Inverse optimization on hierarchical networks: an application to breast cancer clinical pathways.

Clinical pathways are standardized processes that outline the steps required for managing a specific disease. However, patient pathways often deviate from clinical pathways. Measuring the concordance of patient pathways to clinical pathways is important for health system monitoring and informing quality improvement initiatives. In this paper, we develop an inverse optimization-based approach to measuring pathway concordance in breast cancer, a complex disease. We capture this complexity in a hierarchical network that models the patient's journey through the health system. A novel inverse shortest path model is formulated and solved on this hierarchical network to estimate arc costs, which are used to form a concordance metric to measure the distance between patient pathways and shortest paths (i.e., clinical pathways). Using real breast cancer patient data from Ontario, Canada, we demonstrate that our concordance metric has a statistically significant association with survival for all breast cancer patient subgroups. We also use it to quantify the extent of patient pathway discordances across all subgroups, finding that patients undertaking additional clinical activities constitute the primary driver of discordance in the population.

Forecasting Ontario Oncology Drug Expenditures: A Hybrid Approach to Improving Accuracy.

BACKGROUND: The Provincial Drug Reimbursement Program (PDRP) at Cancer Care Ontario (CCO) is responsible for monitoring actual and projected outpatient intravenous cancer drug spending in the province. We developed a hybrid forecasting approach combining automated time-series forecasting with expert-customizable input. OBJECTIVE: Our objectives were to provide a flexible tool in which to incorporate multiple forecasts and to improve the accuracy of the resulting forecast. METHODS: The approach employed linear and non-linear time-series techniques and a combined hybrid model incorporating both approaches. We developed an interactive tool that incorporated the statistical models and identified the best performing forecast according to standard goodness-of-fit measures. Model selection procedures considered both the amount of historical expenditure data available per drug policy and the individual policy contributions to the overall budget. The user was allowed to customize forecasts based on knowledge of external factors related to policy or price changes and new drugs that come to market RESULTS: A comparison of 2016/17 fiscal year expenditures showed that all policies with a significant contribution to the overall budget were forecast with < 4% error. Forecasting error was reduced by at least $Can5 million for the nine most expensive policies compared with expert opinion. This approach to drug budget forecasting was implemented in Ontario for the first time in the 2017/18 fiscal year, where 1% error was observed for the overall budget, corresponding to an overestimate of expenditures by $Can3.0 million. CONCLUSION: We introduced a pragmatic approach for regular forecasting by budget holders in Ontario. Our approach to isolating 'big budget' from 'small budget' drugs using an 80-20 rule and providing multiple forecasts depending on the length of the drug expenditure histories is transferable to other jurisdictions.