Effects of Hospital Information System on the Performance of Management Units in Public Hospitals Analysis in Southwestern Iran

: The current study examines the effects of a hospital information system (HIS) on the performance of management units in Ahvaz public hospitals, Iran. The HIS supports hospital activities at practical, tactical, and strategic levels. In other words, this system establishes a connection between patient care and administrative information in all hospital activities. This descriptive-analytic research was an applied study with a correlational method. The hypotheses were tested by correlation model, structural equation modeling, one-sample t-test, one-way analysis of variance, and one-sample Kolmogorov-Smirnov test using the SPSS software version 20 and LISREL. The findings of this study indicated that an automated HIS can be a powerful tool helping managers with the process of hospital management and decision-making, leading to significantly improved hospital performance. Therefore, continuous training courses are beneficial in enhancing information quality and modern technology usage, which in turn improve the quality of services offered to patients and clients and make them less time-consuming. As a result, an effective step is taken in improving health services. The present study showed that the characteristics of HIS, including user-friendliness, speed, quality, being up-to-date, conformity with working conditions, and proficiency, have positive and significant impacts on the performance of management units.

Association of women leaders in the C-suite with hospital performance

BackgroundWomen comprise 50% of the healthcare workforce, but only about 25% of senior leadership positions in the USA. No studies to our knowledge have investigated the performance of hospitals led by women versus those led by men to evaluate the potential explanation that the inequity reflects appropriate selection due to skill or performance differences.MethodsWe conducted a descriptive analysis of the gender composition of hospital senior leadership (C-suite) teams and cross-sectional, regression-based analyses of the relationship between gender composition, hospital characteristics (eg, location, size, ownership), and financial, clinical, safety, patient experience and innovation performance metrics using 2018 data for US adult medical/surgical hospitals with >200 beds. C-suite positions examined included chief executive officer (CEO), chief financial officer (CFO) and chief operating officer (COO). Gender was obtained from hospital web pages and LinkedIn. Hospital characteristics and performance were obtained from American Hospital Directory, American Hospital Association Annual Hospital Survey, Healthcare Cost Report Information System and Hospital Consumer Assessment of Healthcare Providers and Systems surveys.ResultsOf the 526 hospitals studied, 22% had a woman CEO, 26% a woman CFO and 36% a woman COO. While 55% had at least one woman in the C-suite, only 15.6% had more than one. Of the 1362 individuals who held one of the three C-suite positions, 378 were women (27%). Hospital performance on 27 of 28 measures (p>0.05) was similar between women and men-led hospitals. Hospitals with a woman CEO performed significantly better than men-led hospitals on one financial metric, days in accounts receivable (p=0.04).ConclusionHospitals with women in the C-suite have comparable performance to those without, yet inequity in the gender distribution of leaders remains. Barriers to women’s advancement should be recognised and efforts made to rectify this inequity, rather than underusing an equally skilled pool of potential women leaders.

Functional IT Complementarity and Hospital Performance in the United State: A Longitudinal Investigation

For healthcare practitioners and policymakers, one of the most challenging problems is understanding how to implement health information technology (HIT) applications in a way that yields the most positive impacts on quality and cost of care. We identify four clinical HIT functions which we label as order entry and management (OEM), decision support (DS), electronic clinical documentation (ECD), and results viewing (RV). We view OEM and DS as primary clinical functions and ECD and RV as support clinical functions. Our results show that no single combination of applications uniformly improves clinical and experiential quality and reduces cost for all hospitals. Thus, managers must assess which HIT interactions improve which performance metric under which conditions. Our results suggest that synergies can be realized when these systems are implemented simultaneously. Additionally, synergies can occur when support HIT is implemented before primary HIT and irrespective of the order in which primary HITs are implemented. Practitioners should also be aware that the synergistic effects of HITs and their impact on cost and quality are different for chronic and acute diseases. Our key message to top managers is to prioritize different combinations of HIT contingent on the performance variables they are targeting for their hospitals but also to realize that technology may not impact all outcomes.

DeepDRG: Performance of Artificial Intelligence Model for Real-Time Prediction of Diagnosis-Related Groups

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.

Designing a Solar Photovoltaic System for Generating Renewable Energy of a Hospital: Performance Analysis and Adjustment Based on RSM and ANFIS Approaches

One of the most favorable renewable energy sources, solar photovoltaic (PV) can meet the electricity demand considerably. Sunlight is converted into electricity by the solar PV systems using cells containing semiconductor materials. A PV system is designed to meet the energy needs of King Abdulaziz University Hospital. A new method has been introduced to find optimal working capacity, and determine the self-consumption and sufficiency rates of the PV system. Response surface methodology (RSM) is used for determining the optimal working conditions of PV panels. Similarly, an adaptive neural network based fuzzy inference system (ANFIS) was employed to analyze the performance of solar PV panels. The outcomes of methods were compared to the actual outcomes available for testing the performance of models. Hence, for a 40 MW target PV system capacity, the RSM determined that approximately 33.96 MW electricity can be produced, when the radiation rate is 896.3 W/m2, the module surface temperature is 41.4 °C, the outdoor temperature is 36.2 °C, the wind direction and speed are 305.6 and 6.7 m/s, respectively. The ANFIS model (with nine rules) gave the highest performance with lowest residual for the same design parameters. Hence, it was determined that the hourly electrical energy requirement of the hospital can be met by the PV system during the year.

Derivation and Validation of a Risk Factor Model to Identify Medical Inpatients at Risk for Venous Thromboembolism

Background: Venous thromboembolism (VTE) prophylaxis is recommended for hospitalized medical patients at high risk for VTE. Multiple risk assessment models exist, but few have been compared in large data sets. Methods: We constructed a derivation cohort using 6 years of data from 13 hospitals to identify risk factors associated with developing VTE within 14 days of admission. VTE was identified using a complex algorithm combining administrative codes and clinical data. We developed a multivariable prediction model and applied it to 2 validation cohorts: a temporal cohort, including two additional years and a cross-validation, in which we refit the model excluding one hospital at a time, and applied the refitted model to the holdout hospital. Performance was evaluated using the C-statistic. Results: The derivation cohort included 160,928 patients with a 14-day VTE rate of 0.79%. The final multivariable model contained 13 patient risk factors. The model had an optimism corrected C-statistic of 0.80 and good calibration. The temporal validation cohort included 55,301 patients, with a VTE rate of 0.74%. Based on the c-statistic, the Cleveland Clinic Model (CCM) outperformed the Padua model (0.76 vs. 0.72, p<0.01). The CCM was more sensitive (65.8% vs. 60.4%, p=0.05) and more specific (74.9% vs. 71.4%, p<.001), with higher positive (1.9% vs. 1.5%, p<.001) and negative predictive values (99.7% vs. 99.6%, p=0.01). C-statistics for the CCM at individual hospitals ranged from 0.64 to 0.76. Conclusion: A new VTE risk assessment model outperformed the Padua model. After further validation it could be recommended for widespread use.

P.070 Introducing Stroke Endovascular Thrombectomy Into A Smaller Canadian Site, Is It Safe?

Background: Success of Endovascular Thrombectomy (EVT) requires ultra-fast access to specialized neuro imaging, neurological assessment and an angio suite with interventional radiologists. Prior access was via transport to Vancouver and outcomes were poor, with a high rate of disability or death. This appeared primarily due to long delays. Methods: Quality control process, in parallel to the introduction of a new intervention, EVT, to Vancouver Island, to determine if this intervention could be delivered with reasonable safety and good outcomes. Patients receiving EVT from May, 2016 until Sep, 2019 are included, with 90-day outcomes. Data was collected by stroke nurses. Results: The proportion of patients having a good outcome was comparable to that of the major clinical trial involving Canadian academic centres. The proportion sustaining a poor outcome was comparable to the control group in that trial population (who still received tPA treatment where possible). This was despite a median age 4.5 years greater than in that trial. Conclusions: EVT required coordination of multiple services. Victoria General Hospital performance in terms of speed to treatment was slower than in the published trials. This is a factor in determining outcome and is therefore an important quality improvement target moving forward.

102. Evaluation of the Association between the Antibiotic Spectrum Index and Antibiotic Days of Therapy: A Retrospective Study across 124 Acute-care Hospitals

Background Antibiotic stewardship programs often measure antibiotic days of therapy (DOT), but this metric does not reflect the antibiotic spectrum. In this study, we used the previously published Antibiotic Spectrum Index (ASI), which attaches a score (1-13) to the spectrum of each antibiotic, to evaluate the content of antibiotic use across all Veterans Health Administration (VHA) hospitals. We also assessed how benchmarking hospital performance changed when ASI was used instead of DOT. Methods We conducted a retrospective cohort study of patients admitted to 124 acute-care VHA hospitals during 2018. We obtained data on administered antibiotics, the days of antibiotic use (DOT), and days-present (DP) from the VHA Corporate Data Warehouse and then aggregated data to the hospital-level using the National Healthcare Safety Network’s methodology. We modified the original ASI by changing 3.8% of the bug-drug scores to ensure consistency across all scores and adding 27 new antibiotics agents. For each hospital, we calculated ASI/DOT, ASI/1,000 DP, and DOT/1,000 DP and ranked hospitals on their performance. We performed a Spearman’s rank-order correlation to compare hospitals on these metrics and their associated rankings. Results At the hospital-level, the median ASI/DOT, ASI/1,000 DP and DOT/1,000 DP were 5.4 (interquartile range: 5.2-5.8), 2,332.7 (1,941.8-2,796.2) and 443.5 (362.5-512.2), respectively. There was a strong correlation between the ASI/1,000 DP and DOT/1,000 DP metrics [Spearman’s correlation test: r=0.97 (p&lt; 0.01)] but only a weak and insignificant correlation between ASI/DOT and DOT/1,000 DP [r=0.17 (p=0.06), Figure 1]. Twenty (16.1%) hospitals showed a difference of 10% or more in their ranking for ASI/1,000 DP compared to their ranking for DOT/1,000 DP. The range of ranking difference was from -17.7% to 21.0% (Figure 2a and b). Figure 1. Distribution of the Antibiotic Spectrum Index / Day of Therapy by Days of Therapy / 1000 Days Present for 124 Acute-Care VHA Hospitals during 2018. Black line: Median values of DOT/1,000 DP and ASI/DOT, respectively. Figure 2. (a) Distribution of the rankings in DOT/1,000 DP and ASI/1,000 DP. Blue line: the position of same ranking between ASI/1,000 DP and DOT/1,000 DP. (b) Distribution of the differences in each hospital’s ranking for DOT/1,000 DP and ASI/1,000 DP Conclusion Our findings suggest that hospitals using fewer days of antibiotic therapy did not necessarily use narrower-spectrum antibiotics. ASI/1,000 DP, as a combined measure of antibiotic consumption quantity and average spectrum, provided a different view of hospital performance than DOT/1,000 DP alone. Future work is needed to define how this new metric relates to the quality of antibiotic use. Disclosures All Authors: No reported disclosures