Aggregating Loss to Follow-Up Behaviour in People Living with HIV on ART: A Cluster Analysis Using Unsupervised Machine Learning Algorithm in R

22 Pages Posted: 25 Nov 2020

See all articles by Amobi Onovo

Amobi Onovo

USAID Nigeria

Akinyemi Atobatele

USAID Nigeria

Abiye Kalaiwo

United States Agency for International Development (USAID) - USAID Nigeria

Christopher Obanubi

United States Agency for International Development (USAID) - USAID Nigeria

Ezekiel James

United States Agency for International Development (USAID) - USAID Nigeria

Dolapo Ogundehin

USAID Nigeria

Pamela Gado

United States Agency for International Development (USAID) - USAID Nigeria

Gertrude Odezugo

United States Agency for International Development (USAID) - USAID Nigeria

Babatunji Odelola

United States Agency for International Development (USAID) - USAID Nigeria

Temitayo Odusote

USAID Nigeria

Isa Iyortim

United States Agency for International Development (USAID) - USAID Nigeria

Tessie Philips-Ononye

United States Agency for International Development (USAID) - USAID Nigeria

Jemeh Pius

United States Agency for International Development (USAID) - USAID Nigeria

Omosalewa Oyelaran

United States Agency for International Development (USAID) - USAID Nigeria

Helina Meri

United States Agency for International Development (USAID) - USAID Nigeria

Rachel Goldstein

United States Agency for International Development (USAID) - USAID Nigeria

Date Written: November 11, 2020

Abstract

Background
Lifelong antiretroviral therapy (ART) improves optimal health outcomes for HIV‐positive individuals, but is threatened by fluctuations in sustained care, self efficacy and hence poor adherence. Retention of patients in the HIV care continuum is crucial for epidemic control. This study aimed to aggregate loss to follow-up (LTFU) behaviour in People Living with HIV (PLHIV) into clusters in order to examine and describe PLHIV clusters having similar characteristics and patterns according to their risk profile.

Methods
This was a retrospective, cross-sectional study that randomly reviewed 11,589 records of LTFU adult patients initiated on first-line ART from 313 USAID/PEPFAR-supported HIV clinics spread across 5 of Nigeria’s 6 geographical regions between July 1, 2008 and June 30, 2020. LTFU, was defined for PLHIV on ART as > 28 days without an encounter since the last scheduled ART refill appointment. Using the Minkowski method and ward.D2 clustering technique for unsupervised machine learning algorithm "agglomerative hierarchical clustering" in R, we identified 6 clusters associated with patients LTFU behaviour.

Results
Within the review period, 497,620 patients were ever enrolled on ART. 324,225 (65.2%) remained on treatment, 101,716 (20.4%) had an LTFU event captured, 36,021 (7.2%) were transferred out to other facilities, 25,633 (5.2%) died and 10,025 (2.0%) self-terminated treatment. Approximately 11% (11,589) of LTFU patients were included. Majority (66.7%) of the clusters consist of female LTFUs. LTFU doubled steadily by age among adolescents (15-19 years) and young people (15-29 years), but as age increased above 40-years the rate of LTFU decreased. High rate of LTFU was reflective of shorter-time on ART. Patients classified in clusters with shorter-time on ART [8-months (female) vs. 72.6-months (male)] indicated the highest rates of LTFU [31.0% (female) vs. 14.9% (male)]. LTFU rate varied by region, was highest among clusters confined in the North West (50%) followed by the South South (33%) and lowest in the North East (17%). Viral load test was low, with only half (50.0%) of the clusters having a documented viral load test result.

Conclusion
LTFU rates in HIV-positive patients receiving ART in our clinical sites have varied by the duration of ART, with rates declining in recent years. Our study demonstrates that aggregating LTFU behaviour among patients on ART offers great benefit for LTFU surveillance in the HIV care continuum. Our findings would inform targeted HIV program interventions for patient-centered care, reduce LTFU and promote optimal retention.

Keywords: Loss to follow-up; Antiretroviral therapy; Hierarchical clustering; Viral load test; Nigeria

Suggested Citation

Onovo, Amobi and Atobatele, Akinyemi and Kalaiwo, Abiye and Obanubi, Christopher and James, Ezekiel and Ogundehin, Dolapo and Gado, Pamela and Odezugo, Gertrude and Odelola, Babatunji and Odusote, Temitayo and Iyortim, Isa and Philips-Ononye, Tessie and Pius, Jemeh and Oyelaran, Omosalewa and Meri, Helina and Goldstein, Rachel, Aggregating Loss to Follow-Up Behaviour in People Living with HIV on ART: A Cluster Analysis Using Unsupervised Machine Learning Algorithm in R (November 11, 2020). Available at SSRN: https://ssrn.com/abstract=3734679 or http://dx.doi.org/10.2139/ssrn.3734679

Amobi Onovo (Contact Author)

USAID Nigeria ( email )

Nigeria
+2347030538954 (Phone)

Akinyemi Atobatele

USAID Nigeria ( email )

Nigeria

Abiye Kalaiwo

United States Agency for International Development (USAID) - USAID Nigeria

Nigeria

Christopher Obanubi

United States Agency for International Development (USAID) - USAID Nigeria ( email )

Nigeria

Ezekiel James

United States Agency for International Development (USAID) - USAID Nigeria ( email )

Nigeria

Dolapo Ogundehin

USAID Nigeria ( email )

Nigeria

Pamela Gado

United States Agency for International Development (USAID) - USAID Nigeria ( email )

Nigeria

Gertrude Odezugo

United States Agency for International Development (USAID) - USAID Nigeria ( email )

Nigeria

Babatunji Odelola

United States Agency for International Development (USAID) - USAID Nigeria ( email )

Nigeria

Temitayo Odusote

USAID Nigeria ( email )

Nigeria

Isa Iyortim

United States Agency for International Development (USAID) - USAID Nigeria ( email )

Nigeria

Tessie Philips-Ononye

United States Agency for International Development (USAID) - USAID Nigeria ( email )

Nigeria

Jemeh Pius

United States Agency for International Development (USAID) - USAID Nigeria ( email )

Nigeria

Omosalewa Oyelaran

United States Agency for International Development (USAID) - USAID Nigeria ( email )

Nigeria

Helina Meri

United States Agency for International Development (USAID) - USAID Nigeria ( email )

Nigeria

Rachel Goldstein

United States Agency for International Development (USAID) - USAID Nigeria ( email )

Nigeria

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
172
Abstract Views
679
rank
245,138
PlumX Metrics