Multimorbidity analysis with low condition counts: a robust Bayesian approach for small but important subgroupsResearch in context
Summary: Background: Robustly examining associations between long-term conditions may be important in identifying opportunities for intervention in multimorbidity but is challenging when evidence is limited. We have developed a Bayesian inference framework that is robust to sparse data and used it...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-04-01
|
| Series: | EBioMedicine |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2352396424001166 |
| _version_ | 1797214917302943744 |
|---|---|
| author | Guillermo Romero Moreno Valerio Restocchi Jacques D. Fleuriot Atul Anand Stewart W. Mercer Bruce Guthrie |
| author_facet | Guillermo Romero Moreno Valerio Restocchi Jacques D. Fleuriot Atul Anand Stewart W. Mercer Bruce Guthrie |
| author_sort | Guillermo Romero Moreno |
| collection | DOAJ |
| description | Summary: Background: Robustly examining associations between long-term conditions may be important in identifying opportunities for intervention in multimorbidity but is challenging when evidence is limited. We have developed a Bayesian inference framework that is robust to sparse data and used it to quantify morbidity associations in the oldest old, a population with limited available data. Methods: We conducted a retrospective cross-sectional study of a representative dataset of primary care patients in Scotland as of March 2007. We included 40 long-term conditions and studied their associations in 12,009 individuals aged 90 and older, stratified by sex (3039 men, 8970 women). We analysed associations obtained with Relative Risk (RR), a standard measure in the literature, and compared them with our proposed measure, Associations Beyond Chance (ABC). To enable a broad exploration of interactions between long-term conditions, we built networks of association and assessed differences in their analysis when associations are estimated by RR or ABC. Findings: Our Bayesian framework was appropriately more cautious in attributing association when evidence is lacking, particularly in uncommon conditions. This caution in reporting association was also present in reporting differences in associations between sex and affected the aggregated measures of multimorbidity and network representations. Interpretation: Incorporating uncertainty into multimorbidity research is crucial to avoid misleading findings when evidence is limited, a problem that particularly affects small but important subgroups. Our proposed framework improves the reliability of estimations of associations and, more in general, of research into disease mechanisms and multimorbidity. Funding: National Institute for Health and Care Research. |
| first_indexed | 2024-04-24T11:21:47Z |
| format | Article |
| id | doaj.art-bb9a458872ea46a4b644651c0ccef244 |
| institution | Directory Open Access Journal |
| issn | 2352-3964 |
| language | English |
| last_indexed | 2024-04-24T11:21:47Z |
| publishDate | 2024-04-01 |
| publisher | Elsevier |
| record_format | Article |
| series | EBioMedicine |
| spelling | doaj.art-bb9a458872ea46a4b644651c0ccef2442024-04-11T04:41:30ZengElsevierEBioMedicine2352-39642024-04-01102105081Multimorbidity analysis with low condition counts: a robust Bayesian approach for small but important subgroupsResearch in contextGuillermo Romero Moreno0Valerio Restocchi1Jacques D. Fleuriot2Atul Anand3Stewart W. Mercer4Bruce Guthrie5School of Informatics, University of Edinburgh, Edinburgh, UK; Corresponding author. School of Informatics, University of Edinburgh, 10 Crichton St, Edinburgh, EH8 9AB, UK.School of Informatics, University of Edinburgh, Edinburgh, UKSchool of Informatics, University of Edinburgh, Edinburgh, UKCentre for Cardiovascular Science, University of Edinburgh, Edinburgh, UKUsher Institute of Population Health Sciences and Informatics, University of Edinburgh, Edinburgh, UKUsher Institute of Population Health Sciences and Informatics, University of Edinburgh, Edinburgh, UKSummary: Background: Robustly examining associations between long-term conditions may be important in identifying opportunities for intervention in multimorbidity but is challenging when evidence is limited. We have developed a Bayesian inference framework that is robust to sparse data and used it to quantify morbidity associations in the oldest old, a population with limited available data. Methods: We conducted a retrospective cross-sectional study of a representative dataset of primary care patients in Scotland as of March 2007. We included 40 long-term conditions and studied their associations in 12,009 individuals aged 90 and older, stratified by sex (3039 men, 8970 women). We analysed associations obtained with Relative Risk (RR), a standard measure in the literature, and compared them with our proposed measure, Associations Beyond Chance (ABC). To enable a broad exploration of interactions between long-term conditions, we built networks of association and assessed differences in their analysis when associations are estimated by RR or ABC. Findings: Our Bayesian framework was appropriately more cautious in attributing association when evidence is lacking, particularly in uncommon conditions. This caution in reporting association was also present in reporting differences in associations between sex and affected the aggregated measures of multimorbidity and network representations. Interpretation: Incorporating uncertainty into multimorbidity research is crucial to avoid misleading findings when evidence is limited, a problem that particularly affects small but important subgroups. Our proposed framework improves the reliability of estimations of associations and, more in general, of research into disease mechanisms and multimorbidity. Funding: National Institute for Health and Care Research.http://www.sciencedirect.com/science/article/pii/S2352396424001166MultimorbidityAssociation measuresNetwork analysisRelative riskBayesian inferenceLow counts |
| spellingShingle | Guillermo Romero Moreno Valerio Restocchi Jacques D. Fleuriot Atul Anand Stewart W. Mercer Bruce Guthrie Multimorbidity analysis with low condition counts: a robust Bayesian approach for small but important subgroupsResearch in context EBioMedicine Multimorbidity Association measures Network analysis Relative risk Bayesian inference Low counts |
| title | Multimorbidity analysis with low condition counts: a robust Bayesian approach for small but important subgroupsResearch in context |
| title_full | Multimorbidity analysis with low condition counts: a robust Bayesian approach for small but important subgroupsResearch in context |
| title_fullStr | Multimorbidity analysis with low condition counts: a robust Bayesian approach for small but important subgroupsResearch in context |
| title_full_unstemmed | Multimorbidity analysis with low condition counts: a robust Bayesian approach for small but important subgroupsResearch in context |
| title_short | Multimorbidity analysis with low condition counts: a robust Bayesian approach for small but important subgroupsResearch in context |
| title_sort | multimorbidity analysis with low condition counts a robust bayesian approach for small but important subgroupsresearch in context |
| topic | Multimorbidity Association measures Network analysis Relative risk Bayesian inference Low counts |
| url | http://www.sciencedirect.com/science/article/pii/S2352396424001166 |
| work_keys_str_mv | AT guillermoromeromoreno multimorbidityanalysiswithlowconditioncountsarobustbayesianapproachforsmallbutimportantsubgroupsresearchincontext AT valeriorestocchi multimorbidityanalysiswithlowconditioncountsarobustbayesianapproachforsmallbutimportantsubgroupsresearchincontext AT jacquesdfleuriot multimorbidityanalysiswithlowconditioncountsarobustbayesianapproachforsmallbutimportantsubgroupsresearchincontext AT atulanand multimorbidityanalysiswithlowconditioncountsarobustbayesianapproachforsmallbutimportantsubgroupsresearchincontext AT stewartwmercer multimorbidityanalysiswithlowconditioncountsarobustbayesianapproachforsmallbutimportantsubgroupsresearchincontext AT bruceguthrie multimorbidityanalysiswithlowconditioncountsarobustbayesianapproachforsmallbutimportantsubgroupsresearchincontext |