In order to overcome the shortage of the current costly DVT diagnosis and reduce the waste of valuable healthcare resources, we proposed a new diagnostic approach based on machine learning pre-test prediction models using EHRs. We examined the sociodemographic and clinical factors in the prediction of DVT with 518 NICU admitted patients, including 189 patients who eventually developed DVT. We used cross-validation on the training data to determine the optimal parameters, and finally, the applied ROC analysis is adopted to evaluate the predictive strength of each model. Two models (GLM and SVM) with the strongest ROC were selected for DVT prediction, based on which, we optimized the current intervention and diagnostic process of DVT and examined the performance of the proposed approach through simulations. The use of machine learning based pre-test prediction models can simplify and improve the intervention and diagnostic process of patients in NICU with suspected DVT, and reduce the valuable healthcare resource occupation/usage and medical costs.

No abstract

This paper studies the admission scheduling problem with considering the capacity usage of two interrelated resources (beds and operating rooms) between three consecutive stages of care during surgical patients' admissions to Chinese public hospitals, namely (1) pre-surgical inpatient bed, (2) surgery, (3) post-surgical inpatient bed. Demand comes from two types of patients: (1) emergency patients, who arise randomly and have to be admitted immediately, and (2) elective patients, whose admissions can be scheduled. The authors develop a Markov Decision Process (MDP) model that decides how many elective patients should be admitted each day, with the objective of optimally using both operating room and inpatient bed capacity. The authors demonstrate that the number of elective admissions scheduled each day is monotonically increasing in the state of the system and in the bed capacity, indicating that a higher level of waiting elective patients and available (or total) bed capacity pulls more elective admissions through the system. The total discounted expected cost of the system exhibits decreasing marginal returns as the capacity in each stage increases independently of other stages. Through numerical experiments, there is substantial value in making admission scheduling decisions by jointly considering inpatient beds and operating rooms.

No abstract