Predicting preventable hospital readmissions with causal machine learning

Marafino, Ben J; Schuler, Alejandro; Liu, Vincent X; Escobar, Gabriel J.; Baiocchi, Mike

doi:10.1111/1475-6773.13586

Cited by 13 publications

(13 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These characteristics make them particularly appealing for developing risk prediction algorithms that can be deployed at the level of populations for health system planning. While there is an increasing number of risk prediction models intended for clinical use in individuals in an ambulatory setting,25–28 there are few examples of a single, unified model that can be deployed on routinely collected data to regularly support population health and health system management 29. Databases with analogous AHD are available in most single-payer healthcare systems such as the UK, Australia and New Zealand.…”

Section: Introductionmentioning

confidence: 99%

Predicting hospitalisations related to ambulatory care sensitive conditions with machine learning for population health planning: derivation and validation cohort study

Harish

Gutierrez³

et al. 2022

BMJ Open

View full text Add to dashboard Cite

ObjectiveTo predict older adults’ risk of avoidable hospitalisation related to ambulatory care sensitive conditions (ACSC) using machine learning applied to administrative health data of Ontario, Canada.Design, setting and participantsA retrospective cohort study was conducted on a large cohort of all residents covered under a single-payer system in Ontario, Canada over the period of 10 years (2008–2017). The study included 1.85 million Ontario residents between 65 and 74 years old at any time throughout the study period.Data sourcesAdministrative health data from Ontario, Canada obtained from the (ICES formely known as the Institute for Clinical Evaluative Sciences Data Repository.Main outcome measuresRisk of hospitalisations due to ACSCs 1 year after the observation period.ResultsThe study used a total of 1 854 116 patients, split into train, validation and test sets. The ACSC incidence rates among the data points were 1.1% for all sets. The final XGBoost model achieved an area under the receiver operating curve of 80.5% and an area under precision–recall curve of 0.093 on the test set, and the predictions were well calibrated, including in key subgroups. When ranking the model predictions, those at the top 5% of risk as predicted by the model captured 37.4% of those presented with an ACSC-related hospitalisation. A variety of features such as the previous number of ambulatory care visits, presence of ACSC-related hospitalisations during the observation window, age, rural residence and prescription of certain medications were contributors to the prediction. Our model was also able to capture the geospatial heterogeneity of ACSC risk in Ontario, and especially the elevated risk in rural and marginalised regions.ConclusionsThis study aimed to predict the 1-year risk of hospitalisation from ambulatory-care sensitive conditions in seniors aged 65–74 years old with a single, large-scale machine learning model. The model shows the potential to inform population health planning and interventions to reduce the burden of ACSC-related hospitalisations.

show abstract

Section: Introductionmentioning

confidence: 99%

Predicting hospitalisations related to ambulatory care sensitive conditions with machine learning for population health planning: derivation and validation cohort study

Harish

Gutierrez³

et al. 2022

BMJ Open

View full text Add to dashboard Cite

show abstract

“…60 Our analysis, in its current form, although finding limited evidence for heterogeneity in the associations between implementation and readmission and mortality outcomes across levels of predicted risk, might not be able to capture the full extent of whatever treatment effect heterogeneity might exist. 61 Indeed, in our analysis we found that the regression discontinuity estimates of the extent of association between implementation and outcomes for patients at relatively lower risk (25%) tended to be larger than those from the difference-in-differences estimates, which represent an overall association that includes all patients at increased risk (25% to 100%), including high risk patients. This discrepancy was particularly pronounced for post-discharge mortality, where the regression discontinuity estimate suggesting benefit at a relatively lower risk level was statistically significant, but not the overall difference-in-differences estimate.…”

Section: Unanswered Questions and Future Researchmentioning

confidence: 53%

Section: Discussionmentioning

confidence: 99%

Evaluation of an intervention targeted with predictive analytics to prevent readmissions in an integrated health system: observational study

Marafino

Escobar

Baiocchi

et al. 2021

BMJ

Self Cite

View full text Add to dashboard Cite

Objectives To determine the associations between a care coordination intervention (the Transitions Program) targeted to patients after hospital discharge and 30 day readmission and mortality in a large, integrated healthcare system. Design Observational study. Setting 21 hospitals operated by Kaiser Permanente Northern California. Participants 1 539 285 eligible index hospital admissions corresponding to 739 040 unique patients from June 2010 to December 2018. 411 507 patients were discharged post-implementation of the Transitions Program; 80 424 (19.5%) of these patients were at medium or high predicted risk and were assigned to receive the intervention after discharge. Intervention Patients admitted to hospital were automatically assigned to be followed by the Transitions Program in the 30 days post-discharge if their predicted risk of 30 day readmission or mortality was greater than 25% on the basis of electronic health record data. Main outcome measures Non-elective hospital readmissions and all cause mortality in the 30 days after hospital discharge. Results Difference-in-differences estimates indicated that the intervention was associated with significantly reduced odds of 30 day non-elective readmission (adjusted odds ratio 0.91, 95% confidence interval 0.89 to 0.93; absolute risk reduction 95% confidence interval −2.5%, −3.1% to −2.0%) but not with the odds of 30 day post-discharge mortality (1.00, 0.95 to 1.04). Based on the regression discontinuity estimate, the association with readmission was of similar magnitude (absolute risk reduction −2.7%, −3.2% to −2.2%) among patients at medium risk near the risk threshold used for enrollment. However, the regression discontinuity estimate of the association with post-discharge mortality (−0.7% −1.4% to −0.0%) was significant and suggested benefit in this subgroup of patients. Conclusions In an integrated health system, the implementation of a comprehensive readmissions prevention intervention was associated with a reduction in 30 day readmission rates. Moreover, there was no association with 30 day post-discharge mortality, except among medium risk patients, where some evidence for benefit was found. Altogether, the study provides evidence to suggest the effectiveness of readmission prevention interventions in community settings, but further research might be required to confirm the findings beyond this setting.

show abstract

“…Causal inference in machine learning is a relatively new addition to the methodologic arsenal [ 5 ]. The causal forest, a special version of the generalized random forest [ 7 ], is the most widely used method for computing conditional average treatment effects in the medical literature; being used for readmission risk [ 11 ], targeted intervention development [ 6 ], diabetes epidemiology [ 12 ], and identification of risk factors for thyroid disease [ 13 ]. As discussed previously, causal machine learning methods are distinct from traditional supervised machine learning since these models estimate the treatment effect as opposed to risk or prediction.…”

Section: Discussionmentioning

confidence: 99%

“…As discussed previously, causal machine learning methods are distinct from traditional supervised machine learning since these models estimate the treatment effect as opposed to risk or prediction. Further, they are not bound by parametric assumptions common in traditional methods such as regression modeling and are less apt to overfit through application of regularization in the computation [ 8 , 11 ]. These factors, along with the ability to assess conditional average treatment effects in small sample sizes allowed us to perform a more robust analysis of these randomized data.…”

Section: Discussionmentioning

confidence: 99%

Effectiveness of oseltamivir treatment on clinical failure in hospitalized patients with lower respiratory tract infection

et al. 2021

View full text Add to dashboard Cite

Background Influenza is associated with excess morbidity and mortality of individuals each year. Few therapies exist for treatment of influenza infection, and each require initiation as early as possible in the course of infection, making efficacy difficult to estimate in the hospitalized patient with lower respiratory tract infection. Using causal machine learning methods, we re-analyze data from a randomized trial of oseltamivir versus standard of care aimed at reducing clinical failure in hospitalized patients with lower respiratory tract infection during the influenza season. Methods This was a secondary analysis of the Rapid Empiric Treatment with Oseltamivir Study (RETOS). Conditional average treatment effects (CATE) and 95% confidence intervals were computed from causal forest including 85 clinical and demographic variables. RETOS was a multicenter, randomized, unblinded, trial of adult patients hospitalized with lower respiratory tract infections in Kentucky from 2009 through 2012. Adult hospitalized patients with lower respiratory tract infection were randomized to standard of care or standard of care plus oseltamivir as early as possible after hospital admission but within 24 h of enrollment. After randomization, oseltamivir was initiated in the treatment arm per package insert. The primary outcome was clinical failure, a composite measure including failure to reach clinical improvement within 7 days, transfer to intensive care 24 h after admission, or rehospitalization or death within 30 days. Results A total of 691 hospitalized patients with lower respiratory tract infections were included in the study. The only subgroup of patients with a statistically significant CATE was those with laboratory-confirmed influenza infection with a 26% lower risk of clinical failure when treated with oseltamivir (95% CI 3.2–48.0%). Conclusions This study suggests that addition of oseltamivir to standard of care may decrease clinical failure in hospitalized patients with influenza-associated lower respiratory tract infection versus standard of care alone. These results are supportive of current recommendations to initiate antiviral treatment in hospitalized patients with confirmed or suspected influenza as soon as possible after admission. Trial registration Original trial: Clinical Trials.Gov; Rapid Empiric Treatment With Oseltamivir Study (RETOS) (RETOS); ClinicalTrials.gov Identifier: NCT01248715 https://clinicaltrials.gov/ct2/show/NCT01248715

show abstract

Predicting preventable hospital readmissions with causal machine learning

Cited by 13 publications

References 45 publications

Predicting hospitalisations related to ambulatory care sensitive conditions with machine learning for population health planning: derivation and validation cohort study

Predicting hospitalisations related to ambulatory care sensitive conditions with machine learning for population health planning: derivation and validation cohort study

Evaluation of an intervention targeted with predictive analytics to prevent readmissions in an integrated health system: observational study

Effectiveness of oseltamivir treatment on clinical failure in hospitalized patients with lower respiratory tract infection

Contact Info

Product

Resources

About