Online journal of public health informatics最新文献

{"title":"The Association of Broadband Internet Use With Drug Overdose Mortality Rates in the United States: Cross-Sectional Analysis.","authors":"Ioannis Karakis, Genti Kostandini, Konstantinos Tsamakis, Velma Zahirovic-Herbert","doi":"10.2196/52686","DOIUrl":"10.2196/52686","url":null,"abstract":"<p><strong>Background: </strong>The availability and use of broadband internet play an increasingly important role in health care and public health.</p><p><strong>Objective: </strong>This study examined the associations between broadband internet availability and use with drug overdose deaths in the United States.</p><p><strong>Methods: </strong>We linked 2019 county-level drug overdose death data in restricted-access multiple causes of death files from the National Vital Statistics System at the US Centers for Disease Control and Prevention with the 2019 county-level broadband internet rollout data from the Federal Communications Commission and the 2019 county-level broadband usage data available from Microsoft's Airband Initiative. Cross-sectional analysis was performed with the fixed-effects regression method to assess the association of broadband internet availability and usage with opioid overdose deaths. Our model also controlled for county-level socioeconomic characteristics and county-level health policy variables.</p><p><strong>Results: </strong>Overall, a 1% increase in broadband internet use was linked with a 1.2% increase in overall drug overdose deaths. No significant association was observed for broadband internet availability. Although similar positive associations were found for both male and female populations, the association varied across different age subgroups. The positive association on overall drug overdose deaths was the greatest among Hispanic and Non-Hispanic White populations.</p><p><strong>Conclusions: </strong>Broadband internet use was positively associated with increased drug overdose deaths among the overall US population and some subpopulations, even after controlling for broadband availability, sociodemographic characteristics, unemployment, and median household income.</p>","PeriodicalId":74345,"journal":{"name":"Online journal of public health informatics","volume":"16 ","pages":"e52686"},"PeriodicalIF":0.0,"publicationDate":"2024-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11237777/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141452347","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Bringing the Public Health Informatics and Technology Workforce Together: The PHIAT Conference.","authors":"April Moreno Arellano, Huan-Ju Shih, Karmen S Williams","doi":"10.2196/55377","DOIUrl":"10.2196/55377","url":null,"abstract":"<p><p>The field of public health informatics has undergone significant evolution in recent years, and advancements in technology and its applications are imperative to address emerging public health challenges. Interdisciplinary approaches and training can assist with these challenges. In 2023, the inaugural Public Health Informatics and Technology (PHIAT) Conference was established as a hybrid 3-day conference at the University of California, San Diego, and online. The conference's goal was to establish a forum for academics and public health organizations to discuss and tackle new opportunities and challenges in public health informatics and technology. This paper provides an overview of the quest for interest, speakers and topics, evaluations from the attendees, and lessons learned to be implemented in future conferences.</p>","PeriodicalId":74345,"journal":{"name":"Online journal of public health informatics","volume":"16 ","pages":"e55377"},"PeriodicalIF":0.0,"publicationDate":"2024-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11259087/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141302193","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"e-Cigarette Tobacco Flavors, Public Health, and Toxicity: Narrative Review.","authors":"Yehao Sun, Prital Prabhu, Ryan Rahman, Dongmei Li, Scott McIntosh, Irfan Rahman","doi":"10.2196/51991","DOIUrl":"10.2196/51991","url":null,"abstract":"<p><strong>Background: </strong>Recently, the US Food and Drug Administration implemented enforcement priorities against all flavored, cartridge-based e-cigarettes other than menthol and tobacco flavors. This ban undermined the products' appeal to vapers, so e-cigarette manufacturers added flavorants of other attractive flavors into tobacco-flavored e-cigarettes and reestablished appeal.</p><p><strong>Objective: </strong>This review aims to analyze the impact of the addition of other flavorants in tobacco-flavored e-cigarettes on both human and public health issues and to propose further research as well as potential interventions.</p><p><strong>Methods: </strong>Searches for relevant literature published between 2018 and 2023 were performed. Cited articles about the toxicity of e-cigarette chemicals included those published before 2018, and governmental websites and documents were also included for crucial information.</p><p><strong>Results: </strong>Both the sales of e-cigarettes and posts on social media suggested that the manufacturers' strategy was successful. The reestablished appeal causes not only a public health issue but also threats to the health of individual vapers. Research has shown an increase in toxicity associated with the flavorants commonly used in flavored e-cigarettes, which are likely added to tobacco-flavored e-cigarettes based on tobacco-derived and synthetic tobacco-free nicotine, and these other flavors are associated with higher clinical symptoms not often induced solely by natural, traditional tobacco flavors.</p><p><strong>Conclusions: </strong>The additional health risks posed by the flavorants are pronounced even without considering the toxicological interactions of the different tobacco flavorants, and more research should be done to understand the health risks thoroughly and to take proper actions accordingly for the regulation of these emerging products.</p>","PeriodicalId":74345,"journal":{"name":"Online journal of public health informatics","volume":"16 ","pages":"e51991"},"PeriodicalIF":0.0,"publicationDate":"2024-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11165290/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141157315","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Geospatial Imprecision With Constraints for Precision Public Health: Algorithm Development and Validation.","authors":"Daniel Harris, Chris Delcher","doi":"10.2196/54958","DOIUrl":"10.2196/54958","url":null,"abstract":"<p><strong>Background: </strong>Location and environmental social determinants of health are increasingly important factors in both an individual's health and the monitoring of community-level public health issues.</p><p><strong>Objective: </strong>We aimed to measure the extent to which location obfuscation techniques, designed to protect an individual's privacy, can unintentionally shift geographical coordinates into neighborhoods with significantly different socioeconomic demographics, which limits the precision of findings for public health stakeholders.</p><p><strong>Methods: </strong>Point obfuscation techniques intentionally blur geographic coordinates to conceal the original location. The pinwheel obfuscation method is an existing technique in which a point is moved along a pinwheel-like path given a randomly chosen angle and a maximum radius; we evaluate the impact of this technique using 2 data sets by comparing the demographics of the original point and the resulting shifted point by cross-referencing data from the United States Census Bureau.</p><p><strong>Results: </strong>Using poverty measures showed that points from regions of low poverty may be shifted to regions of high poverty; similarly, points in regions with high poverty may be shifted into regions of low poverty. We varied the maximum allowable obfuscation radius; the mean difference in poverty rate before and after obfuscation ranged from 6.5% to 11.7%. Additionally, obfuscation inadvertently caused false hot spots for deaths by suicide in Cook County, Illinois.</p><p><strong>Conclusions: </strong>Privacy concerns require patient locations to be imprecise to protect against risk of identification; precision public health requires accuracy. We propose a modified obfuscation technique that is constrained to generate a new point within a specified census-designated region to preserve both privacy and analytical accuracy by avoiding demographic shifts.</p>","PeriodicalId":74345,"journal":{"name":"Online journal of public health informatics","volume":"16 ","pages":"e54958"},"PeriodicalIF":0.0,"publicationDate":"2024-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11150894/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141077435","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Intention to Use Mobile-Based Partograph and Its Predictors Among Obstetric Health Care Providers Working at Public Referral Hospitals in the Oromia Region of Ethiopia in 2022: Cross-Sectional Questionnaire Study.","authors":"Kefyalew Naniye Tilahun, Jibril Bashir Adem, Wabi Temesgen Atinafu, Agmasie Damtew Walle, Nebyu Demeke Mengestie, Abraham Yeneneh Birhanu","doi":"10.2196/51601","DOIUrl":"10.2196/51601","url":null,"abstract":"<p><strong>Background: </strong>A partograph is a pictorial representation of the relationship between cervical dilatation and the time used to diagnose prolonged and obstructed labor. However, the utilization of paper-based partograph is low and it is prone to documentation errors, which can be avoided with the use of electronic partographs. There is only limited information on the proportion of intention to use mobile-based partographs and its predictors.</p><p><strong>Objective: </strong>The objective of this study was to determine the proportion of obstetric health care providers at public referral hospitals in Oromia, Ethiopia, in 2022 who had the intention to use mobile-based partographs and to determine the predictors of their intention to use mobile-based partographs.</p><p><strong>Methods: </strong>We performed an institution-based cross-sectional study from June 1 to July 1, 2022. Census was conducted on 649 participants. A self-administered structured English questionnaire was used, and a 5% pretest was performed. Data were entered into EpiData version 4.6 and exported to SPSS version 25 for descriptive analysis and AMOS (analysis of moment structure; version 23) for structural and measurement model assessment. Descriptive and structural equation modeling analyses were performed. The hypotheses developed based on a modified Technology Acceptance Model were tested using path coefficients and P values <.05.</p><p><strong>Results: </strong>About 65.7% (414/630; 95% CI 61.9%-69.4%) of the participants intended to use mobile-based electronic partographs, with a 97% (630/649) response rate. Perceived usefulness had a positive influence on intention to use (β=.184; P=.02) and attitude (β=.521; P=.002). Perceived ease of use had a positive influence on attitude (β=.382; P=.003), perceived usefulness (β=.503; P=.002), and intention to use (β=.369; P=.001). Job relevance had a positive influence on perceived usefulness (β=.408; P=.001) and intention to use (β=.185; P=.008). Attitude positively influenced intention to use (β=.309; P=.002). Subjective norms did not have a significant influence on perceived usefulness (β=.020; P=.61) and intention to use (β=-.066; P=.07).</p><p><strong>Conclusions: </strong>Two-thirds of the obstetric health care providers in our study intended to use mobile-based partographs. Perceived usefulness, perceived ease of use, job relevance, and attitude positively and significantly influenced their intention to use mobile-based electronic partographs. The development of a user-friendly mobile-based partograph that meets job and user expectations can enhance the intention to use.</p>","PeriodicalId":74345,"journal":{"name":"Online journal of public health informatics","volume":"16 ","pages":"e51601"},"PeriodicalIF":0.0,"publicationDate":"2024-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11127132/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140900501","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Characterization of Post-COVID-19 Definitions and Clinical Coding Practices: Longitudinal Study.","authors":"Monika Maripuri, Andrew Dey, Jacqueline Honerlaw, Chuan Hong, Yuk-Lam Ho, Vidisha Tanukonda, Alicia W Chen, Vidul Ayakulangara Panickan, Xuan Wang, Harrison G Zhang, Doris Yang, Malarkodi Jebathilagam Samayamuthu, Michele Morris, Shyam Visweswaran, Brendin Beaulieu-Jones, Rachel Ramoni, Sumitra Muralidhar, J Michael Gaziano, Katherine Liao, Zongqi Xia, Gabriel A Brat, Tianxi Cai, Kelly Cho","doi":"10.2196/53445","DOIUrl":"10.2196/53445","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Post-COVID-19 condition (colloquially known as \"long COVID-19\") characterized as postacute sequelae of SARS-CoV-2 has no universal clinical case definition. Recent efforts have focused on understanding long COVID-19 symptoms, and electronic health record (EHR) data provide a unique resource for understanding this condition. The introduction of the International Classification of Diseases, Tenth Revision (ICD-10) code U09.9 for \"Post COVID-19 condition, unspecified\" to identify patients with long COVID-19 has provided a method of evaluating this condition in EHRs; however, the accuracy of this code is unclear.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;This study aimed to characterize the utility and accuracy of the U09.9 code across 3 health care systems-the Veterans Health Administration, the Beth Israel Deaconess Medical Center, and the University of Pittsburgh Medical Center-against patients identified with long COVID-19 via a chart review by operationalizing the World Health Organization (WHO) and Centers for Disease Control and Prevention (CDC) definitions.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;Patients who were COVID-19 positive with either a U07.1 ICD-10 code or positive polymerase chain reaction test within these health care systems were identified for chart review. Among this cohort, we sampled patients based on two approaches: (1) with a U09.9 code and (2) without a U09.9 code but with a new onset long COVID-19-related ICD-10 code, which allows us to assess the sensitivity of the U09.9 code. To operationalize the long COVID-19 definition based on health agency guidelines, symptoms were grouped into a \"core\" cluster of 11 commonly reported symptoms among patients with long COVID-19 and an extended cluster that captured all other symptoms by disease domain. Patients having ≥2 symptoms persisting for ≥60 days that were new onset after their COVID-19 infection, with ≥1 symptom in the core cluster, were labeled as having long COVID-19 per chart review. The code's performance was compared across 3 health care systems and across different time periods of the pandemic.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;Overall, 900 patient charts were reviewed across 3 health care systems. The prevalence of long COVID-19 among the cohort with the U09.9 ICD-10 code based on the operationalized WHO definition was between 23.2% and 62.4% across these health care systems. We also evaluated a less stringent version of the WHO definition and the CDC definition and observed an increase in the prevalence of long COVID-19 at all 3 health care systems.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusions: &lt;/strong&gt;This is one of the first studies to evaluate the U09.9 code against a clinical case definition for long COVID-19, as well as the first to apply this definition to EHR data using a chart review approach on a nationwide cohort across multiple health care systems. This chart review approach can be implemented at other EHR systems to further evaluate the utility and performanc","PeriodicalId":74345,"journal":{"name":"Online journal of public health informatics","volume":"16 ","pages":"e53445"},"PeriodicalIF":0.0,"publicationDate":"2024-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11073632/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140872344","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Deriving Treatment Decision Support From Dutch Electronic Health Records by Exploring the Applicability of a Precision Cohort-Based Procedure for Patients With Type 2 Diabetes Mellitus: Precision Cohort Study.","authors":"Xavier Pinho, Willemijn Meijer, Albert de Graaf","doi":"10.2196/51092","DOIUrl":"10.2196/51092","url":null,"abstract":"<p><strong>Background: </strong>The rapidly increasing availability of medical data in electronic health records (EHRs) may contribute to the concept of learning health systems, allowing for better personalized care. Type 2 diabetes mellitus was chosen as the use case in this study.</p><p><strong>Objective: </strong>This study aims to explore the applicability of a recently developed patient similarity-based analytics approach based on EHRs as a candidate data analytical decision support tool.</p><p><strong>Methods: </strong>A previously published precision cohort analytics workflow was adapted for the Dutch primary care setting using EHR data from the Nivel Primary Care Database. The workflow consisted of extracting patient data from the Nivel Primary Care Database to retrospectively generate decision points for treatment change, training a similarity model, generating a precision cohort of the most similar patients, and analyzing treatment options. This analysis showed the treatment options that led to a better outcome for the precision cohort in terms of clinical readouts for glycemic control.</p><p><strong>Results: </strong>Data from 11,490 registered patients diagnosed with type 2 diabetes mellitus were extracted from the database. Treatment-specific filter cohorts of patient groups were generated, and the effect of past treatment choices in these cohorts was assessed separately for glycated hemoglobin and fasting glucose as clinical outcome variables. Precision cohorts were generated for several individual patients from the filter cohorts. Treatment options and outcome analyses were technically well feasible but in general had a lack of statistical power to demonstrate statistical significance for treatment options with better outcomes.</p><p><strong>Conclusions: </strong>The precision cohort analytics workflow was successfully adapted for the Dutch primary care setting, proving its potential for use as a learning health system component. Although the approach proved technically well feasible, data size limitations need to be overcome before application for clinical decision support becomes realistically possible.</p>","PeriodicalId":74345,"journal":{"name":"Online journal of public health informatics","volume":"16 ","pages":"e51092"},"PeriodicalIF":0.0,"publicationDate":"2024-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11097050/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140873137","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Effect of Long-Distance Domestic Travel Ban Policies in Japan on COVID-19 Outbreak Dynamics During Dominance of the Ancestral Strain: Ex Post Facto Retrospective Observation Study","authors":"Junko Kurita, Yoshitaro Iwasaki","doi":"10.2196/44931","DOIUrl":"https://doi.org/10.2196/44931","url":null,"abstract":"Background In Japan, long-distance domestic travel was banned while the ancestral SARS-CoV-2 strain was dominant under the first declared state of emergency from March 2020 until the end of May 2020. Subsequently, the “Go To Travel” campaign travel subsidy policy was activated, allowing long-distance domestic travel, until the second state of emergency as of January 7, 2021. The effects of this long-distance domestic travel ban on SARS-CoV-2 infectivity have not been adequately evaluated. Objective We evaluated the effects of the long-distance domestic travel ban in Japan on SARS-CoV-2 infectivity, considering climate conditions, mobility, and countermeasures such as the “Go To Travel” campaign and emergency status. Methods We calculated the effective reproduction number R(t), representing infectivity, using the epidemic curve in Kagoshima prefecture based on the empirical distribution of the incubation period and procedurally delayed reporting from an earlier study. Kagoshima prefecture, in southern Japan, has several resorts, with an airport commonly used for transportation to Tokyo or Osaka. We regressed R(t) on the number of long-distance domestic travelers (based on the number of airport limousine bus users provided by the operating company), temperature, humidity, mobility, and countermeasures such as state of emergency declarations and the “Go To Travel” campaign in Kagoshima. The study period was June 20, 2020, through February 2021, before variant strains became dominant. A second state of emergency was not declared in Kagoshima prefecture but was declared in major cities such as Tokyo and Osaka. Results Estimation results indicated a pattern of declining infectivity with reduced long-distance domestic travel volumes as measured by the number of airport limousine bus users. Moreover, infectivity was lower during the “Go To Travel” campaign and the second state of emergency. Regarding mobility, going to restaurants, shopping malls, and amusement venues was associated with increased infectivity. However, going to grocery stores and pharmacies was associated with decreased infectivity. Climate conditions showed no significant association with infectivity patterns. Conclusions The results of this retrospective analysis suggest that the volume of long-distance domestic travel might reduce SARS-CoV-2 infectivity. Infectivity was lower during the “Go To Travel” campaign period, during which long-distance domestic travel was promoted, compared to that outside this campaign period. These findings suggest that policies banning long-distance domestic travel had little legitimacy or rationale. Long-distance domestic travel with appropriate infection control measures might not increase SARS-CoV-2 infectivity in tourist areas. Even though this analysis was performed much later than the study period, if we had performed this study focusing on the period of April or May 2021, it would likely yield the same results. These findings might be helpful for go","PeriodicalId":74345,"journal":{"name":"Online journal of public health informatics","volume":"42 9","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140677303","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Applying Machine Learning Techniques to Implementation Science.","authors":"Nathalie Huguet, Jinying Chen, Ravi B Parikh, Miguel Marino, Susan A Flocke, Sonja Likumahuwa-Ackman, Justin Bekelman, Jennifer E DeVoe","doi":"10.2196/50201","DOIUrl":"10.2196/50201","url":null,"abstract":"<p><p>Machine learning (ML) approaches could expand the usefulness and application of implementation science methods in clinical medicine and public health settings. The aim of this viewpoint is to introduce a roadmap for applying ML techniques to address implementation science questions, such as predicting what will work best, for whom, under what circumstances, and with what predicted level of support, and what and when adaptation or deimplementation are needed. We describe how ML approaches could be used and discuss challenges that implementation scientists and methodologists will need to consider when using ML throughout the stages of implementation.</p>","PeriodicalId":74345,"journal":{"name":"Online journal of public health informatics","volume":"16 ","pages":"e50201"},"PeriodicalIF":0.0,"publicationDate":"2024-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11074902/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140875070","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Machine Learning for Prediction of Tuberculosis Detection: Case Study of Trained African Giant Pouched Rats.","authors":"Joan Jonathan, Alcardo Alex Barakabitze, Cynthia D Fast, Christophe Cox","doi":"10.2196/50771","DOIUrl":"https://doi.org/10.2196/50771","url":null,"abstract":"<p><strong>Background: </strong>Technological advancement has led to the growth and rapid increase of tuberculosis (TB) medical data generated from different health care areas, including diagnosis. Prioritizing better adoption and acceptance of innovative diagnostic technology to reduce the spread of TB significantly benefits developing countries. Trained TB-detection rats are used in Tanzania and Ethiopia for operational research to complement other TB diagnostic tools. This technology has increased new TB case detection owing to its speed, cost-effectiveness, and sensitivity.</p><p><strong>Objective: </strong>During the TB detection process, rats produce vast amounts of data, providing an opportunity to identify interesting patterns that influence TB detection performance. This study aimed to develop models that predict if the rat will hit (indicate the presence of TB within) the sample or not using machine learning (ML) techniques. The goal was to improve the diagnostic accuracy and performance of TB detection involving rats.</p><p><strong>Methods: </strong>APOPO (Anti-Persoonsmijnen Ontmijnende Product Ontwikkeling) Center in Morogoro provided data for this study from 2012 to 2019, and 366,441 observations were used to build predictive models using ML techniques, including decision tree, random forest, naïve Bayes, support vector machine, and k-nearest neighbor, by incorporating a variety of variables, such as the diagnostic results from partner health clinics using methods endorsed by the World Health Organization (WHO).</p><p><strong>Results: </strong>The support vector machine technique yielded the highest accuracy of 83.39% for prediction compared to other ML techniques used. Furthermore, this study found that the inclusion of variables related to whether the sample contained TB or not increased the performance accuracy of the predictive model.</p><p><strong>Conclusions: </strong>The inclusion of variables related to the diagnostic results of TB samples may improve the detection performance of the trained rats. The study results may be of importance to TB-detection rat trainers and TB decision-makers as the results may prompt them to take action to maintain the usefulness of the technology and increase the TB detection performance of trained rats.</p>","PeriodicalId":74345,"journal":{"name":"Online journal of public health informatics","volume":"16 ","pages":"e50771"},"PeriodicalIF":0.0,"publicationDate":"2024-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11061786/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140869021","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}