1
|
Mamo DN, Yilma TM, Fekadie M, Sebastian Y, Bizuayehu T, Melaku MS, Walle AD. Machine learning to predict virological failure among HIV patients on antiretroviral therapy in the University of Gondar Comprehensive and Specialized Hospital, in Amhara Region, Ethiopia, 2022. BMC Med Inform Decis Mak 2023; 23:75. [PMID: 37085851 PMCID: PMC10122289 DOI: 10.1186/s12911-023-02167-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/15/2022] [Accepted: 04/04/2023] [Indexed: 04/23/2023] Open
Abstract
BACKGROUND Treatment with effective antiretroviral therapy (ART) reduces viral load as well as HIV-related morbidity and mortality in HIV-positive patients. Despite the expanded availability of antiretroviral therapy around the world, virological failure remains a serious problem for HIV-positive patients. Thus, Machine learning predictive algorithms have the potential to improve the quality of care and predict the needs of HIV patients by analyzing huge amounts of data, and enhancing prediction capabilities. This study used different machine learning classification algorithms to predict the features that cause virological failure in HIV-positive patients. METHOD An institution-based secondary data was used to conduct patients who were on antiretroviral therapy at the University of Gondar Comprehensive and Specialized Hospital from January 2020 to May 2022. Patients' data were extracted from the electronic database using a structured checklist and imported into Python version three software for data pre-processing and analysis. Then, seven supervised classification machine-learning algorithms for model development were trained. The performances of the predictive models were evaluated using accuracy, sensitivity, specificity, precision, f1-score, and AUC. Association rule mining was used to generate the best rule for the association between independent features and the target feature. RESULT Out of 5264 study participants, 1893 (35.06%) males and 3371 (64.04%) females were included. The random forest classifier (sensitivity = 1.00, precision = 0.987, f1-score = 0.993, AUC = 0.9989) outperformed in predicting virological failure among all selected classifiers. Random forest feature importance and association rules identified the top eight predictors (Male, younger age, longer duration on ART, not taking CPT, not taking TPT, secondary educational status, TDF-3TC-EFV, and low CD4 counts) of virological failure based on the importance ranking, and the CD-4 count was recognized as the most important predictor feature. CONCLUSION The random forest classifier outperformed in predicting and identifying the relevant predictors of virological failure. The results of this study could be very helpful to health professionals in determining the optimal virological outcome.
Collapse
Affiliation(s)
- Daniel Niguse Mamo
- Department of Health Informatics, College of Medicine and Health Sciences, School of Public Health, Arbaminch University, Arbaminch, Ethiopia.
| | - Tesfahun Melese Yilma
- Department of Health Informatics, Institute of Public Health, University of Gondar, Gondar, Ethiopia
| | - Makida Fekadie
- Department of Health Informatics, Institute of Public Health, University of Gondar, Gondar, Ethiopia
| | - Yakub Sebastian
- College of Engineering, IT, and Environment, Charles Darwin University, Casuarina, Australia
| | - Tilahun Bizuayehu
- Department of Internal Medicine, School of Medicine, University of Gondar, Gondar, Ethiopia
| | - Mequannent Sharew Melaku
- Department of Health Informatics, Institute of Public Health, University of Gondar, Gondar, Ethiopia
| | - Agmasie Damtew Walle
- Department of Health Informatics, college of health science, Mettu University, Mettu, Ethiopia
| |
Collapse
|
2
|
Mundamshimu JS, Malale K, Kidenya BR, Gunda DW, Bwemelo L, Mwashiuya M, Omar SS, Mlowe N, Kiyumbi M, Ngocho JS, Balandya E, Sunguya B, Mshana SE, Mteta K, Bartlett J, Lyamuya E, Mmbaga BT, Kalluvya S. Failure to Attain HIV Viral Suppression After Intensified Adherence Counselling-What Can We Learn About Its Factors? Infect Drug Resist 2023; 16:1885-1894. [PMID: 37020794 PMCID: PMC10069435 DOI: 10.2147/idr.s393456] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/03/2022] [Accepted: 03/06/2023] [Indexed: 03/31/2023] Open
Abstract
Background Introduction and expansion of antiretroviral therapy (ART) have turned the tide of HIV pandemic, thus helping people living with HIV (PLHIV) achieve viral suppression. This success may need to be complemented by intensified adherence counseling (IAC) to improve adherence to treatment. However, some PLHIV still face higher than acceptable viral loads despite being on treatment. Purpose We investigated the factors associated with the failure to suppress HIV viral load after three months of IAC sessions. Patients and Methods This cross-sectional study analyzed secondary data from PLHIV-attended care and treatment clinics in Mwanza between January 2018 and December 2019 who had unsuppressed VL after being on ART for at least six months. We identified PLHIV in first-line ART with viral load evaluation before receiving IAC and had viral load results done at 90 days after IAC. We conducted descriptive statistics to examine the magnitude of viral suppression. Wilcoxon signed-rank test used to compare the median viral load before and after IAC sessions, and logistic regressions predicted the factors associated with failure. Results This study included 212 subjects. After intervention, most participants 85.9% (182) had significantly improved adherence compared to baseline. More than half 75.5% (160) of the participants had viral suppression after the intervention. Participants aged 18-25 years (AOR = 5.6, 95% CI, 1.1-29.6), unstable client during ART initiation (AOR = 0.3, 95% CI, 0.13-0.62), and poor adherence to ART (AOR = 4, 95% CI, 1.3-12.3) remained the main predictors of virological failure after IAC intervention. Conclusion Even though virological suppression is influenced by ART adherence, the findings in this study have shown co-existence of other factors to be addressed. Unstable during ART initiation is a new factor identified in this study.
Collapse
Affiliation(s)
| | - Kija Malale
- Catholic University of Health and Allied Sciences, Mwanza, Tanzania
| | - Benson R Kidenya
- Catholic University of Health and Allied Sciences, Mwanza, Tanzania
| | - Daniel W Gunda
- Catholic University of Health and Allied Sciences, Mwanza, Tanzania
| | - Logious Bwemelo
- Catholic University of Health and Allied Sciences, Mwanza, Tanzania
| | | | | | - Neema Mlowe
- Catholic University of Health and Allied Sciences, Mwanza, Tanzania
| | - Magwa Kiyumbi
- Catholic University of Health and Allied Sciences, Mwanza, Tanzania
| | - James S Ngocho
- Kilimanjaro Christian Medical University College, Moshi, Tanzania
- Kilimanjaro Clinical Research Institute, Moshi, Tanzania
| | - Emmanuel Balandya
- Muhimbili University of Health and Allied Sciences, Dar es Salaam, Tanzania
| | - Bruno Sunguya
- Muhimbili University of Health and Allied Sciences, Dar es Salaam, Tanzania
| | - Stephen E Mshana
- Catholic University of Health and Allied Sciences, Mwanza, Tanzania
| | - Kien Mteta
- Kilimanjaro Christian Medical University College, Moshi, Tanzania
| | - John Bartlett
- Kilimanjaro Christian Medical University College, Mosh, Tanzania
- Duke Global Health Institute, Duke University Medical Center, Durham, NC, USA
| | - Eligius Lyamuya
- Muhimbili University of Health and Allied Sciences, Dar es Salaam, Tanzania
| | - Blandina Theophil Mmbaga
- Kilimanjaro Christian Medical University College, Moshi, Tanzania
- Kilimanjaro Clinical Research Institute, Moshi, Tanzania
| | - Samuel Kalluvya
- Catholic University of Health and Allied Sciences, Mwanza, Tanzania
| |
Collapse
|
3
|
Jaleta F, Bekele B, Kedir S, Hassan J, Getahun A, Ligidi T, Garoma G, Itefa K, Gerenfes T, Botore A, Kenate B, Dagafa G, Muleta D. Predictors of unsuppressed viral load among adults on follow up of antiretroviral therapy at selected public and private health facilities of Adama town: unmached case-control study. BMC Public Health 2022; 22:1770. [PMID: 36123609 PMCID: PMC9484167 DOI: 10.1186/s12889-022-14169-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/26/2022] [Accepted: 09/12/2022] [Indexed: 11/10/2022] Open
Abstract
BACKGROUND Despite the scale up of antiretroviral therapy (ART), unsuppressed viral load among population taking ART in private and public health facilities is still a public health concern increasing the risk of treatment failure. Studies comprehensively assessing significant predictors of non-suppressed viral load among patients on follow up of AR in public and private health facilities are limited. The objective of the study was to identify predictors of unsuppressed viral load among adult patients taking antiretroviral therapy at selected public and private health facilities of Adama town, East shewa zone, Ethiopia. METHODS An unmatched case-control study was conducted from April 15 /2021 to May 20/2021. A total sample size of 347 patients consisting 116 cases and 231 controls was selected from electronic database among patients who started ART from September 2015 to August 2020. Data were collected using checklist from patient medical records and analyzed by SPSS. The association of dependent and independent variables was determined using multivariate analysis with 95% confidence interval and P - value in logistic regression model to identify independent predictors. RESULT From the total 347 participants, 140 (40.3%) of them were males and 207 (59.7%) were females. In multivariate logistic regression, CD4 count < 100 [(AOR:1.22, 95% CI: 1.4-7.3)], CD4 100-200[(AOR: 2.58 95% CI: 1.06-8.28)], Fair Adherence [(AOR: 2.44, 95% CI: 1.67-4.82)], poor adherence [(AOR: 1.11, 95% CI: 1.7-6.73)], History of Cotrimoxazole Therapy (CPT) use and not used [(AOR: 2.60, 95% CI: 1.23-5.48)] and History of drug substitution [(AOR:. 361, 95% CI: .145-.897)] were independent predictors of unsuppressed viral load with the p-value less than 0.05. CONCLUSION AND COMMENDATION In this study, Baseline CD4, adherence, History of CPT used and history of drug substitution was predictors of unsuppressed viral load. Monitoring immunological response through scheduled CD4 tests is essential to maintain immunity of the patients preventing diseases progression. Intensive adherence support and counseling should conclusively be provided through effective implementation of ART programs by providers would enhance viral suppression ensuring the quality of care and treatment.
Collapse
Affiliation(s)
- Fraol Jaleta
- Department of Public Health Emergency Preparedness and Research, Adama Public Health Research and Referral Laboratory Center, Adama, Ethiopia.
| | - Bayissa Bekele
- Department of Public Health Emergency Preparedness and Research, Adama Public Health Research and Referral Laboratory Center, Adama, Ethiopia
| | - Soriya Kedir
- Department of Public Health Emergency Preparedness and Research, Adama Public Health Research and Referral Laboratory Center, Adama, Ethiopia
| | - Jemal Hassan
- Department of Public Health and Water Analysis, Adama Public Health Research and Referral Laboratory Center, Adama, Ethiopia
| | - Asnakech Getahun
- Department of Referral Diagnosis, Adama Public Health Research and Referral laboratory Center, Adama, Ethiopia
| | - Tadesse Ligidi
- Department of Capacity Building, Adama Public Health Research and Referral laboratory Center, Adama, Ethiopia
| | - Getinet Garoma
- Department of Capacity Building, Adama Public Health Research and Referral laboratory Center, Adama, Ethiopia
| | - Kiflu Itefa
- Department of Referral Diagnosis, Adama Public Health Research and Referral laboratory Center, Adama, Ethiopia
| | - Tadesse Gerenfes
- Department of Bio Safety and Bio Security, Ethiopian Public Health Institute, Addis Ababa, Ethiopia
| | - Abera Botore
- Department of Public Health Emergency Preparedness and Research, Oromia Regional Health Bureau, Addis Ababa, Ethiopia
| | - Berhanu Kenate
- Department of Public Health Emergency Preparedness and Research, Oromia Regional Health Bureau, Addis Ababa, Ethiopia
| | - Gutu Dagafa
- Department of Anesthesiology, Myungsung Christian Medical Hospital, Addis Ababa, Ethiopia
| | - Daba Muleta
- Chief Executive Officer at Adama Public Health Research and Referral Center, Adama, Ethiopia
| |
Collapse
|
4
|
Kiros T, Taye A, Workineh L, Eyayu T, Damtie S, Hailemichael W, Tiruneh T. Immuno-virological status and its associated factors among HIV-positive patients receiving highly active antiretroviral therapy at delgi primary hospital, northwest Ethiopia, 2020/2021: A cross-sectional study. Heliyon 2022; 8:e10169. [PMID: 36033289 PMCID: PMC9399164 DOI: 10.1016/j.heliyon.2022.e10169] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/25/2021] [Revised: 03/17/2022] [Accepted: 07/28/2022] [Indexed: 11/29/2022] Open
Abstract
Background Highly active antiretroviral therapy (HAART) improves clinical outcomes by suppressing viral replication and allowing immune reconstitution. It also reduces HIV-related complications including morbidity, mortality, and extended hospitalizations for HIV-positive individuals. Regular assessment for antiretroviral treatment response is fundamentally important to address the factors associated with the poor clinical outcome including immunologic failures among HIV-positive patients on HAART. Therefore, this study aimed to investigate the immuno-virological status and describe its determinants among HIV-positive patients receiving HAART at Delgi primary hospital, Northwest Ethiopia. Methods A hospital-based cross-sectional study was conducted at Delgi primary hospital from October 25th through June 19th 2021 among a total of 442 study participants. A systematic random sampling technique was employed to enrol participants in the study. Socio-demographic and clinically related data were collected using a semi-structured questionnaire. About 3–5 ml of venous blood was collected aseptically for CD4+ T cell count and viral load test. SPSS version 20 software was used for statistical analysis. Bivariate and multivariate logistic regression analyses were conducted to determine the factors associated with immuno-virologic status among HIV-positive patients on HAART. The odds ratio with 95% CI was computed to determine the strength of association. Then, a p-value < 0.05 was considered a statistically significant association. For this study, the results were presented by using frequency summary tables, and texts. Results Among the total study participants, 283 (64%) were males and the mean age of the study participants was 37 ± 11.5. The overall immunological and virological failure among highly active antiretroviral therapy (HAART) receiving participants was found to be 9.5% (42/442, 95%CI:3.23–15.09) and 12.2% (54/442, 95% CI: 2.81–23.04) respectively. In the multivariate analysis, study participants with age ≥50 years old [AOR = 1.97, p = 0.01, 95%CI (0.02–4.03)], participants having current viral load count greater ≥1000 copies/ml [AOR = 3.97, p = 0.03, 95%CI (1.09–5.01)] and having TB-co-infection [AOR = 2.51, p = 0.05, 95%CI (1.02–7.51)] were statistically associated with increased risk of immunological failure. Similarly, TB-coinfected participants were 1.88 (95%CI = 0.89–10.02) times at greater risk for virological failure. Conclusion In this study, the magnitude of immuno-virological failure is alarming. This may be shown the need for integrated and substantial commitment to enhancing patient antiretroviral treatment adherence in the study area. Also, regular assessment for antiretroviral treatment response is fundamentally important to address the determinants associated with virological and immunologic failures among HIV-positive patients taking HAART. Furthermore, early initiation of HAART may be imperative to achieve favourable virological suppression and immunological reconstitution.
Collapse
Affiliation(s)
- Teklehaimanot Kiros
- Department of Medical Laboratory Sciences, College of Health Sciences and School of Medicine, Debre Tabor University, Debre Tabor, Ethiopia
| | - Abebe Taye
- Department of Medical Laboratory Sciences, College of Health Sciences and School of Medicine, Debre Tabor University, Debre Tabor, Ethiopia
| | - Lemma Workineh
- Department of Medical Laboratory Sciences, College of Health Sciences and School of Medicine, Debre Tabor University, Debre Tabor, Ethiopia
| | - Tahir Eyayu
- Department of Medical Laboratory Sciences, College of Health Sciences and School of Medicine, Debre Tabor University, Debre Tabor, Ethiopia
| | - Shewaneh Damtie
- Department of Medical Laboratory Sciences, College of Health Sciences and School of Medicine, Debre Tabor University, Debre Tabor, Ethiopia
| | - Wasihun Hailemichael
- Department of Medical Laboratory Sciences, College of Health Sciences and School of Medicine, Debre Tabor University, Debre Tabor, Ethiopia
| | - Tegenaw Tiruneh
- Department of Medical Laboratory Sciences, College of Health Sciences and School of Medicine, Debre Tabor University, Debre Tabor, Ethiopia
| |
Collapse
|
5
|
Mugglin C, Kläger D, Gueler A, Vanobberghen F, Rice B, Egger M. The HIV care cascade in sub-Saharan Africa: systematic review of published criteria and definitions. J Int AIDS Soc 2021; 24:e25761. [PMID: 34292649 PMCID: PMC8297382 DOI: 10.1002/jia2.25761] [Citation(s) in RCA: 14] [Impact Index Per Article: 4.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/16/2020] [Revised: 05/14/2021] [Accepted: 05/25/2021] [Indexed: 01/08/2023] Open
Abstract
INTRODUCTION The HIV care cascade examines the attrition of people living with HIV from diagnosis to the use of antiretroviral therapy (ART) and suppression of viral replication. We reviewed the literature from sub-Saharan Africa to assess the definitions used for the different steps in the HIV care cascade. METHODS We searched PubMed, Embase and CINAHL for articles published from January 2004 to December 2020. Longitudinal and cross-sectional studies were included if they reported on at least one step of the UNAIDS 90-90-90 cascade or two steps of an extended 7-step cascade. A step was clearly defined if authors reported definitions for numerator and denominator, including the description of the eligible population and methods of assessment or measurement. The review protocol has been published and registered in Prospero. RESULTS AND DISCUSSION Overall, 3364 articles were screened, and 82 studies from 19 countries met the inclusion criteria. Most studies were from Southern (38 studies, 34 from South Africa) and East Africa (29 studies). Fifty-eight studies (71.6%) were longitudinal, with a median follow-up of three years. The medium number of steps covered out of 7 steps was 3 (interquartile range [IQR] 2 to 4); the median year of publication was 2015 (IQR 2013 to 2019). The number of different definitions for the numerators ranged from four definitions (for step "People living with HIV") to 21 (step "Viral suppression"). For the denominators, it ranged from three definitions ("Diagnosed and aware of HIV status") to 14 ("Viral suppression"). Only 12 studies assessed all three of the 90-90-90 steps. Most studies used longitudinal data, but denominator-denominator or denominator-numerator linkages over several steps were rare. Also, cascade data are lacking for many countries. Our review covers the academic literature but did not consider other data, such as government reports on the HIV care cascade. Also, it did not examine disengagement and reengagement in care. CONCLUSIONS The proportions of patients retained at each step of the HIV care cascade cannot be compared between studies, countries and time periods, nor meta-analysed, due to the many different definitions used for numerators and denominators. There is a need for standardization of methods and definitions.
Collapse
Affiliation(s)
- Catrina Mugglin
- Institute of Social and Preventive Medicine (ISPM)University of BernBernSwitzerland
| | - Delia Kläger
- Institute of Social and Preventive Medicine (ISPM)University of BernBernSwitzerland
| | - Aysel Gueler
- Institute of Social and Preventive Medicine (ISPM)University of BernBernSwitzerland
| | - Fiona Vanobberghen
- Faculty of Epidemiology and Population HealthLondon School of Hygiene and Tropical MedicineLondonUK
- Swiss Tropical and Public Health InstituteBaselSwitzerland
- University of BaselBaselSwitzerland
| | - Brian Rice
- Faculty of Epidemiology and Population HealthLondon School of Hygiene and Tropical MedicineLondonUK
| | - Matthias Egger
- Institute of Social and Preventive Medicine (ISPM)University of BernBernSwitzerland
- Centre for Infectious Disease Epidemiology and Research (CIDER)University of Cape TownCape TownSouth Africa
- Population Health SciencesBristol Medical SchoolUniversity of BristolBristolUK
| | | |
Collapse
|