Ogwel Billy, Mzazi Vincent H, Nyawanda Bryan O, Otieno Gabriel, Tickell Kirkby D, Omore Richard
Kenya Medical Research Institute-Center for Global Health Research (KEMRI-CGHR) Kisumu Kenya.
Department of Information Systems University of South Africa Pretoria South Africa.
Learn Health Syst. 2024 Dec 26;9(2):e10478. doi: 10.1002/lrh2.10478. eCollection 2025 Apr.
Mortality prediction scores for children admitted with diarrhea are unavailable, early identification of at-risk patients for proper management remains a challenge. This study utilizes machine learning (ML) to develop a highly sensitive model for timelier identification of at-risk children admitted with acute gastroenteritis (AGE) for better management.
We used seven ML algorithms to build prognostic models for the prediction of mortality using de-identified data collected from children aged <5 years hospitalized with AGE at Siaya County Referral Hospital (SCRH), Kenya, between 2010 through 2020. Potential predictors included demographic, medical history, and clinical examination data collected at admission to hospital. We conducted split-sampling and employed tenfold cross-validation in the model development. We evaluated the sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and the area under the curve (AUC) for each of the models.
During the study period, 12 546 children aged <5 years admitted at SCRH were enrolled in the inpatient disease surveillance, of whom 2271 (18.1%) had AGE and 164 (7.2%) subsequently died. The following features were identified as predictors of mortality in decreasing order: AVPU scale, Vesikari score, dehydration, sunken eyes, skin pinch, maximum number of vomits, unconsciousness, wasting, vomiting, pulse, fever, sunken fontanelle, restless, nasal flaring, diarrhea days, stridor, <90% oxygen saturation, chest indrawing, malaria, and stunting. The sensitivity ranged from 46.3%-78.0% across models, while the specificity and AUC ranged from 71.7% to 78.7% and 56.5%-82.6%, respectively. The random forest model emerged as the champion model achieving 78.0%, 76.6%, 20.6%, 97.8%, and 82.6% for sensitivity, specificity, PPV, NPV, and AUC, respectively.
This study demonstrates promising predictive performance of the proposed algorithm for identifying patients at risk of mortality in resource-limited settings. However, further validation in real-world clinical settings is needed to assess its feasibility and potential impact on patient outcomes.
目前尚无针对腹泻住院儿童的死亡率预测评分，早期识别高危患者以进行恰当管理仍是一项挑战。本研究利用机器学习（ML）开发一种高度敏感的模型，以便更及时地识别因急性胃肠炎（AGE）住院的高危儿童，从而实现更好的管理。
我们使用七种ML算法，利用从2010年至2020年期间在肯尼亚西亚亚县转诊医院（SCRH）因AGE住院的5岁以下儿童收集的去识别化数据，构建预测死亡率的预后模型。潜在预测因素包括入院时收集的人口统计学、病史和临床检查数据。我们在模型开发中进行了拆分抽样并采用十折交叉验证。我们评估了每个模型的敏感性、特异性、阳性预测值（PPV）、阴性预测值（NPV）和曲线下面积（AUC）。
在研究期间，SCRH收治的12546名5岁以下儿童纳入了住院疾病监测，其中2271名（18.1%）患有AGE，164名（7.2%）随后死亡。以下特征被确定为死亡率预测因素，按降序排列：AVPU量表、韦西卡里评分、脱水、眼窝凹陷、皮肤捏起试验、呕吐最大次数、昏迷、消瘦、呕吐、脉搏、发热、囟门凹陷、烦躁不安、鼻翼扇动、腹泻天数、喘鸣、氧饱和度<90%、胸廓凹陷、疟疾和发育迟缓。各模型的敏感性范围为46.3% - 78.0%，而特异性和AUC分别为71.7%至78.7%和56.5% - 82.6%。随机森林模型成为最佳模型，其敏感性、特异性、PPV、NPV和AUC分别达到78.0%、76.6%、20.6%、97.8%和82.6%。
本研究表明，所提出的算法在资源有限的环境中识别有死亡风险患者方面具有良好的预测性能。然而，需要在现实世界的临床环境中进行进一步验证，以评估其可行性以及对患者结局的潜在影响。
