Integration of elicited expert information via a power prior in Bayesian variable selection: Application to colon cancer data

Abstract

Background Building tools to support personalized medicine needs to model medical decision-making. For this purpose, both expert and real world data provide a rich source of information. Currently, machine learning techniques are developing to select relevant variables for decision-making. Rather than using data-driven analysis alone, eliciting prior information from physicians related to their medical decision-making processes can be useful in variable selection. Our framework is electronic health records data on repeated dose adjustment of Irinotecan for the treatment of metastatic colorectal cancer. We propose a method that incorporates elicited expert weights associated with variables involved in dose reduction decisions into the Stochastic Search Variable Selection (SSVS), a Bayesian variable selection method, by using a power prior. Methods Clinician experts were first asked to provide numerical clinical relevance weights to express their beliefs about the importance of each variable in their medical decision making. Then, we modeled the link between repeated dose reduction, patient characteristics, and toxicities by assuming a logistic mixed-effects model. Simulated data were generated based on the elicited weights and combined with the observed dose reduction data via a power prior. We compared the Bayesian power prior-based SSVS performance to the usual SSVS in our case study, including a sensitivity analysis using the power prior parameter. Results The selected variables differ when using only expert knowledge, only the usual SSVS, or combining both. Our method enables one to select rare variables that may be missed using only the observed data and to discard variables that appear to be relevant based on the data but not relevant from the expert perspective. Conclusion We introduce an innovative Bayesian variable selection method that adaptively combines elicited expert information and real world data. The method selects a set of variables relevant to model medical decision process.

Research and Application of Artificial Intelligence Based on Electronic Health Records of Patients With Cancer: Systematic Review

“…Of the 148 studies, 21 (14.2%) used AI to adapt doses in antidrug regimen [ 35 ], assess effect and combination of dose, evaluate cancer therapeutic procedures, and recommend treatment schemes based on EHRs. The precision, recall, specificity, F-score, accuracy, and AUC were above 0.67, except in a model for drug repurposing reported by Wu et al [ 36 ].…”

Prior elicitation for Gaussian spatial process: An application to TMS brain mapping

“…Higher number of spatial knots placed strategically or equidistantly over  improves the performance of the model. Hence, (9) becomes…”

“…It is a clever way to borrow information about a parameter from a previous study to a current study in situations where historical data are available. It is a useful statistical tool in clinical research, [6][7][8] public health studies, 9,10 epidemiological studies, 11 and quality control. 12 The incorporation of historical data into a current study can be helpful in results interpretation.…”

Expert elicitation of risk factors for progression to dementia in individuals with mild cognitive impairment

“…A number of guidelines on developing risk prediction tools 1,10–12 have recommended using clinical expert knowledge to guide the selection of predictors. If done informally, there is a concern that this might reinforce expert cognitive biases without fully capturing their uncertainties, which would result in biased risk scores, limited generalizability, and highly variable practice 13,14 . Expert judgment (belief or intuition) is often a combination of fact‐based knowledge and subjective interpretation.…”