0.58). No differences in the incidence of blood transfusion (pre-intervention, 6%; intervention I, 7%; intervention II, 7%) or severe adverse events in the first 24 hours (allergic reactions: pre-intervention, 0.2%; intervention I, 0%; intervention II, 0%; respiratory failure: pre-intervention, 2%; intervention I, 2%; intervention II, 2%; acute renal failure: pre-intervention, 2%; intervention I, 2%; intervention II, 1%) were observed. Conclusions: Our results indicate that a focused education program and implementation of an infection treatment bundle in clinical practice increased the rate of early evidence-based interventions in patients with acute infections (mostly malaria) admitted to a sub-Saharan African district hospital. Provision of material resources did not further increase this rate. While no safety issues were detected, this could be related to the very low disease severity of the enrolled patient population (www.clinicaltrials.gov: NCT02697513).