Search

Nowadays, the use of diagnosis-related groups (DRGs) has been increased to claim reimbursement for inpatient care. The overall benefits of using DRGs depend upon the accuracy of clinical coding to obtain reasonable reimbursement. However, the selection of appropriate codes is always challenging and requires professional expertise. The rate of incorrect DRGs is always high due to the heavy workload, poor quality of documentation, and lack of computer assistance. We therefore developed deep learning (DL) models to predict the primary diagnosis for appropriate reimbursement and improving hospital performance. A dataset consisting of 81,486 patients with 128,105 episodes was used for model training and testing. Patients’ age, sex, drugs, diseases, laboratory tests, procedures, and operation history were used as inputs to our multiclass prediction model. Gated recurrent unit (GRU) and artificial neural network (ANN) models were developed to predict 200 primary diagnoses. The performance of the DL models was measured by the area under the receiver operating curve, precision, recall, and F1 score. Of the two DL models, the GRU method, had the best performance in predicting the primary diagnosis (AUC: 0.99, precision: 83.2%, and recall: 66.0%). However, the performance of ANN model for DRGs prediction achieved AUC of 0.99 with a precision of 0.82 and recall of 0.57. The findings of our study show that DL algorithms, especially GRU, can be used to develop DRGs prediction models for identifying primary diagnosis accurately. DeepDRGs would help to claim appropriate financial incentives, enable proper utilization of medical resources, and improve hospital performance.

This research explores the association of public health expenditure with economic performance across the United States. Healthcare expenditure can result in better provision of health opportunities, which can strengthen human capital and improve the productivity, thereby contributing to economic performance. It is therefore important to assess the phenomenon of healthcare spending in a country. Using visual analytics, we collected economic and health data from the Bureau of Economic Analysis and the Bureau of Labor Statistics for the years 2003–2014. The overall results strongly suggest a positive correlation between healthcare expenditure and the economic indicators of income, GDP, and labor productivity. While healthcare expenditure is negatively associated with multi-factor productivity, it is positively associated with the indicators of labor productivity, personal spending, and GDP. The study shows that an increase in healthcare expenditure has a positive relationship with economic performance. There are also variations across states that justify further research. Building on this and prior research, policy implications include that the good health of citizens indeed results in overall better economy. Therefore, investing carefully in various healthcare aspects would boost income, GDP, and productivity, and alleviate poverty. In light of these potential benefits, universal access to healthcare is something that warrants further research. Also, research can be done in countries with single-payer systems to see if a link to productivity exists there. The results support arguments against our current healthcare system's structure in a limited way.

Some researchers claim that health care expenditures for older people are growing faster than for the rest of the population. This process is referred to as steepening. The aim of this paper is to test steepening, applying new data and revised methods. Furthermore, we explain the connection between the terms red herring hypothesis, i.e., that time to death and not age per se drives the health care expenditures, and steepening. We also present the mechanisms that may induce steepening, as presented in the literature. When testing steepening, we apply data from all inpatient stays in somatic hospitals in Norway in the period 1998–2009, i.e., the data has no self-selection and covers the entire population of Norway (5 million). Our analysis does not reject steepening, with the exception of the 0-year-olds. The results also hold when controlling for mortality-related expenditures. Furthermore, we observe an increase in expenditures for the 0-year-olds. Finally, we find increasing mortality-related expenditures over time. We find the link between steepening and the red herring hypothesis to be vague, and we find steepening and the red herring hypothesis to be independent.

Geographical clusters in health expenditures are well documented and accounting for spatial interactions may contribute to properly identify the factors affecting the use of health services the most. As for hospital care, spillovers may derive from strategic behaviour of hospitals and from patients’ preferences that may induce mobility across jurisdictions, as well as from geographically-concentrated risk factors, knowledge transfer and interactions between different layers of care. Our paper focuses on a largely overlooked potential source of spillovers in hospital expenditure: the heterogeneity of primary care providers’ behaviour. To do so, we analyse expenditures associated to avoidable hospitalisations separately from expenditures for highly complex treatments, as the former are most likely affected by General Practitioners, while the latter are not. We use administrative data for Italy’s Region Emilia Romagna between 2007 and 2010. Since neighbouring districts may belong to different Local Health Authorities (LHAs), we employ a spatial contiguity matrix that allows to investigate the effects of geographical and institutional proximity and use it to estimate Spatial Autoregressive and Spatial Durbin Models.

Introduction: Preventable hospitalizations are responsible for increasing the cost of health care and reflect ineffectiveness of the health services in the primary care setting. The objective of this study was to assess expenditure for hospitalizations and utilize expenditure differentials to determine factors associated with ambulatory care - sensitive conditions (ACSCs) hospitalizations. Methods: A cross-sectional study of hospitalizations among Medicaid enrollees in comprehensive managed care plans in 2009 was conducted. A total of 25 581 patients were included in the analysis. Expenditures on hospitalizations were examined at the 50th, 75th, 90th, and 95th expenditure percentiles both at the bivariate level and in the logistic regression model to determine the impact of differing expenditure on ACSC hospitalizations. Results: Compared with patients without ACSC admissions, a larger proportion of patients with ACSC hospitalizations required advanced treatment or died on admission. Overall mean expenditures were higher for the ACSC group than for non-ACSC group (US$18 070 vs US$14 452). Whites and blacks had higher expenditures for ACSC hospitalization than Hispanics at all expenditure percentiles. Patient’s age remained a consistent predictor of ACSC hospitalization across all expenditure percentiles. Patients with ACSC were less likely to have a procedure on admission; however, the likelihood decreased as expenditure percentiles increased. At the median expenditure, blacks and Hispanics were more likely than other race/ethnic groups to have ACSC hospitalizations (odds ratio [OR]: 1.307, 95% confidence interval [CI]: 1.013-1.686 and OR 1.252, 95% CI: 1.060-1.479, respectively). Conclusion: Future review of delivery and monitoring of services at the primary care setting should include managed care plans in order to enhance access and overall quality of care for optimal utilization of the resources.

Background: This study aims to contribute to the ongoing policy and scholarly debate on physician-hospital integration (INT) and health care cost by providing evidence for the role of physician boards in mitigating hospital expenditure associated with INT. Methods: We conducted our study of the relationship between INT, physician boards, and hospital expenditure using data on hospitals in California. We obtained data from the Centers for Medicare and Medicaid Services, American Hospital Association, and California Office of Statewide Health Planning and Development from 2002 to 2006. A hospital fixed-effect ordinary least square (OLS) regression analysis was used. Results: Hospital expenditure was higher in a hospital with an integrated arrangement (e.g., a hospital that adopted an integrated salary model) than under other independent arrangements between physicians and hospitals, and the proportion of physician members on hospital boards negatively moderated the effect of integration on hospital expenditure. Conclusions: Physician boards may provide a context that affords benefits that can reduce hospital expenditures under INT. This finding highlights the importance to having a supportive organizational design when implementing INT.

Pay-for-Performance programs offering additional payments to GPs can be used not only to improve the quality of care but also for cost containment purposes. In this paper, we analyse the impact of removing financial incentives in primary care that were aimed at containing hospital expenditure in the Italian region of Emilia-Romagna during the period 2002–2004. Our analysis draws on regional databanks linking GPs' characteristics to those of their patients (including all sources of public payments made to GPs), together with information on the utilisation of hospital services. The dataset includes 2,936,834 patients, 3229 GPs and 39 districts belonging to 11 Local Health Authorities. We employ a difference-in-difference specification to assess changes in expenditures for avoidable and total hospital admissions. We identify the treatment group with GPs operating in districts where the program is withdrawn during the observation period (“Leavers”). Their performance is compared to that of two separate control groups, namely: GPs working in districts that grant incentives for the entire period (“Stayers”) and those working in districts that never introduced measures for the containment of hospitalisations (“Non Participants”). The comparison between treatment and control groups shows that removing incentives does not result in a worse performance by Leavers compared to both control groups. This supports the policy of removing incentives, as such entail extra payments to GPs which, however, do not seem capable of significantly influencing their behaviour in the desired way. Our findings complement previous evidence from the same institutional context showing that only those programs that aim to improve disease management for specific conditions – rather than to simply contain expenditure – have proven successful in reducing avoidable admissions for the target population.

Objective: This is the second of three reports on the follow-up review of mental health care at Helen Joseph Hospital (HJH). Objectives for the review were to provide realistic estimates of cost for unit activities and to establish a quality assurance cycle that may facilitate cost centre management. Method: The study described and used activity-based costing (ABC) as an approach to analyse the recurrent cost of acute in-patient care for the financial year 2007-08. Fixed (e.g. goods and services, staff salaries) and variable recurrent costs (including laboratory’, ‘pharmacy’) were calculated. Cost per day, per user and per diagnostic group was calculated. Results: While the unit accounted for 4.6% of the hospital’s total clinical activity (patient days), the cost of R8.12 million incurred represented only 2.4% of the total hospital expenditure (R341.36 million). Fixed costs constituted 90% of the total cost. For the total number of 520 users that stayed on average 15.4 days, the average cost was R1,023.00 per day and R15748.00 per user. Users with schizophrenia accounted for the most (35%) of the cost, while the care of users with dementia was the most expensive (R23,360.68 per user). Costing of the application of World Health Organization norms for acute care staffing for the unit, projected an average increase of 103% in recurrent costs (R5.1 million), with the bulk (a 267% increase) for nursing. Conclusion: In the absence of other guidelines, aligning clinical activity with the proportion of the hospital’s total budget may be an approach to determine what amount should be afforded to acute mental health in-patient care activities in a general regional hospital such as HJH. Despite the potential benefits of ABC, its continued application will require time, infrastructure and staff investment to establish the capacity to maintain routine annual cost analyses for different cost centres. Key words: Cost analysis; Activity-based costing; Acute mental health care; Recurrent cost; Fixed and variable cost; Cost centre management; Hospital expenditure

Τα ΑΕΕ είναι η πρώτη αιτία αναπηρίας και η τρίτη αιτία θανάτου παγκοσμίως. Επίσης οι ασθενείς με ΑΕΕ είναι οι συχνότεροι χρήστες των υπηρεσιών υγείας. Παράλληλα, στη χώρα μας δαπανάται ετησίως το 10% του Ακαθάριστου Εγχώριου Προϊόντος (ΑΕΠ) για την υγεία σε σχέση με το μέσο όρο του 8,9% των χωρών του Οργανισμού Οικονομικής Συνεργασίας και Ανάπτυξης (ΟΟΣΑ). Στόχος της μελέτης είναι η οικονομική αξιολόγηση του ενδο-νοσοκομειακού κόστους ασθενών με οξύ ΑΕΕ στην Ελλάδα καθώς επίσης και ο προσδιορισμός ανεξάρτητων παραγόντων που επηρεάζουν το κόστος νοσηλείας. Καταγράφηκαν δημογραφικά και κλινικά χαρακτηριστικά σε 429 συνεχόμενους ασθενείς με οξύ ΑΕΕ (ισχαιμικό ή αιμορραγικό) που εισήχθησαν σε όλες τις κλινικές του Πανεπιστημιακού Γενικού Νοσοκομείου Πατρών για διάστημα 18 μηνών. Υπολογίσαμε το κόστος, για κάθε ασθενή ατομικά, από την ώρα της εισβολής του ΑΕΕ έως την έξοδό του από το νοσοκομείο. Το κόστος μετρήθηκε σε ευρώ (€) και σύμφωνα με τις πραγματικές δαπάνες του νοσοκομείου. Η μέση ηλικία των ασθενών ήταν 68.9 (±12.7) έτη και η διάρκεια νοσηλείας ήταν 10.9 (±7.9) ημέρες. Οι 345 ασθενείς (80%) είχαν ισχαιμικό ΑΕΕ και 84 (20%) είχαν πρωτοπαθή ενδοεγκεφαλική αιμορραγία. Το άμεσο ενδο-νοσοκομειακό κόστος νοσηλείας όλων των ασθενών με οξύ ΑΕΕ ανήλθε στα 1.551.445,00 € για μια συνολική διάρκεια νοσηλείας 4.674 ημερών (331,9 € ανά ημέρα νοσηλείας). Το μέσο ενδονοσοκομειακό κόστος ανά ασθενή με ΑΕΕ ήταν 3.624,9(±2695.4) €. Το 59% του συνολικού κόστους αποδόθηκε στο κόστος "κλίνης και προσωπικού", (6%) "προ εισαγωγής", (13%) "εργαστηριακό έλεγχο", (6%) "απεικονιστικό έλεγχο", (8%) "αποκλειστική νοσηλευτική φροντίδα", (7%) "φαρμακευτική αγωγή", (0.6%) "θεραπεία αποκατάστασης" και (0.7%) "διάφορα έξοδα". Τα αιμορραγικά ΑΕΕ είχαν σημαντικά μεγαλύτερο κόστος από τα ισχαιμικά ΑΕΕ (μέσο 5305.4 και 3.214,5 €, αντίστοιχα). Μεταξύ των υπότυπων των ισχαιμικών ΑΕΕ το συνολικό μέσο κόστος ήταν σημαντικά χαμηλότερο για τα "κενοτοπιώδη" έμφρακτα (2328.7±1100.2 €). Η διάρκεια νοσηλείας είχε υψηλή συσχέτιση με το συνολικό ενδο-νοσοκομειακό κόστος. Η πολυπαραγοντική γραμμική ανάλυση παλινδρόμησης έδειξε ότι το τμήμα εισαγωγής, η βαρύτητα του ΑΕΕ στην εισαγωγή, ο τύπος του ΑΕΕ και η κατάσταση εξόδου ήταν ανεξάρτητοι παράγοντες του κόστους. Αν επιθυμούμε τη συγκράτηση του νοσοκομειακού κόστους, θα πρέπει να ληφθούν υπόψη πολιτικές διοίκησης που στοχεύουν στη μείωση της διάρκειας νοσηλείας. Stroke is the first cause of disability and the third cause of death worldwide. Moreover, in the western countries, the stroke patients are the most frequent users of all the health services and the hospital budgets. At the same time, 10% of the Gross Domestic Product (GDP) is annually spent on health in relation with the average 8.9% of the Organisation for Economic Co-operation and Development (OECD) countries. Aim of this study is the economic evaluation on the in-hospital cost of patients with an acute stroke in Greece and the identification of potential independent factors influencing this cost. Demographic and clinical data were recorded on 429 consecutive patients with an acute stroke (ischemic and hemorrhagic), admitted to the University General Hospital of Patras during a period of 18 months. We calculated the cost, individually for each patient, from the stroke onset until the discharge from the hospital. The cost was measured in euro (€), according to the real expenditure of hospital. Mean age was 68.9 (±12.7) years and length of stay (LOS) was 10.9 (±7.9) days. In all, 345 patients (80%) had an ischemic stroke and 84 (20%) had a primary intracerebral hemorrhage. The direct in-hospital cost of all stroke patients, 1.551.445,00 €, accounted for a total hospitalisation of 4.674 days (331.9 € per day in hospital). The mean in-hospital cost per patient was 3.624,9 (±2695.4) €. The 59% of the total cost concerns the cost of "bed and staff", (6%) "pre-hospital cost", (13%) "laboratory investigations", (6%) "imaging investigations", (8%) "supportive nursing", (7%) "medication", (0.6%) "rehabilitation therapy" and (0.7%) "other expenses". Hemorrhagic strokes were significantly more expensive than the ischemic strokes (mean 5305.4 (± 4204.8) € and 3214,5 (±1976.2) € respectively). Amongst ischemic stroke subtypes the mean total cost was significantly lower for lacunar strokes (2328.7 ± 1100.2 €). The length of stay was highly correlated with in-hospital total cost. Multivariate linear regression model showed that the admission ward, stroke severity on admission, stroke type and status discharge were independent predictors of cost. In order to withhold the hospital cost, policies of administration that aiming to the reduction of length of stay should be taken into consideration.