Machine Learning Detects Heterogeneous Effects of Medicaid Coverage on Depression
© The Author(s) 2024. Published by Oxford University Press on behalf of the Johns Hopkins Bloomberg School of Public Health. All rights reserved. For permissions, please e-mail: journals.permissionsoup.com..
In 2008, Oregon expanded its Medicaid program using a lottery, creating a rare opportunity to study the effects of Medicaid coverage using a randomized controlled design (Oregon Health Insurance Experiment). Analysis showed that Medicaid coverage lowered the risk of depression. However, this effect may vary between individuals, and the identification of individuals likely to benefit the most has the potential to improve the effectiveness and efficiency of the Medicaid program. By applying the machine learning causal forest to data from this experiment, we found substantial heterogeneity in the effect of Medicaid coverage on depression; individuals with high predicted benefit were older and had more physical or mental health conditions at baseline. Expanding coverage to individuals with high predicted benefit generated greater reduction in depression prevalence than expanding to all eligible individuals (21.5 vs. 8.8 percentage point reduction; adjusted difference [95%CI], +12.7 [+4.6,+20.8]; P=0.003), at substantially lower cost per case prevented ($16,627 vs. $36,048; adjusted difference [95%CI], -$18,598 [-$156,953,-$3,120]; P=0.04). Medicaid coverage reduces depression substantially more in a subset of the population than others, in ways that are predictable in advance. Targeting coverage on those most likely to benefit could improve the effectiveness and efficiency of insurance expansion.
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2024 |
---|---|
Erschienen: |
2024 |
Enthalten in: |
Zur Gesamtaufnahme - year:2024 |
---|---|
Enthalten in: |
American journal of epidemiology - (2024) vom: 22. Feb. |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Goto, Ryunosuke [VerfasserIn] |
---|
Links: |
---|
Anmerkungen: |
Date Revised 24.02.2024 published: Print-Electronic Citation Status Publisher |
---|
doi: |
10.1093/aje/kwae008 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM368906256 |
---|
LEADER | 01000naa a22002652 4500 | ||
---|---|---|---|
001 | NLM368906256 | ||
003 | DE-627 | ||
005 | 20240229151408.0 | ||
007 | cr uuu---uuuuu | ||
008 | 240229s2024 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1093/aje/kwae008 |2 doi | |
028 | 5 | 2 | |a pubmed24n1304.xml |
035 | |a (DE-627)NLM368906256 | ||
035 | |a (NLM)38400644 | ||
035 | |a (PII)kwae008 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Goto, Ryunosuke |e verfasserin |4 aut | |
245 | 1 | 0 | |a Machine Learning Detects Heterogeneous Effects of Medicaid Coverage on Depression |
264 | 1 | |c 2024 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a ƒaComputermedien |b c |2 rdamedia | ||
338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
500 | |a Date Revised 24.02.2024 | ||
500 | |a published: Print-Electronic | ||
500 | |a Citation Status Publisher | ||
520 | |a © The Author(s) 2024. Published by Oxford University Press on behalf of the Johns Hopkins Bloomberg School of Public Health. All rights reserved. For permissions, please e-mail: journals.permissionsoup.com. | ||
520 | |a In 2008, Oregon expanded its Medicaid program using a lottery, creating a rare opportunity to study the effects of Medicaid coverage using a randomized controlled design (Oregon Health Insurance Experiment). Analysis showed that Medicaid coverage lowered the risk of depression. However, this effect may vary between individuals, and the identification of individuals likely to benefit the most has the potential to improve the effectiveness and efficiency of the Medicaid program. By applying the machine learning causal forest to data from this experiment, we found substantial heterogeneity in the effect of Medicaid coverage on depression; individuals with high predicted benefit were older and had more physical or mental health conditions at baseline. Expanding coverage to individuals with high predicted benefit generated greater reduction in depression prevalence than expanding to all eligible individuals (21.5 vs. 8.8 percentage point reduction; adjusted difference [95%CI], +12.7 [+4.6,+20.8]; P=0.003), at substantially lower cost per case prevented ($16,627 vs. $36,048; adjusted difference [95%CI], -$18,598 [-$156,953,-$3,120]; P=0.04). Medicaid coverage reduces depression substantially more in a subset of the population than others, in ways that are predictable in advance. Targeting coverage on those most likely to benefit could improve the effectiveness and efficiency of insurance expansion | ||
650 | 4 | |a Journal Article | |
650 | 4 | |a Medicaid | |
650 | 4 | |a Oregon Health Insurance Experiment | |
650 | 4 | |a causal forest | |
650 | 4 | |a causal inference | |
650 | 4 | |a causal machine learning | |
650 | 4 | |a depression | |
650 | 4 | |a generalized random forest | |
650 | 4 | |a high-benefit approach | |
650 | 4 | |a machine learning | |
650 | 4 | |a mental health | |
650 | 4 | |a psychiatry | |
700 | 1 | |a Inoue, Kosuke |e verfasserin |4 aut | |
700 | 1 | |a Osawa, Itsuki |e verfasserin |4 aut | |
700 | 1 | |a Baicker, Katherine |e verfasserin |4 aut | |
700 | 1 | |a Fleming, Scott L |e verfasserin |4 aut | |
700 | 1 | |a Tsugawa, Yusuke |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t American journal of epidemiology |d 1965 |g (2024) vom: 22. Feb. |w (DE-627)NLM000012327 |x 1476-6256 |7 nnns |
773 | 1 | 8 | |g year:2024 |g day:22 |g month:02 |
856 | 4 | 0 | |u http://dx.doi.org/10.1093/aje/kwae008 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |j 2024 |b 22 |c 02 |