Health Care Management Science最新文献

Patient Activation Measure (PAM) measures the activation level of patients with chronic conditions and correlates well with patient adherence behavior, health outcomes, and healthcare costs. PAM is increasingly used in practice to identify patients needing more support from the care team. We define PAM levels 1 and 2 as low PAM and investigate the performance of eight machine learning methods (Logistic Regression, Lasso Regression, Ridge Regression, Random Forest, Gradient Boosted Trees, Support Vector Machines, Decision Trees, Neural Networks) to classify patients. Primary data collected from adult patients (n=431) with Diabetes Mellitus (DM) or Hypertension (HT) attending Family Health Centers in Istanbul, Turkey, is used to test the methods. [Formula: see text] of patients in the dataset have a low PAM level. Classification performance with several feature sets was analyzed to understand the relative importance of different types of information and provide insights. The most important features are found as whether the patient performs self-monitoring, smoking and exercise habits, education, and socio-economic status. The best performance was achieved with the Logistic Regression algorithm, with Area Under the Curve (AUC)=0.72 with the best performing feature set. Alternative feature sets with similar prediction performance are also presented. The prediction performance was inferior with an automated feature selection method, supporting the importance of using domain knowledge in machine learning.

We study the problem of determining the locations and capacities of COVID-19 specimen collection centers to efficiently improve accessibility to polymerase chain reaction testing during surges in testing demand. We develop a two-echelon multi-period location and capacity allocation model that determines optimal number and locations of pop-up testing centers, capacities of the existing centers as well as assignments of demand regions to these centers, and centers to labs. The objective is to minimize the total number of delayed appointments and specimens subject to budget, capacity, and turnaround time constraints, which will in turn improve the accessibility to testing. We apply our model to a case study for locating COVID-19 testing centers in the Region of Waterloo, Canada using data from the Ontario Ministry of Health, public health databases, and medical literature. We also test the performance of the model under uncertain demand and analyze its outputs under various scenarios. Our analyses provide practical insights to the public health decision-makers on the timing of capacity expansions and the locations for the new pop-up centers. According to our results, the optimal strategy is to dynamically expand the existing specimen collection center capacities and prevent bottlenecks by locating pop-up facilities. The optimal locations of pop-ups are among the densely populated areas that are in proximity to the lab and a subset of those locations are selected with the changes in demand. A comparison with a static approach promises up to 39% cost savings under high demand using the developed multi-period model.

Primary care providers (PCPs) are considered the first-line defenders in preventive care. Patients seeking service from the same PCP constitute that physician's panel, which determines the overall supply and demand of the physician. The process of allocating patients to physician panels is called panel design. This study quantifies patient overflow and builds a mathematical model to evaluate the effect of two implementable panel assignments. In specialized panel assignment, patients are assigned based on their medical needs or visit frequency. In equal panel assignment, patients are distributed uniformly to maintain a similar composition across panels. We utilize majorization theory and numerical examples to evaluate the performance of the two designs. The results show that specialized panel assignment outperforms when (1) patient demands and physician capacity are relatively balanced or (2) patients who require frequent visits incur a higher shortage penalty. In a simulation model with actual patient arrival patterns, we also illustrate the robustness of the results and demonstrate the effect of switching panel policy when the patient pool changes over time.

Assigning inpatients to hospital beds impacts patient satisfaction and the workload of nurses and doctors. The assignment is subject to unknown inpatient arrivals, in particular for emergency patients. Hospitals, therefore, need to deal with uncertainty on actual bed requirements and potential shortage situations as bed capacities are limited. This paper develops a model and solution approach for solving the patient bed-assignment problem that is based on a machine learning (ML) approach to forecasting emergency patients. First, it contributes by improving the anticipation of emergency patients using ML approaches, incorporating weather data, time and dates, important local and regional events, as well as current and historical occupancy levels. Drawing on real-life data from a large case hospital, we were able to improve forecasting accuracy for emergency inpatient arrivals. We achieved up to 17% better root mean square error (RMSE) when using ML methods compared to a baseline approach relying on averages for historical arrival rates. We further show that the ML methods outperform time series forecasts. Second, we develop a new hyper-heuristic for solving real-life problem instances based on the pilot method and a specialized greedy look-ahead (GLA) heuristic. When applying the hyper-heuristic in test sets we were able to increase the objective function by up to 5.3% in comparison to the benchmark approach in [40]. A benchmark with a Genetic Algorithm shows also the superiority of the hyper-heuristic. Third, the combination of ML for emergency patient admission forecasting with advanced optimization through the hyper-heuristic allowed us to obtain an improvement of up to 3.3% on a real-life problem.

Using data from cardiovascular surgery patients with long and highly variable post-surgical lengths of stay (LOS), we develop a modeling framework to reduce recovery unit congestion. We estimate the LOS and its probability distribution using machine learning models, schedule procedures on a rolling basis using a variety of optimization models, and estimate performance with simulation. The machine learning models achieved only modest LOS prediction accuracy, despite access to a very rich set of patient characteristics. Compared to the current paper-based system used in the hospital, most optimization models failed to reduce congestion without increasing wait times for surgery. A conservative stochastic optimization with sufficient sampling to capture the long tail of the LOS distribution outperformed the current manual process and other stochastic and robust optimization approaches. These results highlight the perils of using oversimplified distributional models of LOS for scheduling procedures and the importance of using optimization methods well-suited to dealing with long-tailed behavior.

The Dorfman pooled testing scheme is a process in which individual specimens (e.g., blood, urine, swabs, etc.) are pooled and tested together; if the merged sample tests positive for infection, then each specimen from the pool is tested individually. Through this procedure, laboratories can reduce the expected number of tests required to screen the population, as individual tests are only carried out when the pooled test detects an infection. Several different partitions of the population can be used to form the pools. In this study, we analyze the performance of ordered partitions, those in which subjects with similar probability of infection are pooled together. We derive sufficient conditions under which ordered partitions outperform other types of partitions in terms of minimizing the expected number of tests, the expected number of false negatives, and the expected number of false positive classifications. These sufficient conditions can be easily verified in practical applications once the dilution effect has been estimated. We also propose a measure of equity and present conditions under which this measure is maximized by ordered partitions.

We consider the problem of setting appropriate patient-to-nurse ratios in a hospital, an issue that is both complex and widely debated. There has been only limited effort to take advantage of the extensive empirical results from the medical literature to help construct analytical decision models for developing upper limits on patient-to-nurse ratios that are more patient- and nurse-oriented. For example, empirical studies have shown that each additional patient assigned per nurse in a hospital is associated with increases in mortality rates, length-of-stay, and nurse burnout. Failure to consider these effects leads to disregarded potential cost savings resulting from providing higher quality of care and fewer nurse turnovers. Thus, we present a nurse staffing model that incorporates patient length-of-stay, nurse turnover, and costs related to patient-to-nurse ratios. We present results based on data collected from three participating hospitals, the American Hospital Association (AHA), and the California Office of Statewide Health Planning and Development (OSHPD). By incorporating patient and nurse outcomes, we show that lower patient-to-nurse ratios can potentially provide hospitals with financial benefits in addition to improving the quality of care. Furthermore, our results show that higher policy patient-to-nurse ratio upper limits may not be as harmful in smaller hospitals, but lower policy patient-to-nurse ratios may be necessary for larger hospitals. These results suggest that a "one ratio fits all" patient-to-nurse ratio is not optimal. A preferable policy would be to allow the ratio to be hospital-dependent.

The US is experiencing a severe opioid epidemic with more than 80,000 opioid overdose deaths occurring in 2022. Beyond the tragic loss of life, opioid use disorder (OUD) has emerged as a major contributor to morbidity, lost productivity, mounting criminal justice system costs, and significant social disruption. This Current Opinion article highlights opportunities for analytics in supporting policy making for effective response to this crisis. We describe modeling opportunities in the following areas: understanding the opioid epidemic (e.g., the prevalence and incidence of OUD in different geographic regions, demographics of individuals with OUD, rates of overdose and overdose death, patterns of drug use and associated disease outbreaks, and access to and use of treatment for OUD); assessing policies for preventing and treating OUD, including mitigation of social conditions that increase the risk of OUD; and evaluating potential regulatory and criminal justice system reforms.