ePOCT+ and the medAL-suite: Development of an electronic clinical decision support algorithm and digital platform for pediatric outpatients in low- and middle-income countries

The Tools for Integrated Management of Childhood Illness (TIMCI) study protocol: a multi-country mixed-method evaluation of pulse oximetry and clinical decision support algorithms

Effective and sustainable strategies are needed to address the burden of preventable deaths among children under-five in resource-constrained settings. The Tools for Integrated Management of Childhood Illness (TIMCI) project aims to support healthcare providers to identify and manage severe illness, whilst promoting resource stewardship, by introducing pulse oximetry and clinical decision support algorithms (CDSAs) to primary care facilities in India, Kenya, Senegal and Tanzania. Health impact is assessed through: a pragmatic parallel group, superiority cluster randomised controlled trial (RCT), with primary care facilities randomly allocated (1:1) in India to pulse oximetry or control, and (1:1:1) in Tanzania to pulse oximetry plus CDSA, pulse oximetry, or control; and through a quasi-experimental pre-post study in Kenya and Senegal. Devices are implemented with guidance and training, mentorship, and community engagement. Sociodemographic and clinical data are collected from caregivers and records of enrolled sick children aged 0-59 months at study facilities, with phone follow-up on Day 7 (and Day 28 in the RCT). The primary outcomes assessed for the RCT are severe complications (mortality and secondary hospitalisations) by Day 7 and primary hospitalisations (within 24 hours and with referral); and, for the pre-post study, referrals and antibiotic. Secondary outcomes on other aspects of health status, hypoxaemia, referral, follow-up and antimicrobial prescription are also evaluated. In all countries, embedded mixed-method studies further evaluate the effects of the intervention on care and care processes, implementation, cost and cost-effectiveness. Pilot and baseline studies started mid-2021, RCT and post-intervention mid-2022, with anticipated completion mid-2023 and first results late-2023. Study approval has been granted by all relevant institutional review boards, national and WHO ethical review committees. Findings will be shared with communities, healthcare providers, Ministries of Health and other local, national and international stakeholders to facilitate evidence-based decision-making on scale-up.Study registration: NCT04910750 and NCT05065320.

A digital health algorithm to guide antibiotic prescription in pediatric outpatient care: a cluster randomized controlled trial

Excessive antibiotic use and antimicrobial resistance are major global public health threats. We developed ePOCT+, a digital clinical decision support algorithm in combination with C-reactive protein test, hemoglobin test, pulse oximeter and mentorship, to guide health-care providers in managing acutely sick children under 15 years old. To evaluate the impact of ePOCT+ compared to usual care, we conducted a cluster randomized controlled trial in Tanzanian primary care facilities. Over 11 months, 23,593 consultations were included from 20 ePOCT+ health facilities and 20,713 from 20 usual care facilities. The use of ePOCT+ in intervention facilities resulted in a reduction in the coprimary outcome of antibiotic prescription compared to usual care (23.2% versus 70.1%, adjusted difference -46.4%, 95% confidence interval (CI) -57.6 to -35.2). The coprimary outcome of day 7 clinical failure was noninferior in ePOCT+ facilities compared to usual care facilities (adjusted relative risk 0.97, 95% CI 0.85 to 1.10). There was no difference in the secondary safety outcomes of death and nonreferred secondary hospitalizations by day 7. Using ePOCT+ could help address the urgent problem of antimicrobial resistance by safely reducing antibiotic prescribing. Clinicaltrials.gov Identifier: NCT05144763.

Digitalizing Clinical Guidelines: Experiences in the Development of Clinical Decision Support Algorithms for Management of Childhood Illness in Resource-Constrained Settings

Clinical decision support systems (CDSSs) can strengthen the quality of integrated management of childhood illness (IMCI) in resource-constrained settings. Several IMCI-related CDSSs have been developed and implemented in recent years. Yet, despite having a shared starting point, the IMCI-related CDSSs are markedly varied due to the need for interpretation when translating narrative guidelines into decision logic combined with considerations of context and design choices. Between October 2019 and April 2021, we conducted a comparative analysis of 4 IMCI-related CDSSs. The extent of adaptations to IMCI varied, but common themes emerged. Scope was extended to cover a broader range of conditions. Content was added or modified to enhance precision, align with new evidence, and support rational resource use. Structure was modified to increase efficiency, improve usability, and prioritize care for severely ill children. The multistakeholder development processes involved syntheses of recommendations from existing guidelines and literature; creation and validation of clinical algorithms; and iterative development, implementation, and evaluation. The common themes surrounding adaptations of IMCI guidance highlight the complexities of digitalizing evidence-based recommendations and reinforce the rationale for leveraging standards for CDSS development, such as the World Health Organization's SMART Guidelines. Implementation through multistakeholder dialogue is critical to ensure CDSSs can effectively and equitably improve quality of care for children in resource-constrained settings.

Modular Clinical Decision Support Networks (MoDN)-Updatable, interpretable, and portable predictions for evolving clinical environments

Clinical Decision Support Systems (CDSS) have the potential to improve and standardise care with probabilistic guidance. However, many CDSS deploy static, generic rule-based logic, resulting in inequitably distributed accuracy and inconsistent performance in evolving clinical environments. Data-driven models could resolve this issue by updating predictions according to the data collected. However, the size of data required necessitates collaborative learning from analogous CDSS's, which are often imperfectly interoperable (IIO) or unshareable. We propose Modular Clinical Decision Support Networks (MoDN) which allow flexible, privacy-preserving learning across IIO datasets, as well as being robust to the systematic missingness common to CDSS-derived data, while providing interpretable, continuous predictive feedback to the clinician. MoDN is a novel decision tree composed of feature-specific neural network modules that can be combined in any number or combination to make any number or combination of diagnostic predictions, updatable at each step of a consultation. The model is validated on a real-world CDSS-derived dataset, comprising 3,192 paediatric outpatients in Tanzania. MoDN significantly outperforms 'monolithic' baseline models (which take all features at once at the end of a consultation) with a mean macro F1 score across all diagnoses of 0.749 vs 0.651 for logistic regression and 0.620 for multilayer perceptron (p < 0.001). To test collaborative learning between IIO datasets, we create subsets with various percentages of feature overlap and port a MoDN model trained on one subset to another. Even with only 60% common features, fine-tuning a MoDN model on the new dataset or just making a composite model with MoDN modules matched the ideal scenario of sharing data in a perfectly interoperable setting. MoDN integrates into consultation logic by providing interpretable continuous feedback on the predictive potential of each question in a CDSS questionnaire. The modular design allows it to compartmentalise training updates to specific features and collaboratively learn between IIO datasets without sharing any data.