PROVIDENT : Development and Validation of a Machine Learning Model to Predict Neighborhood-level Overdose Risk in Rhode Island
Copyright © 2023 Wolters Kluwer Health, Inc. All rights reserved..
BACKGROUND: Drug overdose persists as a leading cause of death in the United States, but resources to address it remain limited. As a result, health authorities must consider where to allocate scarce resources within their jurisdictions. Machine learning offers a strategy to identify areas with increased future overdose risk to proactively allocate overdose prevention resources. This modeling study is embedded in a randomized trial to measure the effect of proactive resource allocation on statewide overdose rates in Rhode Island (RI).
METHODS: We used statewide data from RI from 2016 to 2020 to develop an ensemble machine learning model predicting neighborhood-level fatal overdose risk. Our ensemble model integrated gradient boosting machine and super learner base models in a moving window framework to make predictions in 6-month intervals. Our performance target, developed a priori with the RI Department of Health, was to identify the 20% of RI neighborhoods containing at least 40% of statewide overdose deaths, including at least one neighborhood per municipality. The model was validated after trial launch.
RESULTS: Our model selected priority neighborhoods capturing 40.2% of statewide overdose deaths during the test periods and 44.1% of statewide overdose deaths during validation periods. Our ensemble outperformed the base models during the test periods and performed comparably to the best-performing base model during the validation periods.
CONCLUSIONS: We demonstrated the capacity for machine learning models to predict neighborhood-level fatal overdose risk to a degree of accuracy suitable for practitioners. Jurisdictions may consider predictive modeling as a tool to guide allocation of scarce resources.
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2024 |
---|---|
Erschienen: |
2024 |
Enthalten in: |
Zur Gesamtaufnahme - volume:35 |
---|---|
Enthalten in: |
Epidemiology (Cambridge, Mass.) - 35(2024), 2 vom: 01. Feb., Seite 232-240 |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Allen, Bennett [VerfasserIn] |
---|
Links: |
---|
Themen: |
---|
Anmerkungen: |
Date Completed 01.02.2024 Date Revised 06.02.2024 published: Print-Electronic Citation Status MEDLINE |
---|
doi: |
10.1097/EDE.0000000000001695 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM366714961 |
---|
LEADER | 01000caa a22002652 4500 | ||
---|---|---|---|
001 | NLM366714961 | ||
003 | DE-627 | ||
005 | 20240206232106.0 | ||
007 | cr uuu---uuuuu | ||
008 | 240108s2024 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1097/EDE.0000000000001695 |2 doi | |
028 | 5 | 2 | |a pubmed24n1282.xml |
035 | |a (DE-627)NLM366714961 | ||
035 | |a (NLM)38180881 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Allen, Bennett |e verfasserin |4 aut | |
245 | 1 | 0 | |a PROVIDENT |b Development and Validation of a Machine Learning Model to Predict Neighborhood-level Overdose Risk in Rhode Island |
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 Completed 01.02.2024 | ||
500 | |a Date Revised 06.02.2024 | ||
500 | |a published: Print-Electronic | ||
500 | |a Citation Status MEDLINE | ||
520 | |a Copyright © 2023 Wolters Kluwer Health, Inc. All rights reserved. | ||
520 | |a BACKGROUND: Drug overdose persists as a leading cause of death in the United States, but resources to address it remain limited. As a result, health authorities must consider where to allocate scarce resources within their jurisdictions. Machine learning offers a strategy to identify areas with increased future overdose risk to proactively allocate overdose prevention resources. This modeling study is embedded in a randomized trial to measure the effect of proactive resource allocation on statewide overdose rates in Rhode Island (RI) | ||
520 | |a METHODS: We used statewide data from RI from 2016 to 2020 to develop an ensemble machine learning model predicting neighborhood-level fatal overdose risk. Our ensemble model integrated gradient boosting machine and super learner base models in a moving window framework to make predictions in 6-month intervals. Our performance target, developed a priori with the RI Department of Health, was to identify the 20% of RI neighborhoods containing at least 40% of statewide overdose deaths, including at least one neighborhood per municipality. The model was validated after trial launch | ||
520 | |a RESULTS: Our model selected priority neighborhoods capturing 40.2% of statewide overdose deaths during the test periods and 44.1% of statewide overdose deaths during validation periods. Our ensemble outperformed the base models during the test periods and performed comparably to the best-performing base model during the validation periods | ||
520 | |a CONCLUSIONS: We demonstrated the capacity for machine learning models to predict neighborhood-level fatal overdose risk to a degree of accuracy suitable for practitioners. Jurisdictions may consider predictive modeling as a tool to guide allocation of scarce resources | ||
650 | 4 | |a Journal Article | |
650 | 7 | |a Analgesics, Opioid |2 NLM | |
700 | 1 | |a Schell, Robert C |e verfasserin |4 aut | |
700 | 1 | |a Jent, Victoria A |e verfasserin |4 aut | |
700 | 1 | |a Krieger, Maxwell |e verfasserin |4 aut | |
700 | 1 | |a Pratty, Claire |e verfasserin |4 aut | |
700 | 1 | |a Hallowell, Benjamin D |e verfasserin |4 aut | |
700 | 1 | |a Goedel, William C |e verfasserin |4 aut | |
700 | 1 | |a Basta, Melissa |e verfasserin |4 aut | |
700 | 1 | |a Yedinak, Jesse L |e verfasserin |4 aut | |
700 | 1 | |a Li, Yu |e verfasserin |4 aut | |
700 | 1 | |a Cartus, Abigail R |e verfasserin |4 aut | |
700 | 1 | |a Marshall, Brandon D L |e verfasserin |4 aut | |
700 | 1 | |a Cerdá, Magdalena |e verfasserin |4 aut | |
700 | 1 | |a Ahern, Jennifer |e verfasserin |4 aut | |
700 | 1 | |a Neill, Daniel B |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t Epidemiology (Cambridge, Mass.) |d 1990 |g 35(2024), 2 vom: 01. Feb., Seite 232-240 |w (DE-627)NLM012782076 |x 1531-5487 |7 nnns |
773 | 1 | 8 | |g volume:35 |g year:2024 |g number:2 |g day:01 |g month:02 |g pages:232-240 |
856 | 4 | 0 | |u http://dx.doi.org/10.1097/EDE.0000000000001695 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 35 |j 2024 |e 2 |b 01 |c 02 |h 232-240 |