The ability to detect surgical site infections (SSI) is a critical need for healthcare worldwide, but is especially important in low-income countries, where there is limited access to health facilities and trained clinical staff. In this paper, we present a new method of predicting SSI using a thermal image collected with a smart phone. Machine learning algorithms were developed using images collected as part of a clinical study that included 530 women in rural Rwanda who underwent cesarean section surgery. Thermal images were collected approximately 10 days after surgery, in conjunction with an examination by a trained doctor to determine the status of the wound (infected or not). Of the 530 women, 30 were found to have infected wounds. The data were used to develop two Convolutional Neural Net (CNN) models, with special care taken to avoid overfitting and address the problem of class imbalance in binary classification. The first model, a 6-layer naïve CNN model, demonstrated a median accuracy of AUC=0.84 with sensitivity=71% and specificity=87%. The transfer learning CNN model demonstrated a median accuracy of AUC=0.90 with sensitivity =95% and specificity=84%. To our knowledge, this is the first successful demonstration of a machine learning algorithm to predict surgical infection using thermal images alone. Clinical Relevance-This work establishes a promising new method for automated detection of surgical site infection.
BackgroundSurgical site infections (SSIs) cause a significant global public health burden in low and middle-income countries. Most SSIs develop after patient discharge and may go undetected. We assessed the feasibility and diagnostic accuracy of an mHealth-community health worker (CHW) home-based telemedicine intervention to diagnose SSIs in women who delivered via caesarean section in rural Rwanda.MethodsThis prospective cohort study included women who underwent a caesarean section at Kirehe District Hospital between September 2019 and March 2020. At postoperative day 10 (±3 days), a trained CHW visited the woman at home, provided wound care and transmitted a photo of the wound to a remote general practitioner (GP) via WhatsApp. The GP reviewed the photo and made an SSI diagnosis. The next day, the woman returned to the hospital for physical examination by an independent GP, whose SSI diagnosis was considered the gold standard for our analysis. We describe the intervention process indicators and report the sensitivity and specificity of the telemedicine-based diagnosis.ResultsOf 787 women included in the study, 91.4% (n=719) were located at their home by the CHW and all of them (n=719, 100%) accepted the intervention. The full intervention was completed, including receipt of GP telemedicine diagnosis within 1 hour, for 79.0% (n=623). The GPs diagnosed 30 SSIs (4.2%) through telemedicine and 38 SSIs (5.4%) through physical examination. The telemedicine sensitivity was 36.8% and specificity was 97.6%. The negative predictive value was 96.4%.ConclusionsImplementation of an mHealth-CHW home-based intervention in rural Rwanda and similar settings is feasible. Patients’ acceptance of the intervention was key to its success. The telemedicine-based SSI diagnosis had a high negative predictive value but a low sensitivity. Further studies must explore strategies to improve accuracy, such as accompanying wound images with clinical data or developing algorithms using machine learning.
Objective A scoping review of discharge instructions for women undergoing cesarean section (c-section) in sub-Saharan Africa (SSA). Method Studies were identified from PubMed, Globus Index Medicus, NiPAD, EMBASE, and EBSCO databases. Eligible papers included research based in a SSA country, published in English or French, and containing information on discharge instructions addressing general postnatal care, wound care, planning of future births, or postpartum depression targeted for women delivering by c-section. For analysis, we used the PRISMA guidelines for scoping reviews followed by a narrative synthesis. We assessed quality of evidence using the GRADE system. Results We identified 78 eligible studies; 5 papers directly studied discharge protocols and 73 included information on discharge instructions in the context of a different study objective. 37 studies addressed wound care, with recommendations to return to a health facility for dressing changes and wound checks between 3 days to 6 weeks. 16 studies recommended antibiotic use at discharge, with 5 specifying a particular antibiotic. 19 studies provided recommendations around contraception and family planning, with 6 highlighting intrauterine device placement immediately after birth or 6-weeks postpartum and 6 studies discussing the importance of counselling services. Only 5 studies provided recommendations for the evaluation and management of postpartum depression in c-section patients; these studies screened for depression at 4–8 weeks postpartum and highlighted connections between c-section delivery and the loss of self-esteem as well as connections between emergency c-section delivery and psychiatric morbidity. Conclusion Few studies in SSA directly examine discharge protocols and instructions for women following c-section. Those available demonstrate wide variation in recommendations. Research is needed to develop structured evidence-based instructions with clear timelines for women. These instructions should account for financial burden, access to resources, and education of patients and communities.
Introduction While it is recognized that there are costs associated with postoperative patient follow-up, risk assessments of catastrophic health expenditures (CHEs) due to surgery in sub-Saharan Africa rarely include expenses after discharge. We describe patient-level costs for cesarean section (c-section) and follow-up care up to postoperative day (POD) 30 and evaluate the contribution of follow-up to CHEs in rural Rwanda. Methods We interviewed women who delivered via c-section at Kirehe District Hospital between September 2019 and February 2020. Expenditure details were captured on an adapted surgical indicator financial survey tool and extracted from the hospital billing system. CHE was defined as health expenditure of ≥ 10% of annual household expenditure. We report the cost of c-section up to 30 days after discharge, the rate of CHE among c-section patients stratified by in-hospital costs and post-discharge follow-up costs, and the main contributors to c-section follow-up costs. We performed a multivariate logistic regression using a backward stepwise process to determine independent predictors of CHE at POD30 at α ≤ 0.05. Results Of the 479 participants in this study, 90% were classified as impoverished before surgery and an additional 6.4% were impoverished by the c-section. The median out-of-pocket costs up to POD30 was US$122.16 (IQR: $102.94, $148.11); 63% of these expenditures were attributed to post-discharge expenses or lost opportunity costs (US$77.50; IQR: $67.70, $95.60). To afford c-section care, 64.4% borrowed money and 18.4% sold possessions. The CHE rate was 27% when only considering direct and indirect costs up to the time of discharge and 77% when including the reported expenses up to POD30. Transportation and lost household wages were the largest contributors to post-discharge costs. Further, CHE at POD30 was independently predicted by membership in community-based health insurance (aOR = 3.40, 95% CI: 1.21,9.60), being a farmer (aOR = 2.25, 95% CI:1.00,3.03), primary school education (aOR = 2.35, 95% CI:1.91,4.66), and small household sizes had 0.22 lower odds of experiencing CHE compared to large households (aOR = 0.78, 95% CI:0.66,0.91). Conclusion Costs associated with surgical follow-up are often neglected in financial risk calculations but contribute significantly to the risk of CHE in rural Rwanda. Insurance coverage for direct medical costs is insufficient to protect against CHE. Innovative follow-up solutions to reduce costs of patient transport and compensate for household lost wages need to be considered.
ObjectiveDuring the COVID-19 pandemic, community health workers (CHWs) served as front-line workers in the COVID-19 response while maintaining community health services. We aimed to understand challenges faced by Rwanda’s CHWs during a nationwide COVID-19 lockdown that occurred between March and May 2020 by assessing the availability of trainings, supplies and supervision while exploring perceived needs and challenges.Design and settingThis study was a mixed-method study conducted in three Rwandan districts: Burera, Kirehe and Kayonza.Main outcome and measureUsing data collected via telephone, we assessed the availability of trainings, supplies and supervision during the first national lockdown, while exploring perceived needs and challenges of CHWs who were engaged in COVID-19 response, in addition to their existing duties of delivering health services in the community.ResultsAmong the 292 quantitative survey participants, CHWs were responsible for a median of 55 households (IQR: 42–79) and visited a median of 30 households (IQR: 11–52) in the month prior to the survey (July 2020). In the previous 12 months, only 164 (56.2%) CHWs reported being trained on any health topic. Gaps in supply availability, particularly for commodities, existed at the start of the lockdown and worsened over the course of the lockdown. Supervision during the lockdown was low, with nearly 10% of CHWs never receiving supervision and only 24% receiving at least three supervision visits during the 3-month lockdown. In qualitative interviews, CHWs additionally described increases in workload, lack of personal protective equipment and COVID-specific training, fear of COVID-19, and difficult working conditions.ConclusionMany challenges faced by CHWs during the lockdown predated COVID-19 and persisted or were exacerbated during the pandemic. To promote the resilience of Rwanda’s CHW system, we recommend increased access to PPE; investment in training, supervision and supply chain management; and financial compensation for CHWs.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.