Towards Automating Adverse Event Review: A Prediction Model for Case Report Utility. Mu?oz, M. A., Dal Pan, G. J., Wei, Y. J., Delcher, C., Xiao, H., Kortepeter, C. M., & Winterstein, A. G. Drug Saf, Jan, 2020. ![Towards Automating Adverse Event Review: A Prediction Model for Case Report Utility [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper abstract bibtex The rapidly expanding size of the Food and Drug Administration's (FDA) Adverse Event Reporting System database requires modernized pharmacovigilance practices. Techniques to systematically identify high utility individual case safety reports (ICSRs) will support safety signal management.\\ The aim of this study was to develop and validate a model predictive of an ICSR's pharmacovigilance utility (PVU).\\ PVU was operationalized as an ICSR's inclusion in an FDA-authored pharmacovigilance review's case series supporting a recommendation to modify product labeling. Multivariable logistic regression models were used to examine the association between PVU and ICSR features. The best performing model was selected for bootstrapping validation. As a sensitivity analysis, we evaluated the model's performance across subgroups of safety issues.\\ We identified 10,381 ICSRs evaluated in 69 pharmacovigilance reviews, of which 2115 ICSRs were included in a case series. The strongest predictors of ICSR inclusion were reporting of a designated medical event (odds ratio (OR) 1.93, 95% CI 1.54-2.43) and positive dechallenge (OR 1.67, 95% CI 1.50-1.87). The strongest predictors of ICSR exclusion were death reported as the only outcome (OR 2.72, 95% CI 1.76-4.35), more than three suspect products (OR 2.69, 95% CI 2.23-3.24), and > 15 preferred terms reported (OR 2.69, 95% CI 1.90-3.82). The validated model showed modest discriminative ability (C-statistic of 0.71). Our sensitivity analysis demonstrated heterogeneity in model performance by safety issue (C-statistic range 0.58-0.74).\\ Our model demonstrated the feasibility of developing a tool predictive of ICSR utility. The model's modest discriminative ability highlights opportunities for further enhancement and suggests algorithms tailored to safety issues may be beneficial.
@Article{pmid31912439,
Author="Mu?oz, M. A. and Dal Pan, G. J. and Wei, Y. J. and Delcher, C. and Xiao, H. and Kortepeter, C. M. and Winterstein, A. G. ",
Title="{{T}owards {A}utomating {A}dverse {E}vent {R}eview: {A} {P}rediction {M}odel for {C}ase {R}eport {U}tility}",
Journal="Drug Saf",
Year="2020",
Month="Jan",
Abstract={The rapidly expanding size of the Food and Drug Administration's (FDA) Adverse Event Reporting System database requires modernized pharmacovigilance practices. Techniques to systematically identify high utility individual case safety reports (ICSRs) will support safety signal management.\\ The aim of this study was to develop and validate a model predictive of an ICSR's pharmacovigilance utility (PVU).\\ PVU was operationalized as an ICSR's inclusion in an FDA-authored pharmacovigilance review's case series supporting a recommendation to modify product labeling. Multivariable logistic regression models were used to examine the association between PVU and ICSR features. The best performing model was selected for bootstrapping validation. As a sensitivity analysis, we evaluated the model's performance across subgroups of safety issues.\\ We identified 10,381 ICSRs evaluated in 69 pharmacovigilance reviews, of which 2115 ICSRs were included in a case series. The strongest predictors of ICSR inclusion were reporting of a designated medical event (odds ratio (OR) 1.93, 95% CI 1.54-2.43) and positive dechallenge (OR 1.67, 95% CI 1.50-1.87). The strongest predictors of ICSR exclusion were death reported as the only outcome (OR 2.72, 95% CI 1.76-4.35), more than three suspect products (OR 2.69, 95% CI 2.23-3.24), and > 15 preferred terms reported (OR 2.69, 95% CI 1.90-3.82). The validated model showed modest discriminative ability (C-statistic of 0.71). Our sensitivity analysis demonstrated heterogeneity in model performance by safety issue (C-statistic range 0.58-0.74).\\ Our model demonstrated the feasibility of developing a tool predictive of ICSR utility. The model's modest discriminative ability highlights opportunities for further enhancement and suggests algorithms tailored to safety issues may be beneficial.},
url = {https://dx.doi.org/10.1007/s40264-019-00897-0}
}
% 31895146
Downloads: 0
{"_id":"Z6uA9oA9RnAE2vq7s","bibbaseid":"muoz-dalpan-wei-delcher-xiao-kortepeter-winterstein-towardsautomatingadverseeventreviewapredictionmodelforcasereportutility-2020","authorIDs":["cx2mkWAD5ZBDRQ5ka","dYxKbtLjik6YzH6Xm","h4nnb2ba9jm4CdAXJ","zdRntZz94XRzgtbbz"],"author_short":["Mu?oz, M. A.","Dal Pan, G. J.","Wei, Y. J.","Delcher, C.","Xiao, H.","Kortepeter, C. M.","Winterstein, A. G."],"bibdata":{"bibtype":"article","type":"article","author":[{"propositions":[],"lastnames":["Mu?oz"],"firstnames":["M.","A."],"suffixes":[]},{"propositions":[],"lastnames":["Dal","Pan"],"firstnames":["G.","J."],"suffixes":[]},{"propositions":[],"lastnames":["Wei"],"firstnames":["Y.","J."],"suffixes":[]},{"propositions":[],"lastnames":["Delcher"],"firstnames":["C."],"suffixes":[]},{"propositions":[],"lastnames":["Xiao"],"firstnames":["H."],"suffixes":[]},{"propositions":[],"lastnames":["Kortepeter"],"firstnames":["C.","M."],"suffixes":[]},{"propositions":[],"lastnames":["Winterstein"],"firstnames":["A.","G."],"suffixes":[]}],"title":"Towards Automating Adverse Event Review: A Prediction Model for Case Report Utility","journal":"Drug Saf","year":"2020","month":"Jan","abstract":"The rapidly expanding size of the Food and Drug Administration's (FDA) Adverse Event Reporting System database requires modernized pharmacovigilance practices. Techniques to systematically identify high utility individual case safety reports (ICSRs) will support safety signal management.\\\\ The aim of this study was to develop and validate a model predictive of an ICSR's pharmacovigilance utility (PVU).\\\\ PVU was operationalized as an ICSR's inclusion in an FDA-authored pharmacovigilance review's case series supporting a recommendation to modify product labeling. Multivariable logistic regression models were used to examine the association between PVU and ICSR features. The best performing model was selected for bootstrapping validation. As a sensitivity analysis, we evaluated the model's performance across subgroups of safety issues.\\\\ We identified 10,381 ICSRs evaluated in 69 pharmacovigilance reviews, of which 2115 ICSRs were included in a case series. The strongest predictors of ICSR inclusion were reporting of a designated medical event (odds ratio (OR) 1.93, 95% CI 1.54-2.43) and positive dechallenge (OR 1.67, 95% CI 1.50-1.87). The strongest predictors of ICSR exclusion were death reported as the only outcome (OR 2.72, 95% CI 1.76-4.35), more than three suspect products (OR 2.69, 95% CI 2.23-3.24), and > 15 preferred terms reported (OR 2.69, 95% CI 1.90-3.82). The validated model showed modest discriminative ability (C-statistic of 0.71). Our sensitivity analysis demonstrated heterogeneity in model performance by safety issue (C-statistic range 0.58-0.74).\\\\ Our model demonstrated the feasibility of developing a tool predictive of ICSR utility. The model's modest discriminative ability highlights opportunities for further enhancement and suggests algorithms tailored to safety issues may be beneficial.","url":"https://dx.doi.org/10.1007/s40264-019-00897-0","bibtex":"@Article{pmid31912439,\n Author=\"Mu?oz, M. A. and Dal Pan, G. J. and Wei, Y. J. and Delcher, C. and Xiao, H. and Kortepeter, C. M. and Winterstein, A. G. \",\n Title=\"{{T}owards {A}utomating {A}dverse {E}vent {R}eview: {A} {P}rediction {M}odel for {C}ase {R}eport {U}tility}\",\n Journal=\"Drug Saf\",\n Year=\"2020\",\n Month=\"Jan\",\n Abstract={The rapidly expanding size of the Food and Drug Administration's (FDA) Adverse Event Reporting System database requires modernized pharmacovigilance practices. Techniques to systematically identify high utility individual case safety reports (ICSRs) will support safety signal management.\\\\ The aim of this study was to develop and validate a model predictive of an ICSR's pharmacovigilance utility (PVU).\\\\ PVU was operationalized as an ICSR's inclusion in an FDA-authored pharmacovigilance review's case series supporting a recommendation to modify product labeling. Multivariable logistic regression models were used to examine the association between PVU and ICSR features. The best performing model was selected for bootstrapping validation. As a sensitivity analysis, we evaluated the model's performance across subgroups of safety issues.\\\\ We identified 10,381 ICSRs evaluated in 69 pharmacovigilance reviews, of which 2115 ICSRs were included in a case series. The strongest predictors of ICSR inclusion were reporting of a designated medical event (odds ratio (OR) 1.93, 95% CI 1.54-2.43) and positive dechallenge (OR 1.67, 95% CI 1.50-1.87). The strongest predictors of ICSR exclusion were death reported as the only outcome (OR 2.72, 95% CI 1.76-4.35), more than three suspect products (OR 2.69, 95% CI 2.23-3.24), and > 15 preferred terms reported (OR 2.69, 95% CI 1.90-3.82). The validated model showed modest discriminative ability (C-statistic of 0.71). Our sensitivity analysis demonstrated heterogeneity in model performance by safety issue (C-statistic range 0.58-0.74).\\\\ Our model demonstrated the feasibility of developing a tool predictive of ICSR utility. The model's modest discriminative ability highlights opportunities for further enhancement and suggests algorithms tailored to safety issues may be beneficial.},\nurl = {https://dx.doi.org/10.1007/s40264-019-00897-0}\n}\n\n% 31895146 \n","author_short":["Mu?oz, M. A.","Dal Pan, G. J.","Wei, Y. J.","Delcher, C.","Xiao, H.","Kortepeter, C. M.","Winterstein, A. G."],"key":"pmid31912439","id":"pmid31912439","bibbaseid":"muoz-dalpan-wei-delcher-xiao-kortepeter-winterstein-towardsautomatingadverseeventreviewapredictionmodelforcasereportutility-2020","role":"author","urls":{"Paper":"https://dx.doi.org/10.1007/s40264-019-00897-0"},"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://raw.githubusercontent.com/rockey63/rockey63/master/bibbbbbb","creationDate":"2020-03-26T19:48:04.601Z","downloads":0,"keywords":[],"search_terms":["towards","automating","adverse","event","review","prediction","model","case","report","utility","mu?oz","dal pan","wei","delcher","xiao","kortepeter","winterstein"],"title":"Towards Automating Adverse Event Review: A Prediction Model for Case Report Utility","year":2020,"dataSources":["mqd8D39v323i3exJ2"]}