Accurate spatiotemporal mapping of drug overdose deaths by machine learning of drug-related web-searches.
Persons who inject drugs (PWID) are at increased risk for overdose death (ODD), infections with HIV, hepatitis B (HBV) and hepatitis C virus (HCV), and noninfectious health conditions. Spatiotemporal identification of PWID communities is essential for developing efficient and cost-effective public h...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2020-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://doi.org/10.1371/journal.pone.0243622 |
| _version_ | 1818726984331558912 |
|---|---|
| author | David S Campo Joseph W Gussler Amanda Sue Pavel Skums Yury Khudyakov |
| author_facet | David S Campo Joseph W Gussler Amanda Sue Pavel Skums Yury Khudyakov |
| author_sort | David S Campo |
| collection | DOAJ |
| description | Persons who inject drugs (PWID) are at increased risk for overdose death (ODD), infections with HIV, hepatitis B (HBV) and hepatitis C virus (HCV), and noninfectious health conditions. Spatiotemporal identification of PWID communities is essential for developing efficient and cost-effective public health interventions for reducing morbidity and mortality associated with injection-drug use (IDU). Reported ODDs are a strong indicator of the extent of IDU in different geographic regions. However, ODD quantification can take time, with delays in ODD reporting occurring due to a range of factors including death investigation and drug testing. This delayed ODD reporting may affect efficient early interventions for infectious diseases. We present a novel model, Dynamic Overdose Vulnerability Estimator (DOVE), for assessment and spatiotemporal mapping of ODDs in different U.S. jurisdictions. Using Google® Web-search volumes (i.e., the fraction of all searches that include certain words), we identified a strong association between the reported ODD rates and drug-related search terms for 2004-2017. A machine learning model (Extremely Random Forest) was developed to produce yearly ODD estimates at state and county levels, as well as monthly estimates at state level. Regarding the total number of ODDs per year, DOVE's error was only 3.52% (Median Absolute Error, MAE) in the United States for 2005-2017. DOVE estimated 66,463 ODDs out of the reported 70,237 (94.48%) during 2017. For that year, the MAE of the individual ODD rates was 4.43%, 7.34%, and 12.75% among yearly estimates for states, yearly estimates for counties, and monthly estimates for states, respectively. These results indicate suitability of the DOVE ODD estimates for dynamic IDU assessment in most states, which may alert for possible increased morbidity and mortality associated with IDU. ODD estimates produced by DOVE offer an opportunity for a spatiotemporal ODD mapping. Timely identification of potential mortality trends among PWID might assist in developing efficient ODD prevention and HBV, HCV, and HIV infection elimination programs by targeting public health interventions to the most vulnerable PWID communities. |
| first_indexed | 2024-12-17T22:06:53Z |
| format | Article |
| id | doaj.art-794a957672af4d8abe1da9182da72c7b |
| institution | Directory Open Access Journal |
| issn | 1932-6203 |
| language | English |
| last_indexed | 2024-12-17T22:06:53Z |
| publishDate | 2020-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj.art-794a957672af4d8abe1da9182da72c7b2022-12-21T21:30:50ZengPublic Library of Science (PLoS)PLoS ONE1932-62032020-01-011512e024362210.1371/journal.pone.0243622Accurate spatiotemporal mapping of drug overdose deaths by machine learning of drug-related web-searches.David S CampoJoseph W GusslerAmanda SuePavel SkumsYury KhudyakovPersons who inject drugs (PWID) are at increased risk for overdose death (ODD), infections with HIV, hepatitis B (HBV) and hepatitis C virus (HCV), and noninfectious health conditions. Spatiotemporal identification of PWID communities is essential for developing efficient and cost-effective public health interventions for reducing morbidity and mortality associated with injection-drug use (IDU). Reported ODDs are a strong indicator of the extent of IDU in different geographic regions. However, ODD quantification can take time, with delays in ODD reporting occurring due to a range of factors including death investigation and drug testing. This delayed ODD reporting may affect efficient early interventions for infectious diseases. We present a novel model, Dynamic Overdose Vulnerability Estimator (DOVE), for assessment and spatiotemporal mapping of ODDs in different U.S. jurisdictions. Using Google® Web-search volumes (i.e., the fraction of all searches that include certain words), we identified a strong association between the reported ODD rates and drug-related search terms for 2004-2017. A machine learning model (Extremely Random Forest) was developed to produce yearly ODD estimates at state and county levels, as well as monthly estimates at state level. Regarding the total number of ODDs per year, DOVE's error was only 3.52% (Median Absolute Error, MAE) in the United States for 2005-2017. DOVE estimated 66,463 ODDs out of the reported 70,237 (94.48%) during 2017. For that year, the MAE of the individual ODD rates was 4.43%, 7.34%, and 12.75% among yearly estimates for states, yearly estimates for counties, and monthly estimates for states, respectively. These results indicate suitability of the DOVE ODD estimates for dynamic IDU assessment in most states, which may alert for possible increased morbidity and mortality associated with IDU. ODD estimates produced by DOVE offer an opportunity for a spatiotemporal ODD mapping. Timely identification of potential mortality trends among PWID might assist in developing efficient ODD prevention and HBV, HCV, and HIV infection elimination programs by targeting public health interventions to the most vulnerable PWID communities.https://doi.org/10.1371/journal.pone.0243622 |
| spellingShingle | David S Campo Joseph W Gussler Amanda Sue Pavel Skums Yury Khudyakov Accurate spatiotemporal mapping of drug overdose deaths by machine learning of drug-related web-searches. PLoS ONE |
| title | Accurate spatiotemporal mapping of drug overdose deaths by machine learning of drug-related web-searches. |
| title_full | Accurate spatiotemporal mapping of drug overdose deaths by machine learning of drug-related web-searches. |
| title_fullStr | Accurate spatiotemporal mapping of drug overdose deaths by machine learning of drug-related web-searches. |
| title_full_unstemmed | Accurate spatiotemporal mapping of drug overdose deaths by machine learning of drug-related web-searches. |
| title_short | Accurate spatiotemporal mapping of drug overdose deaths by machine learning of drug-related web-searches. |
| title_sort | accurate spatiotemporal mapping of drug overdose deaths by machine learning of drug related web searches |
| url | https://doi.org/10.1371/journal.pone.0243622 |
| work_keys_str_mv | AT davidscampo accuratespatiotemporalmappingofdrugoverdosedeathsbymachinelearningofdrugrelatedwebsearches AT josephwgussler accuratespatiotemporalmappingofdrugoverdosedeathsbymachinelearningofdrugrelatedwebsearches AT amandasue accuratespatiotemporalmappingofdrugoverdosedeathsbymachinelearningofdrugrelatedwebsearches AT pavelskums accuratespatiotemporalmappingofdrugoverdosedeathsbymachinelearningofdrugrelatedwebsearches AT yurykhudyakov accuratespatiotemporalmappingofdrugoverdosedeathsbymachinelearningofdrugrelatedwebsearches |