Search

Modeling a disease or the treatment of a patient has drawn much attention in recent years due to the vast amount of information that Electronic Health Records contain. This paper presents a probabilistic generative model of treatments that are described in terms of sequences of medical activities of variable length. The main objective is to identify distinct subtypes of treatments for a given disease, and discover their development and progression. To this end, the model considers that a sequence of actions has an associated hierarchical structure of latent variables that both classifies the sequences based on their evolution over time, and segments the sequences into different progression stages. The learning procedure of the model is performed with the Expectation–Maximization algorithm which considers the exponential number of configurations of the latent variables and is efficiently solved with a method based on dynamic programming. The evaluation of the model is twofold: first, we use synthetic data to demonstrate that the learning procedure allows the generative model underlying the data to be recovered; we then further assess the potential of our model to provide treatment classification and staging information in real-world data. Our model can be seen as a tool for classification, simulation, data augmentation and missing data imputation., EJ-GV PREDOC 2019

The aim of this study was to evaluate the results and economic costs of using volumetric modulated arc therapy (VMAT) (5 fr × 5 Gy), compared with other conventional 3D radiotherapy schemes such as "5 × 4 Gy" and "10 × 3 Gy".The data about the direct costs for the public health system was obtained from the Economic Information "Management per Patient" System available at the Integrated Health Organization Ezkerraldea Enkarterri Cruces. It is a model of real costs per patient which uses a bottom-up methodology which connects all sources of information generated in clinical practice, integrating healthcare information with economic information. This system presents the real cost per individualized patient, and shows the traceability of all clinical care. The costs of "typical patients" requiring hospital admission were identified for each of the three radiotherapy schemes based on the clinical activity and the material and human resources that were used.The 5 × 5 Gy scheme has a cost of EUR 4,801.48, which is 1.64% higher (EUR 77) than the "5 × 4 Gy" scheme (EUR 4,724.05). The "10 × 3 Gy" scheme has a cost of EUR 8,394.61, which is 74.8% higher (EUR 3,593) than the "5 × 5 Gy" scheme. The main cost factor in the "10 × 3 Gy" scheme is hospitalization, since patients are at hospital for 2 weeks compared with 1 week in the "5 × 5 Gy" scheme.The cost per patient of the VMAT "5 × 5 Gy" radiotherapy scheme is notably lower than that of the "10 × 3 Gy" scheme (conventional 3D radiotherapy), with the advantage of being administered in half the time. In relation to the scheme with 5 Gy × 4 sessions, the cost is similar to that of the "5 × 5 Gy" scheme.

Parkinson’s disease is one of the main reasons for neurological consultation in Spain. Due to the nature of the disease, it impacts patients, families, and caregivers. Parkinson’s disease is a degenerative disease with no cure, although second-line therapies have recently improved the quality of life of patients in advanced stages. The aim of this study was to analyse the costs of the following therapies: deep brain stimulation (DBS), continuous duodenal levodopa/carbidopa infusion (CDLCI), and continuous subcutaneous apomorphine infusion (CSAI). The methodology used was based on real-world data obtained from an integrated healthcare organization in the Basque Country from 2016 to 2018. This bottom-up retrospective approach only took into account the healthcare perspective. The results revealed the annual cost over 3 years and the projected cost for an additional 2 years. The total costs for 5 years of treatment were as follows: €53,217 for DBS, €208,163 for CDLCI, and €170,591 for CSAI. These costs are in line with those found in the available literature on the subject. Additionally, the analysis provided details of the different costs incurred during intervention with the therapies and compared the costs to those reported in other studies.

This paper presents a novel machine learning approach to perform an early prediction of the healthcare cost of breast cancer patients. The learning phase of our prediction method considers the following two steps: (1) in the first step, the patients are clustered taking into account the sequences of actions undergoing similar clinical activities and ensuring similar healthcare costs, and (2) a Markov chain is then learned for each group to describe the action-sequences of the patients in the cluster. A two step procedure is undertaken in the prediction phase: (1) first, the healthcare cost of a new patient’s treatment is estimated based on the average healthcare cost of its k-nearest neighbors in each group, and (2) finally, an aggregate measure of the healthcare cost estimated by each group is used as the final predicted cost. Experiments undertaken reveal a mean absolute percentage error as small as 6%, even when half of the clinical records of a patient is available, substantiating the early prediction capability of the proposed method. Comparative analysis substantiates the superiority of the proposed algorithm over the state-of-the-art techniques.

The efficiency of a smart cabinet with RFID technology to improve the information about inventory management for cardiothoracic surgery as well as for time savings, was assessed in a large reference hospital. In a 6-month study, the implemented operational RFID process (StocKey® Smart Cabinet) consisted of: i) product reception, registration and labelling in the general warehouse; ii) product storage in the cabinet and registered as inputs by radiofrequency; iii) products registered as outputs as required for surgery; iv) product assignment to a patient in the operating room; and v) return of products not used to the cabinet. Stock-outs, stock mismatches, urgent restocking, assignment of high-value medical products to patients, and time allocated by the supervisory staff to the stock management, were assessed on a monthly basis. 0% stock-outs and 0% stock mismatches using RFID were observed during the study. Monthly percentages of products requiring urgent restocking ranged from 0% to 13.3%. No incorrect assignments to patients of surgery products or prostheses were detected. The percentage of correct assignments increased from 36.1%–86.1% to 100% in the first 4–5 months. The total average time allocated by the supervisory staff to the whole logistic chain was reduced by 58% (995 min with the traditional manual system vs. 428 min with RFID). The RFID system showed the ability to monitor both the traceability and consumption per patient of high-value surgery products as well as contributed to significant time savings.

The efficiency of a smart cabinet with RFID technology to improve the information about inventory management for cardiothoracic surgery as well as for time savings, was assessed in a large reference hospital. In a 6-month study, the implemented operational RFID process (StocKey® Smart Cabinet) consisted of: i) product reception, registration and labelling in the general warehouse; ii) product storage in the cabinet and registered as inputs by radiofrequency; iii) products registered as outputs as required for surgery; iv) product assignment to a patient in the operating room; and v) return of products not used to the cabinet. Stock-outs, stock mismatches, urgent restocking, assignment of high-value medical products to patients, and time allocated by the supervisory staff to the stock management, were assessed on a monthly basis. 0% stock-outs and 0% stock mismatches using RFID were observed during the study. Monthly percentages of products requiring urgent restocking ranged from 0% to 13.3%. No incorrect assignments to patients of surgery products or prostheses were detected. The percentage of correct assignments increased from 36.1%-86.1% to 100% in the first 4-5 months. The total average time allocated by the supervisory staff to the whole logistic chain was reduced by 58% (995 min with the traditional manual system vs. 428 min with RFID). The RFID system showed the ability to monitor both the traceability and consumption per patient of high-value surgery products as well as contributed to significant time savings.