Risk Factors For Dropout Research Articles

Analysis of Risk Factors and Predictors of Success in Controlling Drop Out Pulmonary Tuberculosis: An Observational Study in Batang Regency, Indonesia

Introduction: Pulmonary tuberculosis (TB) remains a significant public health problem in Batang Regency, Indonesia. The high drop out (DO) rate of treatment is one of the main obstacles in controlling TB. This study aims to identify risk factors and predictors of DO for pulmonary TB treatment in Batang Regency. Methods: An analytical observational study with a cross-sectional design was conducted in 2023 involving 150 pulmonary TB patients who were recorded as having DO in the 2021-2022 period. Primary data was collected through interviews and secondary data from medical records. Bivariate analysis using the Chi-square test or Fisher's exact test, and multivariate analysis using logistic regression were performed to identify risk factors and predictors of DO. Results: Bivariate analysis showed that young age (<25 years) (OR = 3.21; 95% CI: 1.54-6.69), long distance of residence from health facilities (OR = 4.12; 95% CI: 1.98-8.57), and a history of adverse drug reactions (ESO) (OR = 5.63; 95% CI: 2.65-11.94) were significant risk factors for DO. Multivariate analysis confirmed that young age (aOR = 2.95; 95% CI: 1.35-6.43), long distance of residence (aOR = 3.88; 95% CI: 1.79-8.41), and history of ESO (aOR = 5.12; 95% CI: 2.38-11.01) were independent predictors of DO. Conclusion: Young age, long distance of residence from health facilities, and history of ESO are risk factors and independent predictors of DO for pulmonary TB treatment in Batang Regency. Interventions that target these factors, such as intensive education and counseling for young patients, increased access to health services, and optimal management of ESO, are needed to increase the success of TB control.

Who will stay and who will go? Identifying risk factors for psychotherapy dropout

AbstractObjectiveDropout from psychotherapy remains an issue across various treatment modalities and psychological disorders, with roughly 20% of clients failing to complete treatment. Dropping out of psychotherapy is associated with worse psychological and physical health outcomes. This study aimed to use a clinically generalisable definition of dropout to identify risk factors for dropping out of psychotherapy.MethodRetrospective chart review methods were used to collect data on 203 clients seen at a community‐based clinical psychology doctoral training clinic.ResultsIndependent samples t‐tests and chi‐squared tests for independence indicated that clients who dropped out of psychotherapy were more likely to be non‐students, live farther away from the treatment clinic and no‐show at least once in the first four sessions of therapy.DiscussionTo address dropout risk, it is important that clinicians be attuned to possible indicators of structural and motivational barriers to treatment engagement.

Competing Risks Model to Evaluate Dropout Dynamics Among the Type 1 Diabetes Patients Registered with the Changing Diabetes in Children (CDiC) Program

Understanding the survival dynamics of registered patients on a disease control program is a vital issue for the success of program objectives. Dropout of registered patients from such a program is a critical issue, hindering the effectiveness of the program. This study aimed to identify the risk factors of dropout of patients who were registered on the Changing Diabetes in Children (CDiC) program, taking a case of Uganda. Survival analysis was done by integrating competing risk of factors associated with attrition from the CDiC program. The data for the study was obtained from patients with type 1 diabetes mellitus (T1DM) registered during 2009-2018 at health units with specialized pediatric diabetes clinics from various regions in Uganda. The study considered follow-up data of 1132 children with T1DM. Our analysis revealed that the Body Mass Index (BMI) significantly influences dropout time, with patients classified as underweight showing higher hazards than those with normal BMI. Moreover, when considering competing risks, dropout hazards increased. Comparing the Cox model with the Fine and Gray model shows the latter exhibiting a smaller AIC value, which indicates its superiority in the time-to-dropout analysis. Thus, utilizing methods that integrate competing risks for CDiC dropout analysis is preferable and recommended for related studies. These findings provide actionable insights for enhancing CDiC program efficacy.

Risk factors for dropout from psychological substance use disorder treatment programs in criminal justice settings

BackgroundSubstance use disorders are highly prevalent in people within the criminal justice system. Psychological programs are the most common type of treatment available and have been shown to decrease recidivism, but dropping out of treatment is common. Risk factors associated with treatment dropout remain unclear in this setting, and whether the risk factors differ by treatment form (group-based vs. individual). MethodsOutcome (treatment dropout) was defined as not finishing the program due to client’s own wish, misbehavior, no-shows, or because program leader found client to be unsuitable. Predictors of treatment dropout included a comprehensive set of individual-level clinical, socioeconomic, and crime-related pre-treatment characteristics. Multivariable regression models were used to estimate the associations between predictors and dropout. FindingsThe study cohort included 5239 criminal justice clients who participated in a psychological treatment program (group-based or individual). Multivariable logistic regression models showed that female sex (OR=1.64, 95% CI 1.20–2.25), age (0.99, [0.97–1.00]), sentence length (0.98, [0.97–0.98]), higher education (0.54, [0.28–1.00]), number of violent offenses (1.03, [1.01–1.05]), and anxiety disorders (1.32, [1.01–1.72]) were associated with dropout from the individual treatment program. For the group-based program, age (OR=0.98, 95% CI 0.96–1.00), sentence length (OR=0.96, 95% CI 0.94–0.98), stimulant use disorder (OR=1.48, 95%, 1.00–2.19), and self-harm (OR 1.52, 95% CI 1.00–2.34) were associated with dropout. ConclusionsWe identified certain sociodemographic, crime-related, and clinical characteristics that were particularly important in predicting dropout from psychological treatment. Further, we find that there are similarities and differences in predictors of dropout from group-based and individual treatment forms.

Risk and protective factors for early dropout from telephone monitoring for individuals with drug convictions in community mental health centers in Japan

IntroductionIndividuals involved with the criminal justice system face challenges in receiving and maintaining substance use disorder (SUD) treatment and support. Although telephone monitoring (TM) could reduce these barriers, data on TM for community-dwelling individuals involved with the criminal justice system and research on individuals who drop out of TM are scarce. We examined the factors associated with dropping out early from the Voice Bridges Project, which provides TM for individuals on probation for drug-related convictions through community mental health centers in Japan. MethodsParticipants (n = 546) were individuals aged ≥20 years with methamphetamine-related convictions who were on probation. Univariate analyses examine the associations between one-year follow-up status and baseline variables, and multivariate Cox proportional hazards regression analyses identify the risk and protective factors associated with dropping out. Stratified analyses report results based on sex and halfway-house residency. ResultsThe one-year dropout rate was 43.6 % (n = 238). Multivariate analysis identified two risk factors for dropping out—halfway-house residency and suicide attempts in the past year, and two protective factors—higher education and the current use of SUD services. Sex-stratified analyses showed that halfway-house residency was a risk factor for both men and women. Attempted suicide was a risk factor for women. Conversely, higher education and current use of SUD services were protective factors for men. ConclusionsOur results identify unique risk factors for women, such as a recent history of suicide attempts, and distinctive protective factors for men, including higher education and current use of SUD services, emphasizing the importance of sex-specific approaches. Furthermore, the study reveals that irrespective of sex, vulnerable individuals, such as halfway-house residents, are at a higher risk of dropping out from TM.

Psychosocial factors as risk of dropout in university students of the Early Care and Early Childhood Education Program

The present study analyzed psychosocial risk factors for dropout in students of the Early Care and Early Childhood Education Program. A non-experimental, transversal and descriptive design was carried out. The sample was made up of 102 students, to whom sociodemographic and modified dropout questionnaires were applied. The results showed that the average academic performance in three semesters (57.8%, 56%, 49%); 87.3% of students work, 52.9% full time, affecting their performance; 41.2% understand the contents only sometimes; the family conceives the student poorly (3.9%), very high family expectations (13.7%), they feel valued as bad students (5.9%), affecting their motivation; 70% entered on the advice of others; 5.9% have worse performance than their peers, related to repetition and indirectly dropping out, and more than 78% report deficiencies in previous courses. The students identified the main risk factors for dropping out: economic difficulties (26.5%), family problems (13.7%), possibility of missing the year (11.8%) and job placement (10.8%).

A Qualitative Study of the Dropout Risk Factors in Open and Distance Learning (ODL)

A Qualitative Study of the Dropout Risk Factors in Open and Distance Learning (ODL)

Synthesis and Model Development of Thai Undergraduate Dropout Risk Factors

This study synthesizes existing research to explore factors affecting student attrition in Thai higher education institutions and develop a causal model for dropout risk. The synthesis uses a mixed-method approach following PRISMA 2020 guidelines, drawing on six years of Thai contextual studies on student attrition, academic intention, commitment, and persistence. Through a systematic review of multiple databases, 21 quantitative or mixed-method studies were identified for inclusion, which yielded 107 items representing 186 occurrences related to student dropout or persistence factors in Thai higher education. These items were grouped into nine clusters: academic integration, attitudinal and behavioral factors, classroom and institutional environment, emotional distress, family support, financial considerations, institutional support, social integration, and student satisfaction. The model synthesizes research findings on student attrition in Thai universities, providing a comprehensive framework for understanding the factors influencing students' persistence and dropout risk. By considering the interplay between these factors, the model aids in developing targeted interventions and informed policy decisions that promote academic success and ensure the long-term efficacy of Thai higher education institutions. The model's application can potentially guide researchers, educators, and policymakers in addressing the challenges students face within the Thai higher education system, ultimately fostering a more supportive and conducive environment for academic achievement.

Analysis of cox proportional hazard model for dropout students in university: case study from SIMAD university

PurposeThe main purpose of this study is to evaluate the extent of dropout students and identify the relationship between risk factors of dropout and the survival time of students.Design/methodology/approachThe Kaplan–Meier estimator (KM), also known as the product-limit technique, is a nonparametric model function that is commonly used in estimating survival function events (Kaplan and Meier, 1958). The survival function's Kaplan–Meier estimators are used to estimate and graph survival probabilities as a function of time, as well as explanatory data analysis (EDA) for the survival data, including the median survival time, and compare for two or more of the survival events. In addition, Cox proportional hazards model is employed for modelling purpose.FindingsResults of the Kaplan–Meier curves show that male students have lower survival rates than female, researchers have found that there is a difference between the survival times of the student's school types, results show students from English-based schools are higher than Arabic-based schools as suggested by the survival curve. Similarly, there is a difference between the survival times of students aging equal or greater than 25 and students aging less than 25 and survival function estimates of dropout according to high school grade marks has huge difference. These results were confirmed using log rank test as age, school type and marks were statistically significantly different while gender is not statistically significant.Research limitations/implicationsThere is no study of this kind from the Somalia context about the student's dropout. Subsequent to the outbreak of civil war in 1988 and the collapse of the central government in 1991, all public social services in Somalia including education centers were severely disrupted.Originality/valueThe statistical methods discussed in the previous section will be applied on a real dataset obtained from different offices of the university; most of the data were extracted from faculty of economics office and admission and record office. The data set comprised of 70 students from SIMAD university, consists of full-time faculty of economics students who enrolled at the university in the academic year of 2017–2018 until two years of diploma, students either complete 24 months of diploma or leave the university and that is the event of interest.

Determinants of School dropouts among adolescents: Evidence from a longitudinal study in India.

India has the largest adolescent population in the world. However, many unprivileged Indian adolescents are still unable to complete schooling. Hence, there is a need to understand the reasons for school dropout among this population. The present study is an attempt to understand the determinants of school dropout among adolescents and identify the factors and reasons that contribute to it. Longitudinal survey data- Understanding Adults and Young Adolescents (UDAYA) for Bihar and Uttar Pradesh has been used to identify the determinants of school dropout among adolescents aged 10-19. The first wave of the survey was conducted in 2015-2016, and the follow-up survey in 2018-2019. Descriptive statistics along with bivariate and multivariate analysis was used to observe school dropout rates and factors associated with it among adolescents. Results show that the school dropout rate was highest among married girls aged 15-19 years (84%), followed by unmarried girls (46%), and boys (38%) of the same age group. The odds of school dropout among adolescents decreased with an increase in household wealth status. School dropout was significantly less likely among adolescents whose mothers were educated as compared to mothers who had no education. Younger boys [AOR: 6.67; CI: 4.83-9.23] and girls [AOR: 2.56; CI: 1.79-3.84] who engaged in paid work were 6.67 times and 2.56 times more likely to drop out of school than those who were not. The likelihood of school dropout was 3.14 times more likely among younger boys [AOR: 3.14; CI: 2.26-4.35], and it was 89% more likely among older boys [AOR: 1.89; CI: 1.55-2.30] who consumed any substances as compared to those who did not consume any substances. Both younger [AOR: 2.05; CI: 1.37-3.05] and older girls [AOR: 1.30; CI: 1.05-1.62] who acknowledged at least one form of discriminatory practice by parents were more likely to drop out of school than their counterparts. Lack of interest in studies/education not necessary (43%) was the predominant reason among younger boys for school dropout, followed by family reasons (23%) and paid work (21%). Dropout was prevalent among lower social and economic strata. Mother's education, parental interaction, participation in sports and having role models reduce school dropout. Conversely, factors such as being engaged in paid work, substance abuse among boys, and gender discriminatory practices towards girls, are risk factors for dropout among adolescents. Lack of interest in studies and familial reasons also increase dropout. There is a need to improve the socio-economic status, delay the marital age of girls, and enhance the government incentives for education, give rightful work to girls after schooling, and provide awareness.

Psychosocial Predictors of Drop-Out from Organised Sport: A Prospective Study in Adolescent Soccer.

In recent years an increased drop-out rate in adolescents' soccer participation has been observed. Given the potentially adverse consequences of drop-out from soccer, more information about risk factors for drop-out is warranted. In the current study, Classification and Regression Tree (CRT) analysis was used to investigate demographic and motivational factors associated with an increased risk of drop-out from adolescent soccer. The results of this study indicate that older age, experiencing less autonomy support from the coach, less intrinsic motivation, being female, and lower socioeconomic status are factors associated with an increased risk of drop-out. An interpretation of the results of this study is that coaches play a central part in creating a sports context that facilitates motivation and continued soccer participation. Based on the findings of the current study we propose that soccer clubs implement theoretically informed coach education programs to help coaches adopt autonomy-supportive coaching strategies.

Urgent vs. planned peritoneal dialysis initiation: complications and outcomes in the first year of therapy.

Urgent-start peritoneal dialysis (US-PD) has been proposed as a safe modality of renal replacement therapy (RRT) for end-stage renal disease (ESRD) patients with an indication for emergency dialysis initiation. We aimed to compare the characteristics, 30-day complications, and clinical outcomes of US-PD and planned peritoneal dialysis (Plan-PD) patients over the first year of therapy. This was a single-center retrospective study that included incident adult patients followed for up to one year. US-PD was considered when incident patients started therapy within 7 days after Tenckhoff catheter implantation. Plan-PD group consisted of patients who started therapy after the breaking period (15 days). Mechanical and infectious complications were compared 30 days from PD initiation. Hospitalization and technique failure during the first 12 months on PD were assessed by Kaplan-Meier curves and the determinants were calculated by Cox regression models. All patients starting PD between October/2016 and November/2019 who fulfilled the inclusion criteria were analyzed. We evaluated 137 patients (70 in the US-PD x 67 Plan-PD). The main complications in the first 30 days were catheter tip migration (7.5% Plan-PD x 4.3% US-PD - p= 0.49) and leakage (4.5% Plan-PD x 5.7% US-PD - p=0.74). Most catheters were placed using the Seldinger technique. The main cause of dropout was death in US-PD patients (15.7%) and transfer to HD in Plan-PD patients (13.4%). The occurrence of complications in the first 30 days was the only risk factor for dropout (OR = 2.9; 95% CI 1.1-7.5, p = 0.03). Hospitalization rates and technique survival were similar in both groups. The lack of significant differences in patients' outcomes between groups reinforces that PD is a safe and applicable dialysis method in patients who need immediate dialysis.

Exploring psychosocial risk factors for dropout in adolescent female soccer

ABSTRACT Objectives We examined the manner in which age, participation in other sports, socioeconomic status, perceived sport competence, achievement goal orientations, and perceived motivational climate may interact to predict the risk of dropout among adolescent female soccer players. Methods Self-reported data from 519 female soccer players between 10 and 19 years of age (M = 13.41, SD = 1.77) were analysed using a person-centred approach to uncover the interactions among risk factors and their relative predictability of dropout. Results Perceived motivational climate was identified as the main predictor, where relatively lower levels of mastery climate were associated with a higher dropout tendency (absolute risk reduction [ARR] = 12.2% ±6.1% [95% CL]). If combined with relatively lower levels of mastery climate, then relatively lower levels of perceived sport competence were related to higher dropout risks (ARR = 16.5% ±9.5%), whereas, in combination with relatively higher levels of mastery climate, then relatively lower levels of ego-orientated achievement goals were associated with higher dropout rates (ARR = 10.8% ±12.6%) Conclusions Our findings afford novel insights into the interactions between, and the relative importance of, various risk factors for dropout in adolescent female soccer. This knowledge may be useful for soccer associations, clubs, and coaches when developing guidelines and strategies that aim to foster young females’ sustained participation in organised soccer.

Prevalence and prediction of dropout during depression treatment in routine outpatient care: an observational study

Efficacious treatments are available for major depressive disorder (MDD), but treatment dropout is common and decreases their effectiveness. However, knowledge about prevalence of treatment dropout and its risk factors in routine care is limited. The objective of this study was to determine the prevalence of and risk factors for dropout in a large outpatient sample. In this retrospective cohort analysis, routinely collected data from 2235 outpatients with MDD who had a diagnostic work-up between 2014 and 2016 were examined. Dropout was defined as treatment termination without achieving remission before the fourth session within six months after its start. Total and item scores on the Dutch Measure for Quantification of Treatment Resistance in Depression (DM-TRD) at baseline, and demographic variables were analyzed for their association with dropout using logistic regression and elastic net analyses. Data of 987 subjects who started routine outpatient depression treatment were included in the analyses of which 143 (14.5%) dropped out. Higher DM-TRD-scores were predictive for lower dropout odds [OR = 0.78, 95% CI = (0.70–0.86), p < 0.001]. The elastic net analysis revealed several clinical variables predictive for dropout. Higher SES, higher depression severity, comorbid personality pathology and a comorbid anxiety disorder were significantly associated with less dropout in the sample. In this observational study, treatment dropout was relatively low. The DM-TRD, an easy-to-use clinical instrument, revealed several variables associated with less dropout. When applied in daily practice and combined with demographical information, this instrument may help to reduce dropout and increase treatment effectiveness.

Characteristics of women who dropped out from pregnancy register in Okinawa, Japan: Findings from a retrospective cohort study.

There is little evidence regarding women who cannot register live births after pregnancy. We aimed to clarify the difference in baseline characteristics between women who registered live births and those who did not (i.e., dropout). We assessed the birth cohort data of 1976 Japanese women who registered their pregnancies between July 2013 and March 2014 in Naha and Urasoe City, Okinawa, Japan. The database consisted of anthropometric data, reproductive history, sociodemographic characteristics, and dietary intake. We estimated the prevalence ratio to examine the associations of baseline characteristics with dropout by multivariable-adjusted Poisson regression with robust standard error estimation. We identified 272 dropouts (13.8%) in the pregnancy registry. About 15% of women reported experience of alcohol drinking preceding 1 month of pregnancy registration. Most participants' vitamin B1 (92.1%) and folate (74.7%) consumption was inadequate considering the dietary reference intake for Japanese pregnant women, but it was not associated with a high prevalence of dropout. The prevalence of dropout was significantly higher in teenagers (prevalence ratio [PR]=2.06, 95% confidence interval [CI] 1.38-3.07) and early 20s (PR=1.42, 95% CI 1.04-1.93) than in women in late 20s. In addition, alcohol consumption was potentially associated with a high prevalence of dropout (adjusted prevalence ratio [aPR]=1.31, 95% CI 0.99-1.73). Participants who experienced one or more live births (aPR=0.43, 95% CI 0.28-0.66) were less likely to dropout. We found that the potential risk factors for dropout from pregnancy registration were young maternal age, no childbirth experience, and alcohol consumption.

Quality outcome of diabetes care during COVID-19 pandemic: a primary care cohort study

AimManagement of diabetes care can be affected by COVID-19 pandemic control measures. This study aimed to determine the impact of the pandemic, during 17.03.2020–16.03.2021, on quality outcomes of diabetes care in general practice in Switzerland.MethodsIn this retrospective cohort study, diabetes mellitus patients (≥ 18 years) with at least one consultation at a general practitioner, during 17.03.2018–16.03.2019 (cohort 1) and 17.03.2019–16.03.2020 (cohort 2) were included and followed-up for two years. Quality indicators and outcomes of diabetes care, at patient and practitioner level, were compared before and during the pandemic. Logistic regression was performed to identify patient’s risk factors for dropout from follow-up.ResultsData from 191 practices, 23,903 patients, cohort 1 and 25,092 patients, cohort 2, were analyzed. The fraction of patients lost to follow-up, attributable to the pandemic, was 28% (95% confidence interval: 25%, 30%). During the pandemic, compared to the previous year, regular measurement of weight, HbA1c, blood pressure and serum creatinine were less frequent and less patients per practitioner reached HbA1c and blood pressure target outcomes. Factors associated with continuity of care during the pandemic were: patient age 41–80 years, longer diabetes duration, diagnosis of hypertension or dyslipidemia, influenza vaccination during the last year. Risk factors for dropout were age > 80 and receiving only insulin as anti-diabetic medication.ConclusionA considerable quality reduction in diabetes mellitus care could be observed during the pandemic. Though the most vulnerable patients were not the most affected by the pandemic, key factors that might reduce dropout from follow-up were identified.

Gender Differences for Health Indicators in a Sample of School Dropout Adolescents: A Pilot Study.

Background: The ever-increasing prevalence of school dropout (SD) highlights the need to gain insight into risk factors for dropout causes and consequences. The aim of this study was to evaluate the gender differences for health indicators in a sample of school dropout adolescents. Methods: Data were collected regarding 450 adolescent’s SD (19 ± 2 years; 308 males), and health-related quality-of-life (HRQoL) and risk behaviors were assessed by means of a standardized questionnaire. Results: The results revealed that the female population was characterized by a compromised health indicator profile in terms of both risk behaviors and HRQoL dimensions. Conclusion: These findings indicate that SD is a multidimensional phenomenon, for which the implementation of multiple educational, social, and psychological policies aimed at mitigating the issue are recommended.

Predictors of dropout in university students participating in an 8-week e-mail-based cognitive-behavioral therapy for insomnia intervention.

We conducted an exploratory study to identify risk factors of dropout in an 8-week e-mail-based cognitive-behavioral therapy for insomnia (REFRESH) to improve sleep among university students with insomnia symptoms. University and graduate students in Hong Kong and Korea who scored higher than 10 on the Insomnia Severity Index participated in REFRESH. Of 158 participants from Hong Kong (n = 43) and Korea (n = 115), 90 (57%) did not complete all 7 sessions, while 52 of 90 (57.8%) dropped out prior to the fourth session. ROC analysis was conducted on the entire sample of 158 participants with intervention completion vs. dropout (non-completion) as the outcome variable. Predictors of dropout were wake time after sleep onset (WASO) < 7.1min on the weekly sleep diary and expectations for sleep (a subscale of dysfunctional beliefs and attitudes about sleep; DBAS) < 18 at baseline. These findings indicate that shorter WASO and less expectations for sleep at baseline were associated with risk of dropout from e-mail delivered self-help CBT-I-based intervention. Our results highlight the importance of identifying and tailoring treatment formats to students based on their presenting sleep characteristics.

Risk factors of dropout from institutional delivery among HIV positive antenatal care booked mothers within one year postpartum in Ethiopia: a case\u2013control study

BackgroundThe uptake of maternal healthcare services remains suboptimal in Ethiopia. Significant proportions of antenatal care attendees give birth at home in the context of HIV. However, in Ethiopia, evidence is scarce on the predictors of dropout from maternity continuum of care among HIV-positive mothers. Therefore, this study aimed to supply valuable information on risk factors regarding dropout of HIV-positive mothers for institutional delivery services in northwest Ethiopia.MethodsA multicenter case–control study was conducted at governmental health facilities in Gondar City from May one to June 30/2018. A total of 222 HIV-positive women were included in the study. Data were collected using structured questionnaires and checklists through face-to-face interview and chart review; entered into EPI INFO version seven, and then exported to SPSS version 25. Both descriptive and analytical procedures were performed. Binary logistic regression analysis was undertaken. A significant association was declared based on the adjusted odds ratio (AOR) with its 95% CI and p-value of ≤ 0.05.ResultsThis study illustrates that maternal age of ≥ 35 years (AOR = 2.37; 95%CI: 1.13,5.13), unmarried marital relation (AOR = 3.28; 95%CI: 1.51, 7.13), unemployed spousal occupation (AOR = 3.91; 95%CI: 1.54, 9.91), family monthly income of ≤ 36 US dollar (AOR = 4.87; 95%CI: 2.08, 11.42) and no obstetric complication in the index pregnancy (AOR = 13.89; 95%CI: 2.73, 27.71) were positively associated with dropout from institutional delivery among HIV positive antenatal care booked mothers.ConclusionIn this study, the risk factors of dropout from institutional delivery in the context of HIV-positive women were connected to social determinants of health such as advanced maternal age, unmarried marital status, unemployed husband occupation, and low family income. Therefore, interacting with the health system by focusing on these women in lower socio-economic strata and unmarried HIV-positive ANC attendees, and increasing access to information on obstetric complications during the antenatal care visit would retain clients in the continuum of maternity services.

Machine Learning for Predicting Risk of Early Dropout in a Recovery Program for Opioid Use Disorder.

Background: An increase in opioid use has led to an opioid crisis during the last decade, leading to declarations of a public health emergency. In response to this call, the Houston Emergency Opioid Engagement System (HEROES) was established and created an emergency access pathway into long-term recovery for individuals with an opioid use disorder. A major contributor to the success of the program is retention of the enrolled individuals in the program. Methods: We have identified an increase in dropout from the program after 90 and 120 days. Based on more than 700 program participants, we developed a machine learning approach to predict the individualized risk for dropping out of the program. Results: Our model achieved sensitivity of 0.81 and specificity of 0.65 for dropout at 90 days and improved the performance to sensitivity of 0.86 and specificity of 0.66 for 120 days. Additionally, we identified individual risk factors for dropout, including previous overdose and relapse and improvement in reported quality of life. Conclusions: Our informatics approach provides insight into an area where programs may allocate additional resources in order to retain high-risk individuals and increase the chances of success in recovery.