1
|
Jung HW, Jang JS. Constructing prediction models and analyzing factors in suicidal ideation using machine learning, focusing on the older population. PLoS One 2024; 19:e0305777. [PMID: 39038039 PMCID: PMC11262681 DOI: 10.1371/journal.pone.0305777] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/06/2024] [Accepted: 06/04/2024] [Indexed: 07/24/2024] Open
Abstract
Suicide among the older population is a significant public health concern in South Korea. As the older individuals have long considered suicide before committing suicide trials, it is important to analyze the suicidal ideation that precedes the suicide attempt for intervention. In this study, six machine learning algorithms were employed to construct a predictive model for suicidal thinking and identify key variables. A traditional logistic regression analysis was supplementarily conducted to test the robustness of the results of machine learning. All analyses were conducted using a hierarchical approach to compare the model fit of each model in both machine learning and logistic regression. Three models were established for analysis. In Model 1, socioeconomic, residential, and health behavioral factors were incorporated. Model 2 expanded upon Model 1 by integrating physical health status, and Model 3 further incorporated mental health conditions. The results indicated that the gradient boosting algorithm outperformed the other machine learning techniques. Furthermore, the household income quintile was the most important feature in Model 1, followed by subjective health status, oral health, and exercise ability in Model 2, and anxiety and depression in Model 3. These results correspond to those of the hierarchical logistic regression. Notably, economic and residential vulnerabilities are significant factors in the mental health of the older population with higher instances of suicidal thoughts. This hierarchical approach could reveal the potential target population for suicide interventions.
Collapse
Affiliation(s)
- Hyun Woo Jung
- Department of Health Administration, Graduate School, Yonsei University, Wonju, Republic of Korea
- Yonsei Institute of Health and Welfare, Yonsei University Mirae Campus, Wonju, Republic of Korea
| | - Jin Su Jang
- Human Behavior & Genetic Institute, Associate Research Center, Korea University, Seoul, Republic of Korea
| |
Collapse
|
2
|
Mputu Mputu P, Beauséjour M, Richard-Denis A, Fallah N, Noonan VK, Mac-Thiong JM. Classifying clinical phenotypes of functional recovery for acute traumatic spinal cord injury. An observational cohort study. Disabil Rehabil 2024:1-8. [PMID: 38390856 DOI: 10.1080/09638288.2024.2320267] [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: 04/18/2023] [Accepted: 02/14/2024] [Indexed: 02/24/2024]
Abstract
PURPOSE Identify patient subgroups with different functional outcomes after SCI and study the association between functional status and initial ISNCSCI components. METHODS Using CART, we performed an observational cohort study on data from 675 patients enrolled in the Rick-Hansen Registry(RHSCIR) between 2014 and 2019. The outcome was the Spinal Cord Independence Measure (SCIM) and predictors included AIS, NLI, UEMS, LEMS, pinprick(PPSS), and light touch(LTSS) scores. A temporal validation was performed on data from 62 patients treated between 2020 and 2021 in one of the RHSCIR participating centers. RESULTS The final CART resulted in four subgroups with increasing totSCIM according to PPSS, LEMS, and UEMS: 1)PPSS < 27(totSCIM = 28.4 ± 16.3); 2)PPSS ≥ 27, LEMS < 1.5, UEMS < 45(totSCIM = 39.5 ± 19.0); 3)PPSS ≥ 27, LEMS < 1.5, UEMS ≥ 45(totSCIM = 57.4 ± 13.8); 4)PPSS ≥ 27, LEMS ≥ 1.5(totSCIM = 66.3 ± 21.7). The validation model performed similarly to the original model. The adjusted R-squared and F-test were respectively 0.556 and 62.2(P-value <0.001) in the development cohort and, 0.520 and 31.9(P-value <0.001) in the validation cohort. CONCLUSION Acknowledging the presence of four characteristic subgroups of patients with distinct phenotypes of functional recovery based on PPSS, LEMS, and UEMS could be used by clinicians early after tSCI to plan rehabilitation and establish realistic goals. An improved sensory function could be key for potentiating motor gains, as a PPSS ≥ 27 was a predictor of a good function.
Collapse
Affiliation(s)
- Pascal Mputu Mputu
- Hôpital du Sacré-Cœur de Montréal/CIUSSS NÎM, Montreal, Canada
- Faculty of Medicine, Université de Montréal, Montreal, Canada
| | - Marie Beauséjour
- Department of Community Health Sciences, Université de Sherbrooke, Sherbrooke, Canada
- CHU Sainte-Justine, Montreal, Canada
| | - Andréane Richard-Denis
- Hôpital du Sacré-Cœur de Montréal/CIUSSS NÎM, Montreal, Canada
- Centre de recherche interdisciplinaire en réadaptation (CRIR), Montreal, Canada
| | - Nader Fallah
- Praxis Spinal Cord Institute, Vancouver, Canada
- University of British Columbia, Vancouver, Canada
| | - Vanessa K Noonan
- Praxis Spinal Cord Institute, Vancouver, Canada
- University of British Columbia, Vancouver, Canada
| | - Jean-Marc Mac-Thiong
- Hôpital du Sacré-Cœur de Montréal/CIUSSS NÎM, Montreal, Canada
- Faculty of Medicine, Université de Montréal, Montreal, Canada
| |
Collapse
|
3
|
Li H, Rosete S, Coyle J, Phillips RV, Hejazi NS, Malenica I, Arnold BF, Benjamin-Chung J, Mertens A, Colford JM, van der Laan MJ, Hubbard AE. Evaluating the robustness of targeted maximum likelihood estimators via realistic simulations in nutrition intervention trials. Stat Med 2022; 41:2132-2165. [PMID: 35172378 PMCID: PMC10362909 DOI: 10.1002/sim.9348] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/09/2021] [Revised: 01/20/2022] [Accepted: 01/26/2022] [Indexed: 12/18/2022]
Abstract
Several recently developed methods have the potential to harness machine learning in the pursuit of target quantities inspired by causal inference, including inverse weighting, doubly robust estimating equations and substitution estimators like targeted maximum likelihood estimation. There are even more recent augmentations of these procedures that can increase robustness, by adding a layer of cross-validation (cross-validated targeted maximum likelihood estimation and double machine learning, as applied to substitution and estimating equation approaches, respectively). While these methods have been evaluated individually on simulated and experimental data sets, a comprehensive analysis of their performance across real data based simulations have yet to be conducted. In this work, we benchmark multiple widely used methods for estimation of the average treatment effect using ten different nutrition intervention studies data. A nonparametric regression method, undersmoothed highly adaptive lasso, is used to generate the simulated distribution which preserves important features from the observed data and reproduces a set of true target parameters. For each simulated data, we apply the methods above to estimate the average treatment effects as well as their standard errors and resulting confidence intervals. Based on the analytic results, a general recommendation is put forth for use of the cross-validated variants of both substitution and estimating equation estimators. We conclude that the additional layer of cross-validation helps in avoiding unintentional over-fitting of nuisance parameter functionals and leads to more robust inferences.
Collapse
Affiliation(s)
- Haodong Li
- Divisions of Epidemiology & Biostatistics, University of California, Berkeley, Berkeley, California, USA
| | - Sonali Rosete
- Divisions of Epidemiology & Biostatistics, University of California, Berkeley, Berkeley, California, USA
| | - Jeremy Coyle
- Divisions of Epidemiology & Biostatistics, University of California, Berkeley, Berkeley, California, USA
| | - Rachael V Phillips
- Divisions of Epidemiology & Biostatistics, University of California, Berkeley, Berkeley, California, USA
| | - Nima S Hejazi
- Divisions of Epidemiology & Biostatistics, University of California, Berkeley, Berkeley, California, USA
| | - Ivana Malenica
- Divisions of Epidemiology & Biostatistics, University of California, Berkeley, Berkeley, California, USA
| | - Benjamin F Arnold
- Proctor Foundation, University of California, San Francisco, San Francisco, California, USA
| | - Jade Benjamin-Chung
- Epidemiology & Population Health, Stanford University, Stanford, California, USA
| | - Andrew Mertens
- Divisions of Epidemiology & Biostatistics, University of California, Berkeley, Berkeley, California, USA
| | - John M Colford
- Divisions of Epidemiology & Biostatistics, University of California, Berkeley, Berkeley, California, USA
| | - Mark J van der Laan
- Divisions of Epidemiology & Biostatistics, University of California, Berkeley, Berkeley, California, USA
| | - Alan E Hubbard
- Divisions of Epidemiology & Biostatistics, University of California, Berkeley, Berkeley, California, USA
| |
Collapse
|
4
|
Wallace J, McWilliams JM, Lollo A, Eaton J, Ndumele CD. Residual Confounding in Health Plan Performance Assessments: Evidence From Randomization in Medicaid. Ann Intern Med 2022; 175:314-324. [PMID: 34978862 DOI: 10.7326/m21-0881] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 11/22/2022] Open
Abstract
BACKGROUND Risk adjustment is used widely in payment systems and performance assessments, but the extent to which it distinguishes plan or provider effects from confounding due to patient differences is typically unknown. OBJECTIVE To assess the degree to which risk-adjusted measures of health plan performance adequately adjust for the variation across plans that arises because of differences in patient characteristics (residual confounding). DESIGN Comparison between plan performance estimates based on enrollees who made plan choices (observational population) and estimates based on enrollees assigned to plans (randomized population). SETTING Natural experiment in which more than two thirds of a state's Medicaid population in 1 region was randomly assigned to 1 of 5 plans. PARTICIPANTS 137 933 enrollees in 2013 to 2014, of whom 31.1% selected a plan and 68.9% were randomly assigned to 1 of the same 5 plans. MEASUREMENTS Annual total spending (that is, payments to providers), primary care use, dental care use, and avoidable emergency department visits, all scored as plan-specific deviations from the "average" plan performance within each population. RESULTS Enrollee characteristics were appreciably imbalanced across plans in the observational population, as expected, but were not in the randomized population. Annual total spending varied across plans more in the observational population (SD, $147 per enrollee) than in the randomized population (SD, $70 per enrollee) after accounting for baseline differences in the observational and randomized populations and for differences across plans. On average, a plan's spending score (its deviation from the "average" performance) in the observational population differed from its score in the randomized population by $67 per enrollee in absolute value (95% CI, $38 to $123), or 4.2% of mean spending per enrollee (P = 0.009, rejecting the null hypothesis that this difference would be expected from sampling error). The difference was reduced modestly by risk adjustment to $62 per enrollee (P = 0.012). Residual confounding was similarly substantial for most other performance measures. Further adjustment for social factors did not materially change estimates. LIMITATION Potential heterogeneity in plan effects between the 2 populations. CONCLUSION Residual confounding in risk-adjusted performance assessments can be substantial and should caution policymakers against assuming that risk adjustment isolates real differences in plan performance. PRIMARY FUNDING SOURCE Arnold Ventures.
Collapse
Affiliation(s)
- Jacob Wallace
- Yale School of Public Health, New Haven, Connecticut (J.W., A.L., C.D.N.)
| | - J Michael McWilliams
- Department of Health Care Policy, Harvard Medical School, and Division of General Internal Medicine and Primary Care, Brigham and Women's Hospital, Boston, Massachusetts (J.M.M.)
| | - Anthony Lollo
- Yale School of Public Health, New Haven, Connecticut (J.W., A.L., C.D.N.)
| | - Janet Eaton
- Yale School of Public Health, and Tobin Center for Economic Policy, Yale University, New Haven, Connecticut (J.E.)
| | - Chima D Ndumele
- Yale School of Public Health, New Haven, Connecticut (J.W., A.L., C.D.N.)
| |
Collapse
|
5
|
Zink A, Rose S. Identifying undercompensated groups defined by multiple attributes in risk adjustment. BMJ Health Care Inform 2021; 28:bmjhci-2021-100414. [PMID: 34535447 PMCID: PMC8451283 DOI: 10.1136/bmjhci-2021-100414] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/19/2021] [Accepted: 08/25/2021] [Indexed: 11/22/2022] Open
Abstract
Objective To identify undercompensated groups in plan payment risk adjustment that are defined by multiple attributes with a systematic new approach, improving on the arbitrary and inconsistent nature of existing evaluations. Methods Extending the concept of variable importance for single attributes, we construct a measure of ‘group importance’ in the random forests algorithm to identify groups with multiple attributes that are undercompensated by current risk adjustment formulas. Using 2016–2018 IBM MarketScan and 2015–2018 Medicare claims and enrolment data, we evaluate two risk adjustment scenarios: the risk adjustment formula used in the individual health insurance Marketplaces and the risk adjustment formula used in Medicare. Results A number of previously unidentified groups with multiple chronic conditions are undercompensated in the Marketplaces risk adjustment formula, while groups without chronic conditions tend to be overcompensated in the Marketplaces. The magnitude of undercompensation when defining groups with multiple attributes is many times larger than with single attributes. No complex groups were found to be consistently undercompensated or overcompensated in the Medicare risk adjustment formula. Conclusions Our method is effective at identifying complex undercompensated groups in health plan payment risk adjustment where undercompensation creates incentives for insurers to discriminate against these groups. This work provides policy-makers with new information on potential targets of discrimination in the healthcare system and a path towards more equitable health coverage.
Collapse
Affiliation(s)
- Anna Zink
- PhD Candidate in Health Policy, Harvard University, Cambridge, Massachusetts, USA
| | - Sherri Rose
- Center for Health Policy and Center for Primary Care & Outcomes Research, Stanford University, Stanford, California, USA
| |
Collapse
|
6
|
Wang Z, Chen X, Tan X, Yang L, Kannapur K, Vincent JL, Kessler GN, Ru B, Yang M. Using Deep Learning to Identify High-Risk Patients with Heart Failure with Reduced Ejection Fraction. JOURNAL OF HEALTH ECONOMICS AND OUTCOMES RESEARCH 2021; 8:6-13. [PMID: 34414250 PMCID: PMC8322198 DOI: 10.36469/jheor.2021.25753] [Citation(s) in RCA: 10] [Impact Index Per Article: 3.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 06/17/2021] [Accepted: 07/15/2021] [Indexed: 06/13/2023]
Abstract
Background: Deep Learning (DL) has not been well-established as a method to identify high-risk patients among patients with heart failure (HF). Objectives: This study aimed to use DL models to predict hospitalizations, worsening HF events, and 30-day and 90-day readmissions in patients with heart failure with reduced ejection fraction (HFrEF). Methods: We analyzed the data of adult HFrEF patients from the IBM® MarketScan® Commercial and Medicare Supplement databases between January 1, 2015 and December 31, 2017. A sequential model architecture based on bi-directional long short-term memory (Bi-LSTM) layers was utilized. For DL models to predict HF hospitalizations and worsening HF events, we utilized two study designs: with and without a buffer window. For comparison, we also tested multiple traditional machine learning models including logistic regression, random forest, and eXtreme Gradient Boosting (XGBoost). Model performance was assessed by area under the curve (AUC) values, precision, and recall on an independent testing dataset. Results: A total of 47 498 HFrEF patients were included; 9427 with at least one HF hospitalization. The best AUCs of DL models without a buffer window in predicting HF hospitalizations and worsening HF events in the total patient cohort were 0.977 and 0.972; with a 7-day buffer window the best AUCs were 0.573 and 0.608, respectively. The best AUCs in predicting 30- and 90-day readmissions in all adult patients were 0.597 and 0.614, respectively. An AUC of 0.861 was attained for prediction of 90-day readmission in patients aged 18-64. For all outcomes assessed, the DL approach outperformed traditional machine learning models. Discussion: The DL approach can automate feature engineering during the model learning, which can increase the clinical applicability and lead to comparable or better model performance. However, the lack of granular clinical data, and sample size and imbalance issues may have limited the model's performance. Conclusions: A DL approach using Bi-LSTM was shown to be a feasible and useful tool to predict HF-related outcomes. This study can help inform the future development and deployment of predictive tools to identify high-risk HFrEF patients and ultimately facilitate targeted interventions in clinical practice.
Collapse
Affiliation(s)
- Zhibo Wang
- Merck & Co., Inc., Kenilworth, NJ, USA; College of Engineering and Computer Science, University of Central Florida, Orlando, FL, USA
| | - Xin Chen
- Merck & Co., Inc., Kenilworth, NJ, USA
| | - Xi Tan
- Merck & Co., Inc., Kenilworth, NJ, USA
| | | | | | | | - Garin N Kessler
- Amazon Web Services Inc., Seattle, WA, USA; Georgetown University, Seattle, WA, USA
| | - Boshu Ru
- Merck & Co., Inc., Kenilworth, NJ, USA
| | - Mei Yang
- Merck & Co., Inc., Kenilworth, NJ, USA
| |
Collapse
|
7
|
Rose S. Intersections of machine learning and epidemiological methods for health services research. Int J Epidemiol 2021; 49:1763-1770. [PMID: 32236476 PMCID: PMC7825941 DOI: 10.1093/ije/dyaa035] [Citation(s) in RCA: 11] [Impact Index Per Article: 3.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 02/17/2020] [Indexed: 12/15/2022] Open
Abstract
The field of health services research is broad and seeks to answer questions about the health care system. It is inherently interdisciplinary, and epidemiologists have made crucial contributions. Parametric regression techniques remain standard practice in health services research with machine learning techniques currently having low penetrance in comparison. However, studies in several prominent areas, including health care spending, outcomes and quality, have begun deploying machine learning tools for these applications. Nevertheless, major advances in epidemiological methods are also as yet underleveraged in health services research. This article summarizes the current state of machine learning in key areas of health services research, and discusses important future directions at the intersection of machine learning and epidemiological methods for health services research.
Collapse
Affiliation(s)
- Sherri Rose
- Department of Health Care Policy, Harvard Medical School, 180 Longwood Ave, Boston, MA, 02115, USA
| |
Collapse
|
8
|
Abstract
OBJECTIVE To demonstrate the performance of methodologies that include machine learning (ML) algorithms to estimate average treatment effects under the assumption of exogeneity (selection on observables). DATA SOURCES Simulated data and observational data on hospitalized adults. STUDY DESIGN We assessed the performance of several ML-based estimators, including Targeted Maximum Likelihood Estimation, Bayesian Additive Regression Trees, Causal Random Forests, Double Machine Learning, and Bayesian Causal Forests, applying these methods to simulated data as well as data on the effects of right heart catheterization. PRINCIPAL FINDINGS In Monte Carlo studies, ML-based estimators generated estimates with smaller bias than traditional regression approaches, demonstrating substantial (69 percent-98 percent) bias reduction in some scenarios. Bayesian Causal Forests and Double Machine Learning were top performers, although all were sensitive to high dimensional (>150) sets of covariates. CONCLUSIONS ML-based methods are promising methods for estimating treatment effects, allowing for the inclusion of many covariates and automating the search for nonlinearities and interactions among variables. We provide guidance and sample code for researchers interested in implementing these tools in their own empirical work.
Collapse
Affiliation(s)
- K John McConnell
- Center for Health Systems Effectiveness, Oregon Health & Science University, Portland, Oregon
| | - Stephan Lindner
- Center for Health Systems Effectiveness, Oregon Health & Science University, Portland, Oregon
| |
Collapse
|
9
|
Huber M, Kurz C, Leidl R. Predicting patient-reported outcomes following hip and knee replacement surgery using supervised machine learning. BMC Med Inform Decis Mak 2019; 19:3. [PMID: 30621670 PMCID: PMC6325823 DOI: 10.1186/s12911-018-0731-6] [Citation(s) in RCA: 60] [Impact Index Per Article: 12.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/27/2018] [Accepted: 12/27/2018] [Indexed: 12/28/2022] Open
Abstract
BACKGROUND Machine-learning classifiers mostly offer good predictive performance and are increasingly used to support shared decision-making in clinical practice. Focusing on performance and practicability, this study evaluates prediction of patient-reported outcomes (PROs) by eight supervised classifiers including a linear model, following hip and knee replacement surgery. METHODS NHS PRO data (130,945 observations) from April 2015 to April 2017 were used to train and test eight classifiers to predict binary postoperative improvement based on minimal important differences. Area under the receiver operating characteristic, J-statistic and several other metrics were calculated. The dependent outcomes were generic and disease-specific improvement based on the EQ-5D-3L visual analogue scale (VAS) as well as the Oxford Hip and Knee Score (Q score). RESULTS The area under the receiver operating characteristic of the best training models was around 0.87 (VAS) and 0.78 (Q score) for hip replacement, while it was around 0.86 (VAS) and 0.70 (Q score) for knee replacement surgery. Extreme gradient boosting, random forests, multistep elastic net and linear model provided the highest overall J-statistics. Based on variable importance, the most important predictors for post-operative outcomes were preoperative VAS, Q score and single Q score dimensions. Sensitivity analysis for hip replacement VAS evaluated the influence of minimal important difference, patient selection criteria as well as additional data years. Together with a small benchmark of the NHS prediction model, robustness of our results was confirmed. CONCLUSIONS Supervised machine-learning implementations, like extreme gradient boosting, can provide better performance than linear models and should be considered, when high predictive performance is needed. Preoperative VAS, Q score and specific dimensions like limping are the most important predictors for postoperative hip and knee PROMs.
Collapse
Affiliation(s)
- Manuel Huber
- German Research Center for Environmental Health, Institute for Health Economics and Health Care Management, Helmholtz Zentrum München, Postfach 1129, 85758 Neuherberg, Germany
| | - Christoph Kurz
- German Research Center for Environmental Health, Institute for Health Economics and Health Care Management, Helmholtz Zentrum München, Postfach 1129, 85758 Neuherberg, Germany
| | - Reiner Leidl
- German Research Center for Environmental Health, Institute for Health Economics and Health Care Management, Helmholtz Zentrum München, Postfach 1129, 85758 Neuherberg, Germany
- Munich Center of Health Sciences, Ludwig-Maximilians-University, Ludwigstr. 28, 80539 Munich, RG Germany
| |
Collapse
|