Dataset Information

Closing the gap on institutional delivery in northern India: a case study of how integrated machine learning approaches can enable precision public health.

ABSTRACT: INTRODUCTION:Meeting ambitious global health goals with limited resources requires a precision public health (PxPH) approach. Here we describe how integrating data collection optimisation, traditional analytics and causal artificial intelligence/machine learning (ML) can be used in a use case for increasing hospital deliveries of newborns in Uttar Pradesh, India. METHODS:Using a systematic behavioural framework we designed a large-scale survey on perceptual, interpersonal and structural drivers of women's behaviour around childbirth (n=5613). Multivariate logistic regression identified factors associated with institutional delivery (ID). Causal ML determined the cause-and-effect ordering of these factors. Variance decomposition was used to parse sources of variation in delivery location, and a supervised learning algorithm was used to distinguish population subgroups. RESULTS:Among the factors found associated with ID, the causal model showed that having a delivery plan (OR=6.1, 95% CI 6.0 to 6.3), believing the hospital is safer than home (OR=5.4, 95% CI 5.1 to 5.6) and awareness of financial incentives were direct causes of ID (OR=3.4, 95% CI 3.3 to 3.5). Distance to the hospital, borrowing delivery money and the primary decision-maker were not causal. Individual-level factors contributed 69% of variance in delivery location. The segmentation analysis showed four distinct subgroups differentiated by ID risk perception, parity and planning. CONCLUSION:These findings generate a holistic picture of the drivers and barriers to ID in Uttar Pradesh and suggest distinct intervention points for different women. This demonstrates data optimised to identify key behavioural drivers, coupled with traditional and ML analytics, can help design a PxPH approach that maximise the impact of limited resources.

SUBMITTER: Huang VS

PROVIDER: S-EPMC7542627 | biostudies-literature | 2020 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Closing the gap on institutional delivery in northern India: a case study of how integrated machine learning approaches can enable precision public health.

Huang Vincent S VS Morris Kasey K Jain Mokshada M Ramesh Banadakoppa Manjappa BM Kemp Hannah H Blanchard James J Isac Shajy S Sarkar Bidyut B Gothalwal Vikas V Namasivayam Vasanthakumar V Kumar Pankaj P Sgaier Sema K SK

BMJ global health 20201001 10

<h4>Introduction</h4>Meeting ambitious global health goals with limited resources requires a precision public health (PxPH) approach. Here we describe how integrating data collection optimisation, traditional analytics and causal artificial intelligence/machine learning (ML) can be used in a use case for increasing hospital deliveries of newborns in Uttar Pradesh, India.<h4>Methods</h4>Using a systematic behavioural framework we designed a large-scale survey on perceptual, interpersonal and stru ...[more]

PMID: 33028696

Similar Datasets

Project description:Background The rising economic burden of cancer on patients is an important determinant of access to treatment initiation and adherence in India. Several publicly financed health insurance (PFHI) schemes have been launched in India, with treatment for cancer as an explicit inclusion in the health benefit packages (HBPs). Although, financial toxicity is widely acknowledged to be a potential consequence of costly cancer treatment, little is known about its prevalence and determinants among the Indian population. There is a need to determine the optimal strategy for clinicians and cancer care centers to address the issue of high costs of care in order to minimize the financial toxicity, promote access to high value care and reduce health disparities. Methods A total of 12,148 cancer patients were recruited at seven purposively selected cancer centres in India, to assess the out-of-pocket expenditure (OOPE) and financial toxicity among cancer patients. Mean OOPE incurred for outpatient treatment and hospitalization, was estimated by cancer site, stage, type of treatment and socio-demographic characteristics. Economic impact of cancer care on household financial risk protection was assessed using standard indicators of catastrophic health expenditures (CHE) and impoverishment, along with the determinants using logistic regression. Results Mean direct OOPE per outpatient consultation and per episode of hospitalization was estimated as ₹8,053 (US$ 101) and ₹39,085 (US$ 492) respectively. Per patient annual direct OOPE incurred on cancer treatment was estimated as ₹331,177 (US$ 4,171). Diagnostics (36.4%) and medicines (45%) are major contributors of OOPE for outpatient treatment and hospitalization, respectively. The overall prevalence of CHE and impoverishment was higher among patients seeking outpatient treatment (80.4% and 67%, respectively) than hospitalization (29.8% and 17.2%, respectively). The odds of incurring CHE was 7.4 times higher among poorer patients [Adjusted Odds Ratio (AOR): 7.414] than richest. Enrolment in PM-JAY (CHE AOR = 0.426, and impoverishment AOR = 0.395) or a state sponsored scheme (CHE AOR = 0.304 and impoverishment AOR = 0.371) resulted in a significant reduction in CHE and impoverishment for an episode of hospitalization. The prevalence of CHE and impoverishment was significantly higher with hospitalization in private hospitals and longer duration of hospital stay (p < 0.001). The extent of CHE and impoverishment due to direct costs incurred on outpatient treatment increased from 83% to 99.7% and, 63.9% to 97.1% after considering both direct and indirect costs borne by the patient and caregivers, respectively. In case of hospitalization, the extent of CHE increased from 23.6% (direct cost) to 59.4% (direct+ indirect costs) and impoverishment increased from 14.1% (direct cost) to 27% due to both direct and indirect cost of cancer treatment. Conclusion There is high economic burden on patients and their families due to cancer treatment. The increase in population and cancer services coverage of PFHI schemes, creating prepayment mechanisms like E-RUPI for outpatient diagnostic and staging services, and strengthening public hospitals can potentially reduce the financial burden among cancer patients in India. The disaggregated OOPE estimates could be useful input for future health technology analyses to determine cost-effective treatment strategies.

Dataset Information

Closing the gap on institutional delivery in northern India: a case study of how integrated machine learning approaches can enable precision public health.

Publications

Closing the gap on institutional delivery in northern India: a case study of how integrated machine learning approaches can enable precision public health.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets