Evaluation of a Computer-Aided Clinical Decision Support System for Point-of-Care Use in Low-Resource Primary Care Settings: Acceptability Evaluation Study.

BACKGROUND: A clinical decision support system (CDSS) based on the logic and philosophy of clinical pathways is critical for managing the quality of health care and for standardizing care processes. Using such a system at a point-of-care setting is becoming more frequent these days. However, in a low-resource setting (LRS), such systems are frequently overlooked. OBJECTIVE: The purpose of the study was to evaluate the user acceptance of a CDSS in LRSs. METHODS: The CDSS evaluation was carried out at the Jimma Health Center and the Jimma Higher Two Health Center, Jimma, Ethiopia. The evaluation was based on 22 parameters organized into 6 categories: ease of use, system quality, information quality, decision changes, process changes, and user acceptance. A Mann-Whitney U test was used to investigate whether the difference between the 2 health centers was significant (2-tailed, 95% CI; α=.05). Pearson correlation and partial least squares structural equation modeling (PLS-SEM) was used to identify the relationship and factors influencing the overall acceptance of the CDSS in an LRS. RESULTS: On the basis of 116 antenatal care, pregnant patient care, and postnatal care cases, 73 CDSS evaluation responses were recorded. We found that the 2 health centers did not differ significantly on 16 evaluation parameters. We did, however, detect a statistically significant difference in 6 parameters (P<.05). PLS-SEM results showed that the coefficient of determination, R2, of perceived user acceptance was 0.703. More precisely, the perceived ease of use (ß=.015, P=.91) and information quality (ß=.149, P=.25) had no positive effect on CDSS acceptance but, rather, on the system quality and perceived benefits of the CDSS, with P<.05 and ß=.321 and ß=.486, respectively. Furthermore, the perceived ease of use was influenced by information quality and system quality, with an R2 value of 0.479, indicating that the influence of information quality on the ease of use is significant but the influence of system quality on the ease of use is not, with ß=.678 (P<.05) and ß=.021(P=.89), respectively. Moreover, the influence of decision changes (ß=.374, P<.05) and process changes (ß=.749, P<.05) both was significant on perceived benefits (R2=0.983). CONCLUSIONS: This study concludes that users are more likely to accept and use a CDSS at the point of care when it is easy to grasp the perceived benefits and system quality in terms of health care professionals' needs. We believe that the CDSS acceptance model developed in this study reveals specific factors and variables that constitute a step toward the effective adoption and deployment of a CDSS in LRSs.

Spatiotemporal distribution of climate-sensitive disease incidences in ethiopia: a longitudinal retrospective analysis of Malaria, Meningitis, Cholera, Dysentery, Leishmaniasis and Dengue fever between 2010 and 2022/2023.

BACKGROUND: Understanding the temporal and geographic distribution of disease incidences is crucial for effective public health planning and intervention strategies. This study presents a comprehensive analysis of the spatiotemporal distribution of disease incidences in Ethiopia, focusing on six major diseases: Malaria, Meningitis, Cholera and Dysentery, over the period from 2010 to 2022, whereas Dengue Fever and Leishmaniasis from 2018 to 2023. METHODS: Using data from Ethiopian public health institute: public health emergency management (PHEM), and Ministry of Health, we examined the occurrence and spread of each disease across different regions of Ethiopia. Spatial mapping and time series analysis were employed to identify hotspots, trends, and seasonal variations in disease incidence. RESULTS: The findings reveal distinct patterns for each disease, with varying cases and temporal dynamics. Monthly wise, Malaria exhibits a cyclical pattern with a peak during the rainy and humid season, while Dysentery, Meningitis and Cholera displays intermittent incidences. Dysentery cases show a consistent presence throughout the years, while Meningitis remains relatively low in frequency but poses a potential threat due to its severity. Dengue fever predominantly occurs in the eastern parts of Ethiopia. A significant surge in reported incident cases occurred during the years 2010 to 2013, primarily concentrated in the Amhara, Sidama, Oromia, Dire Dawa, and Benishangul-Gumuz regions. CONCLUSIONS: This study helps to a better understanding of disease epidemiology in Ethiopia and can serve as a foundation for evidence-based decision-making in disease prevention and control. By recognizing the patterns and seasonal changes associated with each disease, health authorities can implement proactive measures to mitigate the impact of outbreaks and safeguard public health in the region.

Correction: Developing a patient flow visualization and prediction model using aggregated data for a healthcare network cluster in Southwest Ethiopia.

[This corrects the article DOI: 10.1371/journal.pdig.0000376.].

Developing a patient flow visualization and prediction model using aggregated data for a healthcare network cluster in Southwest Ethiopia.

A health information system has been created to gather, aggregate, analyze, interpret, and utilize data collected from diverse sources. In Ethiopia, the most popular digital tools are the Electronic Community Health Information System and the District Health Information System. However, these systems lack capabilities like real-time interactive visualization and a data-driven engine for evidence-based insights. As a result, it was challenging to observe and continuously monitor the flow of patients. To address the gap, this study used aggregated data to visualize and predict patient flow in a South Western Ethiopia healthcare network cluster. The South-Western Ethiopian healthcare network cluster was where the patient flow datasets were collected. The collected dataset encompasses a span of 41 months, from 2019 to 2022, and has been obtained from 21 hospitals and health centers. Python Sankey diagrams were used to develop and build patient flow visualizations. Then, using the random forest and K-Nearest Neighbors (KNN) algorithms, we achieved an accuracy of 0.85 and 0.83 for the outpatient flow modeling and prediction, respectively. The imbalance in the data was further addressed using the NearMiss Algorithm, Synthetic Minority Oversampling Technique (SMOTE), and SMOTE-Tomek methods. In conclusion, we developed a patient flow visualization and prediction model as a first step toward an end-to-end effective real-time patient flow data-driven and analytical dashboard in Ethiopia, as well as a plugin for the already-existing digital health information system. Moreover, the need for and amount of data created by these digital tools will grow along with their use, demanding effective data-driven visualization and prediction to support evidence-based decision-making.

Evaluating a clinical decision support point of care instrument in low resource setting.

BACKGROUND: Clinical pathways are one of the main tools to manage the health care's quality and concerned with the standardization of care processes. They have been used to help frontline healthcare workers by presenting summarized evidence and generating clinical workflows involving a series of tasks performed by various people within and between work environments to deliver care. Integrating clinical pathways into Clinical Decision Support Systems (CDSSs) is a common practice today. However, in a low-resource setting (LRS), this kind of decision support systems is often not readily accessible or even not available. To fill this gap, we developed a computer aided CDSS that swiftly identifies which cases require a referral and which ones may be managed locally. The computer aided CDSS is designed primarily for use in primary care settings for maternal and childcare services, namely for pregnant patients, antenatal and postnatal care. The purpose of this paper is to assess the user acceptance of the computer aided CDSS at the point of care in LRSs. METHODS: For evaluation, we used a total of 22 parameters structured in to six major categories, namely "ease of use, system quality, information quality, decision changes, process changes, and user acceptance." Based on these parameters, the caregivers from Jimma Health Center's Maternal and Child Health Service Unit evaluated the acceptability of a computer aided CDSS. The respondents were asked to express their level of agreement using 22 parameters in a think-aloud approach. The evaluation was conducted in the caregiver's spare-time after the clinical decision. It was based on eighteen cases over the course of two days. The respondents were then asked to score their level of agreement with some statements on a five-point scale: strongly disagree, disagree, neutral, agree, and strongly agree. RESULTS: The CDSS received a favorable agreement score in all six categories by obtaining primarily strongly agree and agree responses. In contrast, a follow-up interview revealed a variety of reasons for disagreement based on the neutral, disagree, and strongly disagree responses. CONCLUSIONS: Though the study had a positive outcome, it was limited to the Jimma Health Center Maternal and Childcare Unit, and hence a wider scale evaluation and longitudinal measurements, including computer aided CDSS usage frequency, speed of operation and impact on intervention time are needed.

Analysis of low resource setting referral pathways to improve coordination and evidence-based services for maternal and child health in Ethiopia.

BACKGROUND: In low-resource settings, patient referral to a hospital is an essential part of the primary health care system. However, there is a paucity of study to explore the challenges and quality of referral coordination and communication. OBJECTIVE: The purpose of this research was to analyze the existing paper-based referral registration logbook for maternal and child health in general and women of reproductive age in particular, to improve referral coordination and evidence-based services in Low-Resource Settings. METHODS: This study analyzed the existing paper-based referral registration logbook (RRL) and card-sheet to explore the documentation of the referral management process, and the mechanism and quality of referrals between the health center (Jimma Health Center-case, Ethiopia) and the Hospital. A sample of 459 paper-based records from the referral registration logbook were digitized as part of a retrospective observational study. For data preprocessing, visualization, and analysis, we developed a python-based interactive referral clinical pathway tool. The data collection was conducted from August to October 2019. Jimma Health Center's RRL was used to examine how the referral decision was made and what cases were referred to the next level of care. However, the RRL was incomplete and did not contain the expected referral feedback from the hospital. Hence, we defined a new protocol to investigate the quality of referral. We compared the information in the health center's RRL with the medical records in the hospital to which the patients were referred. A total of 201 medical records of referred patients were examined. RESULTS: A total of 459 and 201 RRL records from the health center and the referred hospital, respectively, were analyzed in the study. Out of 459, 86.5% referred cases were between the age of 20 to 30 years. We found that "better patient management", "further patient management", and "further investigation" were the main health-center referral reasons and decisions. It accounted for 40.08%, 39.22%, and 16.34% of all 459 referrals, respectively. The leading and most common referral cases in the health center were long labor, prolonged first and second stage labor, labor or delivery complicated by fetal heart rate anomaly, preterm newborn, maternal care with breech presentation, premature rupture of membranes, malposition of the uterus, and antepartum hemorrhage. In the hospital RRL and card-sheet, the main referral-in reasons were technical examination, expert advice, further management, and evaluation. We found it overall impossible to match records from the referral logbook in the health center with the patient files in the hospital. Out of 201, only 13.9% of records were perfect matching entries between health center and referred hospital RRL. We found 84%, 14.4%, and 1.6% were appropriate, unnecessary and unknown referrals respectively. CONCLUSION: The paper illustrates the bottlenecks encountered in the quality assessment of the referrals. We analyzed the current status of the referral pathway, existing communications, guidelines and data quality, as a first step towards an end-to-end effective referral coordination and evidence-based referral service. Accessing, monitoring, and tracking the history of referred patients and referral feedback is challenging with the present paper-based referral coordination and communication system. Overall, the referral services were inadequate, and referral feedback was not automatically delivered, causing unnecessary delays.

A Hybrid Approach for Designing Dynamic and Data-Driven Clinical Pathways Point of Care Instruments in Low Resource Settings.

Though a clinical pathway is one of the tools used to guide evidence-based healthcare, promoting the practice of evidence-based decisions on healthcare services is incredibly challenging in low resource settings (LRS). This paper proposed a novel approach for designing an automated and dynamic generation of clinical pathways (CPs) in LRS through a hybrid (knowledge-based and data-driven based) algorithm that works with limited clinical input and can be updated whenever new information is available. Our proposed approach dynamically maps and validate the knowledge-based clinical pathways with the local context and historical evidence to deliver a multi-criteria decision analysis (concordance table) for adjusting or readjusting the order of knowledge-based CPs decision priority. Our finding shows that the developed approach successfully delivered probabilistic-based CPs and found a promising result with Jimma Health Center "pregnancy, childbearing, and family planning" dataset.