External validation of a mobile clinical decision support system for diarrhea etiology prediction in children: a multicenter study in Bangladesh and Mali

Integration of population-level data sources into an individual-level clinical prediction model for dengue virus test positivity

The differentiation of dengue virus (DENV) infection, a major cause of acute febrile illness in tropical regions, from other etiologies, may help prioritize laboratory testing and limit the inappropriate use of antibiotics. While traditional clinical prediction models focus on individual patient-level parameters, we hypothesize that for infectious diseases, population-level data sources may improve predictive ability. To create a clinical prediction model that integrates patient-extrinsic data for identifying DENV among febrile patients presenting to a hospital in Thailand, we fit random forest classifiers combining clinical data with climate and population-level epidemiologic data. In cross-validation, compared to a parsimonious model with the top clinical predictors, a model with the addition of climate data, reconstructed susceptibility estimates, force of infection estimates, and a recent case clustering metric significantly improved model performance.

Qualitative Assessment of a Smartphone-Based Mobile Health Tool to Guide Diarrhea Management in Bangladesh

Diarrheal diseases are a major cause of morbidity and mortality in children worldwide and a significant contributor to antimicrobial resistance. In the absence of laboratory diagnostics to establish diarrhea etiology, electronic clinical decision support tools can help physicians make informed treatment decisions for children with diarrhea. In Bangladesh, we assessed the feasibility and acceptability of an electronic Diarrhea Etiology Prediction algorithm (DEP tool) embedded into a rehydration calculator, which was designed to help physicians manage children with diarrhea, including decisions on antibiotic use. A team of Bangladeshi anthropologists conducted in-depth interviews with physicians (N = 13) in three public hospitals in Bangladesh about their experience using the tool in the context of a pilot trial. Physicians expressed positive opinions of the DEP tool. Participants perceived the tool to be simple and easy to use, with structured guidance on collecting and entering clinical data from patients. Significant strengths of the tool were as follows: standardization of protocol, efficiency of clinical decision-making, and improved clinical practice. Participants also noted barriers that might restrict the widespread impact of the tool, including physicians' reluctance to use an electronic tool for clinical decision-making, increasing work in overburdened healthcare settings, unavailability of a smartphone, and patients' preferences for antibiotics. We conclude that an electronic clinical decision support tool is a promising method for improving diarrheal management and antibiotic stewardship. Future directions include developing and implementing such a tool for informal healthcare physicians in low-resource settings, where families may first seek care for pediatric diarrhea.

Predictive modeling for infectious diarrheal disease in pediatric populations: A systematic review

Introduction

Diarrhea is still a significant global public health problem. There are currently no systematic evaluation of the modeling areas and approaches to predict diarrheal illness outcomes. This paper reviews existing research efforts in predictive modeling of infectious diarrheal illness in pediatric populations.

Methods

We conducted a systematic review via a PubMed search for the period 1990-2021. A comprehensive search query was developed through an iterative process and literature on predictive modeling of diarrhea was retrieved. The following filters were applied to the search results: human subjects, English language, and children (birth to 18 years). We carried out a narrative synthesis of the included publications.

Results

Our literature search returned 2671 articles. After manual evaluation, 38 of these articles were included in this review. The most common research topic among the studies were disease forecasts 14 (36.8%), vaccine-related predictions 9 (23.7%), and disease/pathogen detection 5 (13.2%). Majority of these studies were published between 2011 and 2020, 28 (73.7%). The most common technique used in the modeling was machine learning 12 (31.6%) with various algorithms used for the prediction tasks. With change in the landscape of diarrheal etiology after rotavirus vaccine introduction, many open areas (disease forecasts, disease detection, and strain dynamics) remain for pathogen-specific predictive models among etiological agents that have emerged as important. Additionally, the outcomes of diarrheal illness remain under researched. We also observed lack of consistency in the reporting of results of prediction models despite the available guidelines highlighting the need for common data standards and adherence to guidelines on reporting of predictive models for biomedical research.

Conclusions

Our review identified knowledge gaps and opportunities in predictive modeling for diarrheal illness, and limitations in existing attempts whilst advancing some precursory thoughts on how to address them, aiming to invigorate future research efforts in this sphere.

Assessment of Model Estimated and Directly Observed Weather Data for Etiological Prediction of Diarrhea

Recent advances in clinical prediction for diarrheal etiology in low- and middle-income countries have revealed that addition of weather data improves predictive performance. However, the optimal source of weather data remains unclear. We aim to compare model estimated satellite- and ground-based observational data with weather station directly-observed data for diarrheal prediction. We used clinical and etiological data from a large multi-center study of children with diarrhea to compare these methods. We show that the two sources of weather conditions perform similarly in most locations. We conclude that while model estimated data is a viable, scalable tool for public health interventions and disease prediction, directly observed weather station data approximates the modeled data, and given its ease of access, is likely adequate for prediction of diarrheal etiology in children in low- and middle-income countries.

Effects of prebiotics on the gut microbiota in vitro associated with functional diarrhea in children

Purpose

Diarrhea is among the top five causes of morbidity and mortality in children. Dysbiosis of the gut microbiota is considered the most important risk factor for diarrhea. Prebiotics have shown efficacy in treating diarrhea by regulating the balance of the gut microbiota in vivo.

Methods

In this study, we used an in vitro fermentation system to prevent the interference of host-gut microbe interactions during in vivo examination and investigated the effect of fructo-oligosaccharides (FOS) on gut microbiota composition and metabolism in 39 pediatric patients with functional diarrhea.

Results

16S rRNA sequencing revealed that FOS significantly improved α- and β-diversity in volunteers with pediatric diarrhea (p < 0.05). This improvement manifested as a significant increase (LDA > 2, p < 0.05) in probiotic bacteria (e.g., Bifidobacterium) and a significant inhibition (LDA > 2, p < 0.05) of harmful bacteria (e.g., Escherichia-Shigella). Notably, the analysis of bacterial metabolites after FOS treatment showed that the decrease in isobutyric acid, isovaleric acid, NH3, and H2S levels was positively correlated with the relative abundance of Lachnoclostridium. This decrease also showed the greatest negative correlation with the abundance of Streptococcus. Random forest analysis and ROC curve validation demonstrated that gut microbiota composition and metabolites were distinct between the FOS treatment and control groups (area under the curve [AUC] > 0.8). Functional prediction using PICRUSt 2 revealed that the FOS-induced alteration of gut microbiota was most likely mediated by effects on starch and sucrose metabolism.

Conclusion

This study is the first to evince that FOS can modulate gut microbial disorders in children with functional diarrhea. Our findings provide a framework for the application of FOS to alleviate functional diarrhea in children and reduce the use of antibiotics for managing functional diarrhea-induced disturbances in the gut microbiota.

Integration of population-level data sources into an individual-level clinical prediction model for dengue virus test positivity

The differentiation of dengue virus (DENV) infection, a major cause of acute febrile illness in tropical regions, from other etiologies, may help prioritize laboratory testing and limit the inappropriate use of antibiotics. While traditional clinical prediction models focus on individual patient-level parameters, we hypothesize that for infectious diseases, population-level data sources may improve predictive ability. To create a clinical prediction model that integrates patient-extrinsic data for identifying DENV among febrile patients presenting to a hospital in Thailand, we fit random forest classifiers combining clinical data with climate and population-level epidemiologic data. In cross validation, compared to a parsimonious model with the top clinical predictors, a model with the addition of climate data, reconstructed susceptibility estimates, force of infection estimates, and a recent case clustering metric, significantly improved model performance.

Use of Framework Matrix and Thematic Coding Methods in Qualitative Analysis for mHealth: NIRUDAK Study Data

Objective

Framework Matrix Analysis (FMA) and Applied Thematic Analysis (ATA) are qualitative methods that have not been as widely used/cited compared to content analysis or grounded theory. This paper compares methods of FMA with ATA for mobile health (mHealth) research. The same qualitative data were analyzed separately, using each methodology. The methods, utility, and results of each are compared, and recommendations made for their effective use.

Methods

Formative qualitative data were collected in eight focus group discussions with physicians and nurses from three hospitals in Bangladesh. Focus groups were conducted via video conference in the local language, Bangla, and audio recorded. Audio recordings were used to complete a FMA of participants' opinions about key features of a novel mHealth application (app) designed to support clinical management in patients with acute diarrhea. The resulting framework matrix was shared with the app design team and used to guide iterative development of the product for a validation study of the app. Subsequently, focus group audio recordings were transcribed in Bangla then translated into English for ATA; transcripts and codes were entered into NVivo qualitative analysis software. Code summaries and thematic memos explored the clinical utility of the mHealth app including clinicians' attitudes about using this decision support tool.

Results

Each of the two methods contributes differently to the research goal and have different implications for an mHealth research timeline. Recommendations for the effective use of each method in app development include: using FMA for data reduction where specific outcomes are needed to make programming and design decisions and using ATA to capture the more nuanced issues that guide use, product implementation, training, and workflow.

Conclusions

By describing how both analytical methods were used in this context, this paper provides guidance and an illustration for use of these two methods, specifically in mHealth design.

Improving Antibiotic Stewardship for Diarrheal Disease With Probability-Based Electronic Clinical Decision Support: A Randomized Crossover Trial

IMPORTANCE

Inappropriate use of antibiotics for diarrheal illness can result in adverse effects and increase in antimicrobial resistance.

OBJECTIVE

To determine whether the diarrheal etiology prediction (DEP) algorithm, which uses patient-specific and location-specific features to estimate the probability that diarrhea etiology is exclusively viral, impacts antibiotic prescriptions in patients with acute diarrhea.

DESIGN, SETTING, AND PARTICIPANTS

A randomized crossover study was conducted to evaluate the DEP incorporated into a smartphone-based electronic clinical decision-support (eCDS) tool. The DEP calculated the probability of viral etiology of diarrhea, based on dynamic patient-specific and location-specific features. Physicians were randomized in the first 4-week study period to the intervention arm (eCDS with the DEP) or control arm (eCDS without the DEP), followed by a 1-week washout period before a subsequent 4-week crossover period. The study was conducted at 3 sites in Bangladesh from November 17, 2021, to January 21, 2021, and at 4 sites in Mali from January 6, 2021, to March 5, 2021. Eligible physicians were those who treated children with diarrhea. Eligible patients were children between ages 2 and 59 months with acute diarrhea and household access to a cell phone for follow-up.

INTERVENTIONS

Use of the eCDS with the DEP (intervention arm) vs use of the eCDS without the DEP (control arm).

MAIN OUTCOMES AND MEASURES

The primary outcome was the proportion of children prescribed an antibiotic.

RESULTS

A total of 30 physician participants and 941 patient participants (57.1% male; median [IQR] age, 12 [8-18] months) were enrolled. There was no evidence of a difference in the proportion of children prescribed antibiotics by physicians using the DEP (risk difference [RD], -4.2%; 95% CI, -10.7% to 1.0%). In a post hoc analysis that accounted for the predicted probability of a viral-only etiology, there was a statistically significant difference in risk of antibiotic prescription between the DEP and control arms (RD, -0.056; 95% CI, -0.128 to -0.01). No known adverse effects of the DEP were detected at 10-day postdischarge.

CONCLUSIONS AND RELEVANCE

Use of a tool that provides an estimate of etiological likelihood did not result in a significant change in overall antibiotic prescriptions. Post hoc analysis suggests that a higher predicted probability of viral etiology was linked to reductions in antibiotic use.

TRIAL REGISTRATION

Clinicaltrials.gov Identifier: NCT04602676.

Designing a Novel Clinician Decision Support Tool for the Management of Acute Diarrhea in Bangladesh: Formative Qualitative Research (Preprint)

Background

The availability of mobile clinical decision support (CDS) tools has grown substantially with the increased prevalence of smartphone devices and apps. Although health care providers express interest in integrating mobile health (mHealth) technologies into their clinical settings, concerns have been raised, including perceived disagreements between information provided by mobile CDS tools and standard guidelines. Despite their potential to transform health care delivery, there remains limited literature on the provider’s perspective on the clinical utility of mobile CDS tools for improving patient outcomes, especially in low- and middle-income countries.

Objective

This study aims to describe providers’ perceptions about the utility of a mobile CDS tool accessed via a smartphone app for diarrhea management in Bangladesh. In addition, feedback was collected on the preliminary components of the mobile CDS tool to address clinicians’ concerns and incorporate their preferences.

Methods

From November to December 2020, qualitative data were gathered through 8 web-based focus group discussions with physicians and nurses from 3 Bangladeshi hospitals. Each discussion was conducted in the local language—Bangla—and audio recorded for transcription and translation by the local research team. Transcripts and codes were entered into NVivo (version 12; QSR International), and applied thematic analysis was used to identify themes that explore the clinical utility of an mHealth app for assessing dehydration severity in patients with acute diarrhea. Summaries of concepts and themes were generated from reviews of the aggregated coded data; thematic memos were written and used for the final analysis.

Results

Of the 27 focus group participants, 14 (52%) were nurses and 13 (48%) were physicians; 15 (56%) worked at a diarrhea specialty hospital and 12 (44%) worked in government district or subdistrict hospitals. Participants’ experience in their current position ranged from 2 to 14 years, with an average of 10.3 (SD 9.0) years. Key themes from the qualitative data analysis included current experience with CDS, overall perception of the app’s utility and its potential role in clinical care, barriers to and facilitators of app use, considerations of overtreatment and undertreatment, and guidelines for the app’s clinical recommendations. Participants felt that the tool would initially take time to use, but once learned, it could be useful during epidemic cholera. Some felt that clinical experience remains an important part of treatment that can be supplemented, but not replaced, by a CDS tool. In addition, diagnostic information, including mid-upper arm circumference and blood pressure, might not be available to directly inform programming decisions.

Conclusions

Participants were positive about the mHealth app and its potential to inform diarrhea management. They provided detailed feedback, which developers used to revise the mobile CDS tool. These formative qualitative data provided timely and relevant feedback to improve the utility of a CDS tool for diarrhea treatment in Bangladesh.