Analyzing health insurance claims on different timescales to predict days in hospital.

Health insurers maintain large databases containing information on medical services utilized by claimants, often spanning several healthcare services and providers. Proper use of these databases could facilitate better clinical and administrative decisions. In these data sets, there exists many unequally spaced events, such as hospital visits. However, data mining of temporal data and point processes is still a developing research area and extracting useful information from such data series is a challenging task. In this paper, we developed a time series data mining approach to predict the number of days in hospital in the coming year for individuals from a general insured population based on their insurance claim data. In the proposed method, the data were windowed at four different timescales (bi-monthly, quarterly, half-yearly and yearly) to construct regularly spaced time series features extracted from such events, resulting in four associated prediction models. A comparison of these models indicates models using a half-yearly windowing scheme delivers the best performance on all three populations (the whole population, a senior sub-population and a non-senior sub-population). The superiority of the half-yearly model was found to be particularly pronounced in the senior sub-population. A bagged decision tree approach was able to predict 'no hospitalization' versus 'at least one day in hospital' with a Matthews correlation coefficient (MCC) of 0.426. This was significantly better than the corresponding yearly model, which achieved 0.375 for this group of customers. Further reducing the length of the analysis windows to three or two months did not produce further improvements.

Gender disparities in red blood cell transfusion in elective surgery: a post hoc multicentre cohort study.

OBJECTIVES: A post hoc gender comparison of transfusion-related modifiable risk factors among patients undergoing elective surgery. SETTINGS: 23 Austrian centres randomly selected and stratified by region and level of care. PARTICIPANTS: We consecutively enrolled in total 6530 patients (3465 women and 3065 men); 1491 underwent coronary artery bypass graft (CABG) surgery, 2570 primary unilateral total hip replacement (THR) and 2469 primary unilateral total knee replacement (TKR). MAIN OUTCOME MEASURES: Primary outcome measures were the number of allogeneic and autologous red blood cell (RBC) units transfused (postoperative day 5 included) and differences in intraoperative and postoperative transfusion rate between men and women. Secondary outcomes included perioperative blood loss in transfused and non-transfused patients, volume of RBCs transfused, perioperative haemoglobin values and circulating red blood volume on postoperative day 5. RESULTS: In all surgical groups, the transfusion rate was significantly higher in women than in men (CABG 81 vs 49%, THR 46 vs 24% and TKR 37 vs 23%). In transfused patients, the absolute blood loss was higher among men in all surgical categories while the relative blood loss was higher among women in the CABG group (52.8 vs 47.8%) but comparable in orthopaedic surgery. The relative RBC volume transfused was significantly higher among women in all categories (CABG 40.0 vs 22.3; TKR 25.2 vs 20.2; THR 26.4 vs 20.8%). On postoperative day 5, the relative haemoglobin values and the relative circulating RBC volume were higher in women in all surgical categories. CONCLUSIONS: The higher transfusion rate and volume in women when compared with men in elective surgery can be explained by clinicians applying the same absolute transfusion thresholds irrespective of a patient's gender. This, together with the common use of a liberal transfusion strategy, leads to further overtransfusion in women.

Impact of hierarchies of clinical codes on predicting future days in hospital.

Health insurance claims contain valuable information for predicting the future health of a population. Nowadays, with many mature machine learning algorithms, models can be implemented to predict future medical costs and hospitalizations. However, it is well-known that the way in which the data are represented significantly affects the performance of machine learning algorithms. In health insurance claims, key clinical information mainly comes from the associated clinical codes, such as diagnosis codes and procedure codes, which are hierarchically structured. In this study, it is investigated whether the hierarchies of such clinical codes can be utilized to improve predictive performance in the context of predicting future days in hospital. Empirical investigations were done on data sets of different sizes, considering that the frequency of the appearance of lower-level (more specific) clinical codes could vary significantly in populations of different sizes. The use of bagged trees with feature sets that include only basic demographic features, low-level, medium-level, high-level clinical codes, and a full feature set were compared. The main finding from this study is that different hierarchies of clinical codes do not have a significant impact on the predictive power. Some other findings include: 1) Sample size greatly affects the predictive outcome (more observations result in more stable and more accurate outcomes); 2) Combined use of enriched demographic features and clinical features give better performance as compared to using them separately.

Predicting days in hospital using health insurance claims.

Health-care administrators worldwide are striving to lower the cost of care while improving the quality of care given. Hospitalization is the largest component of health expenditure. Therefore, earlier identification of those at higher risk of being hospitalized would help health-care administrators and health insurers to develop better plans and strategies. In this paper, a method was developed, using large-scale health insurance claims data, to predict the number of hospitalization days in a population. We utilized a regression decision tree algorithm, along with insurance claim data from 242 075 individuals over three years, to provide predictions of number of days in hospital in the third year, based on hospital admissions and procedure claims data. The proposed method performs well in the general population as well as in subpopulations. Results indicate that the proposed model significantly improves predictions over two established baseline methods (predicting a constant number of days for each customer and using the number of days in hospital of the previous year as the forecast for the following year). A reasonable predictive accuracy (AUC =0.843) was achieved for the whole population. Analysis of two subpopulations-namely elderly persons aged 63 years or older in 2011 and patients hospitalized for at least one day in the previous year-revealed that the medical information (e.g., diagnosis codes) contributed more to predictions for these two subpopulations, in comparison to the population as a whole.

Predicting number of hospitalization days based on health insurance claims data using bagged regression trees.

Healthcare administrators worldwide are striving to both lower the cost of care whilst improving the quality of care given. Therefore, better clinical and administrative decision making is needed to improve these issues. Anticipating outcomes such as number of hospitalization days could contribute to addressing this problem. In this paper, a method was developed, using large-scale health insurance claims data, to predict the number of hospitalization days in a population. We utilized a regression decision tree algorithm, along with insurance claim data from 300,000 individuals over three years, to provide predictions of number of days in hospital in the third year, based on medical admissions and claims data from the first two years. Our method performs well in the general population. For the population aged 65 years and over, the predictive model significantly improves predictions over a baseline method (predicting a constant number of days for each patient), and achieved a specificity of 70.20% and sensitivity of 75.69% in classifying these subjects into two categories of 'no hospitalization' and 'at least one day in hospital'.

Cellular fibronectin expression in human trabecular meshwork and induction by transforming growth factor-ß2.

PURPOSE: Levels of TGF-ß2 are higher in POAG aqueous humor, causing deposition of extracellular matrix (ECM) proteins, including fibronectin (FN), in the glaucomatous human trabecular meshwork (HTM) that may be responsible for elevated IOP. The purpose of this study was to identify the expression of cellular FN (cFN) isoforms (EDA and EDB) in HTM cells and tissues, and to determine whether TGF-ß2 can induce cFN expression and fibril formation in cultured HTM cells. METHODS: Expression of cFN mRNA isoforms and induction by recombinant TGF-ß2 (5 ng/mL) were determined by quantitative RT-PCR. The TGF-ß2 induction of EDA isoform protein expression and FN fibril formation were analyzed using Western immunoblots and immunocytochemistry (ICC), respectively. Immunohistochemistry (IHC) analysis was used to examine total FN and EDA isoform expression in normal (NTM) and glaucomatous (GTM) trabecular meshwork (TM) tissues. RESULTS: Both cFN mRNA isoforms were expressed in cultured HTM cells and were induced by TGF-ß2 after 2, 4, and 7 days (P < 0.05). Similarly, EDA isoform protein and fibril formation were increased after 4 and 7 days of TGF-ß2 treatment. Finally, GTM tissues had significantly greater EDA isoform protein levels (1.7-fold, P < 0.05) compared to NTM tissues. CONCLUSIONS: This study demonstrated that cFN isoforms are expressed and induced in HTM cells by TGF-ß2. Also, increased EDA isoform protein levels were seen in GTM tissues. Our findings suggest that induction of cFN isoform expression in the TM ECM may be a novel pathologic mechanism involved in the TM changes associated with glaucoma.