Research Interests: Algorithms, Ophthalmology, Forecasting, Medicine, Logistic Regression, and 15 moreHumans, Glaucoma, Female, Male, Intraocular Pressure, Follow-up studies, Clinical Sciences, Middle Aged, Optometry and Ophthalmology, Public health systems and services research, Vision Disorders, Visual Fields, Disease Progression, Individualized Medicine, and Sensitivity and Specificity
The authors explore the power and flexibility of using an operations research methodology known as linear programming to support health human resources (HHR) planning. The model takes as input estimates of the future need for healthcare... more
The authors explore the power and flexibility of using an operations research methodology known as linear programming to support health human resources (HHR) planning. The model takes as input estimates of the future need for healthcare providers and, in contrast to simulation, compares all feasible strategies to identify a long-term plan for achieving a balance between supply and demand at the least cost to the system. The approach is illustrated by using it to plan the British Columbia registered nurse (RN) workforce over a 20-year horizon. The authors show how the model can be used for scenario analysis by investigating the impact of decreasing attrition from educational programs, changing RN-to-manager ratios in direct care and exploring how other changes might alter planning recommendations. In addition to HHR policy recommendations, their analysis also points to new research opportunities.
Research Interests:
Few studies have analyzed the Sport Concussion Assessment Tool's (SCAT) utility among athletes whose concussion assessment is challenging. Using a previously published algorithm, we identified Possible and Probable concussions at... more
Few studies have analyzed the Sport Concussion Assessment Tool's (SCAT) utility among athletes whose concussion assessment is challenging. Using a previously published algorithm, we identified Possible and Probable concussions at <6h (n=393 males, n=265 females) and 24-48h (n=323 males, n=236 females) post-injury within collegiate student-athletes and cadets from the Concussion Assessment, Research, and Education (CARE) Consortium. We applied cluster analysis to characterize performance on the Standard Assessment of Concussion (SAC), Balance Error Scoring System (BESS), and the SCAT symptom checklist for these athletes. Among the cluster sets which best separated acute concussions and normal performances, total symptom number raw score and change and Post-traumatic Migraine raw score and change score were the most frequent clustering variables across males and females at <6h and 24-48h. Similarly, total symptom number raw score and change score and Post-traumatic Migraine raw score and change score were most significantly different between clusters for males and females at <6h and 24-48h. Our results suggest that clinicians should focus on total symptom number, Post-traumatic Migraine symptoms, and Cognitive-Fatigue symptoms when assessing Possible and Probable concussions, followed by the SAC and BESS scores.
Research Interests:
Objectives: This study investigated whether emergency department (ED) variables could be used in mathematical models to predict a future surge in ED volume based on recent levels of use of physician capacity. The models may be used to... more
Objectives: This study investigated whether emergency department (ED) variables could be used in mathematical models to predict a future surge in ED volume based on recent levels of use of physician capacity. The models may be used to guide decisions related to on-call staffing in non–crisis-related surges of patient volume. Methods: A retrospective analysis was conducted using information spanning July 2009 through June 2010 from a large urban teaching hospital with a Level I trauma center. A comparison of significance was used to assess the impact of multiple patient-specific variables on the state of the ED. Physician capacity was modeled based on historical physician treatment capacity and productivity. Binary logistic regression analysis was used to determine the probability that the available physician capacity would be sufficient to treat all patients forecasted to arrive in the next time period. The prediction horizons used were 15 minutes, 30 minutes, 1 hour, 2 hours, 4 hou...
Analysts predict impending shortages in the health care workforce, yet wages for health care workers already account for over half of U.S. health expenditures. It is thus increasingly important to adequately plan to meet health workforce... more
Analysts predict impending shortages in the health care workforce, yet wages for health care workers already account for over half of U.S. health expenditures. It is thus increasingly important to adequately plan to meet health workforce demand at reasonable cost. Using infinite linear programming methodology, we propose an infinite-horizon model for health workforce planning in a large health system for a single worker class, e.g. nurses. We give a series of common-sense conditions any system of this kind should satisfy, and use them to prove the optimality of a natural lookahead policy. We then use real-world data to examine how such policies perform in more complex systems with additional detail.
Research Interests:
Research Interests:
Atherosclerotic cardiovascular disease (ASCVD) is among the leading causes of death in the US. While it is known that ASCVD has familial and genetic components, understanding the role of genetic testing in the prevention and treatment of... more
Atherosclerotic cardiovascular disease (ASCVD) is among the leading causes of death in the US. While it is known that ASCVD has familial and genetic components, understanding the role of genetic testing in the prevention and treatment of the cardiovascular disease has been limited. To this end, we develop a simulation framework to estimate the risk for ASCVD events due to clinical and genetic factors. One controllable risk factor for ASCVD events is the cholesterol level of patients. Cholesterol treatment plans are modeled using Markov decision processes. By simulating the health trajectory of patients, we determine the impact of genetic testing in optimal cholesterol treatment plans. As precision medicine and genetic testing become increasingly important, having such a simulation framework becomes essential.
Research Interests:
BACKGROUND Optimizing organ yield (number of organs transplanted per donor) is a potentially modifiable way to increase the number of organs available for transplant. Models to predict the expected deceased donor organ yield have been... more
BACKGROUND Optimizing organ yield (number of organs transplanted per donor) is a potentially modifiable way to increase the number of organs available for transplant. Models to predict the expected deceased donor organ yield have been developed based on ordinary least squares regression and logistic regression. However, alternative modeling methodologies incorporating machine learning may have superior performance compared with conventional approaches. METHODS We evaluated the predictive accuracy of 14 machine learning models for predicting overall organ yield in a cross-validation procedure. The models were parameterized using data from the Organ Procurement and Transplantation Network database from 2000 to 2018. The inclusion criteria for the study were adult deceased donors between 18 and 84 years of age that had at least 1 organ procured for transplantation. RESULTS A total of 89,520 donors met the inclusion criteria. Their mean (standard deviation) age was 44 (15) years, and approximately 58% were male. Our cross-validation analysis showed that a tree-based gradient boosting model outperformed the remaining 13 models. Compared with the currently used prediction models, the gradient boosting model improves prediction accuracy by reducing the mean absolute error between 3 and 11 organs per 100 donors. CONCLUSION Our analysis demonstrated that the gradient boosting methodology had the best performance in predicting overall deceased donor organ yield and can potentially serve as an aid to assess organ procurement organization performance.
Research Interests:
Research Interests:
Research Interests:
Research Interests:
BACKGROUND The Sport Concussion Assessment Tool (SCAT) could be improved by identifying critical subsets that maximize diagnostic accuracy and eliminate low information elements. OBJECTIVE To identify optimal SCAT subsets for acute... more
BACKGROUND The Sport Concussion Assessment Tool (SCAT) could be improved by identifying critical subsets that maximize diagnostic accuracy and eliminate low information elements. OBJECTIVE To identify optimal SCAT subsets for acute concussion assessment. METHODS Using Concussion Assessment, Research, and Education (CARE) Consortium data, we compared student-athletes’ and cadets’ preinjury baselines (n = 2178) with postinjury assessments within 6 h (n = 1456) and 24 to 48 h (n = 2394) by considering demographics, symptoms, Standard Assessment of Concussion (SAC), and Balance Error Scoring System (BESS) scores. We divided data into training/testing (60%/40%) sets. Using training data, we integrated logistic regression with an engineering methodology—mixed integer programming—to optimize models with ≤4, 8, 12, and 16 variables (Opt-k). We also created models including only raw scores (Opt-RS-k) and symptom, SAC, and BESS composite scores (summary scores). We evaluated models using test...
Research Interests:
Research Interests:
ImportanceThe Hospital Readmissions Reduction Program (HRRP) is a Centers for Medicare and Medicaid Services policy that levies hospital reimbursement penalties based on excess readmissions of patients with 4 medical conditions and 3... more
ImportanceThe Hospital Readmissions Reduction Program (HRRP) is a Centers for Medicare and Medicaid Services policy that levies hospital reimbursement penalties based on excess readmissions of patients with 4 medical conditions and 3 surgical procedures. A greater understanding of factors associated with the 3 surgical reimbursement penalties is needed for clinicians in surgical practice.ObjectiveTo investigate the first year of HRRP readmission penalties applied to 2 surgical procedures—elective total hip arthroplasty (THA) and total knee arthroplasty (TKA)—in the context of hospital and patient characteristics.Design, Setting, and ParticipantsFiscal year 2015 HRRP penalization data from Hospital Compare were linked with the American Hospital Association Annual Survey and with the Healthcare Cost and Utilization Project State Inpatient Database for hospitals in the state of Florida. By using a case-control framework, those hospitals were separated based on HRRP penalty severity, as measured with the HRRP THA and TKA excess readmission ratio, and compared according to orthopedic volume as well as hospital-level and patient-level characteristics. The first year of HRRP readmission penalties applied to surgery in Florida Medicare subsection (d) hospitals was examined, identifying 60 663 Medicare patients who underwent elective THA or TKA in 143 Florida hospitals. The data analysis was conducted from February 2016 to January 2017.ExposuresAnnual hospital THA and TKA volume, other hospital-level characteristics, and patient factors used in HRRP risk adjustment.Main Outcomes and MeasuresThe HRRP penalties with HRRP excess readmission ratios were measured, and their association with annual THA and TKA volume, a common measure of surgical quality, was evaluated. The HRRP penalties for surgical care according to hospital and readmitted patient characteristics were then examined.ResultsAmong 143 Florida hospitals, 2991 of 60 663 Medicare patients (4.9%) who underwent THA or TKA were readmitted within 30 days. Annual hospital arthroplasty volume seemed to follow an inverse association with both unadjusted readmission rates (r = −0.16, P = .06) and HRRP risk-adjusted readmission penalties (r = −0.12, P = .14), but these associations were not statistically significant. Other hospital characteristics and readmitted patient characteristics were similar across HRRP orthopedic penalty severity.Conclusions and RelevanceThis study’s findings suggest that higher-volume hospitals had less severe, but not significantly different, rates of readmission and HRRP penalties, without systematic differences across readmitted patients.
Research Interests:
OBJECTIVE To determine if the addition of electronic health record data enables better risk stratification and readmission prediction after radical cystectomy. Despite efforts to reduce their frequency and severity, complications and... more
OBJECTIVE To determine if the addition of electronic health record data enables better risk stratification and readmission prediction after radical cystectomy. Despite efforts to reduce their frequency and severity, complications and readmissions following radical cystectomy remain common. Leveraging readily available, dynamic information such as laboratory results may allow for improved prediction and targeted interventions for patients at risk of readmission. METHODS We used an institutional electronic medical records database to obtain demographic, clinical, and laboratory data for patients undergoing radical cystectomy. We characterized the trajectory of common postoperative laboratory values during the index hospital stay using support vector machine learning techniques. We compared models with and without laboratory results to assess predictive ability for readmission. RESULTS Among 996 patients who underwent radical cystectomy, 259 patients (26%) experienced a readmission within 30 days. During the first week after surgery, median daily values for white blood cell count, urea nitrogen, bicarbonate, and creatinine differentiated readmitted and nonreadmitted patients. Inclusion of laboratory results greatly increased the ability of models to predict 30-day readmissions after cystectomy. CONCLUSIONS Common postoperative laboratory values may have discriminatory power to help identify patients at higher risk of readmission after radical cystectomy. Dynamic sources of physiological data such as laboratory values could enable more accurate identification and targeting of patients at greatest readmission risk after cystectomy. This is a proof of concept study that suggests further exploration of these techniques is warranted.
Research Interests:
Background: Genetic studies suggest that the relative risk reduction (RRR) of statins may increase over time, potentially resulting in much greater long-term benefit if statins are started before cardiovascular (CV) risk is high. Methods:... more
Background: Genetic studies suggest that the relative risk reduction (RRR) of statins may increase over time, potentially resulting in much greater long-term benefit if statins are started before cardiovascular (CV) risk is high. Methods: We used a nationally representative sample of American adults to estimate effects of initiating a statin when 10-year CV risk reaches 5%, 10% or 15%. We examined scenarios in which a statin's initial RRR (30%) gradually doubles over 10 to 30 years of treatment. Results: Initiating a statin when 10-year CV risk is 5% resulted in a mean of 20.1 years on a statin before age 75 (8 years more than starting when CV risk reaches 10%). If a statin's RRR doubles over 20 years, starting when CV risk is 5% would save about 5.1 to 6.1 additional QALYs per 1000 additional treatment years than starting when CV risk is 10%. Most of this additional benefit was accrued by those who reach a 5% risk at a younger age. Due to the prolonged treatment period, how...
Research Interests:
Research Interests:
Research Interests:
Research Interests:
To determine whether a machine learning technique called Kalman filtering (KF) can accurately forecast future values of mean deviation (MD), pattern standard deviation (PSD), and intraocular pressure (IOP) for patients with normal tension... more
To determine whether a machine learning technique called Kalman filtering (KF) can accurately forecast future values of mean deviation (MD), pattern standard deviation (PSD), and intraocular pressure (IOP) for patients with normal tension glaucoma (NTG). Development and testing of a forecasting model for glaucoma progression. We parameterized and validated a Kalman filter (KF-NTG) to forecast MD, PSD, and IOP at 24 months into the future using 263 eyes of 263 Japanese patients with NTG. We determined the proportion of patients with MD forecasts within 0.5, 1.0, and 2.5 decibels (dBs) of the actual values and calculated the root mean squared error (RMSE) for each forecast. We compared KF-NTG to a previously published KF model calibrated using patients with high-tension open-angle glaucoma (KF-HTG) and to 3 conventional forecasting algorithms. The 263 patients with NTG had mean ± SD age of 63.4±10.5 years. KF-NTG forecasted MD values 24 months ahead within 0.5 dBs, 1.0 dBs, 2.5 dBs of...
Research Interests:
The Comprehensive Care for Joint Replacement bundle was created to decrease total knee arthroplasty (TKA) cost. To help accomplish this, there is a focus on reducing TKA readmissions. However, there is a lack of national representative... more
The Comprehensive Care for Joint Replacement bundle was created to decrease total knee arthroplasty (TKA) cost. To help accomplish this, there is a focus on reducing TKA readmissions. However, there is a lack of national representative sample of all-payer hospital admissions to direct strategy, identify risk factors for readmission, and understand actual readmission cost. We used the Nationwide Readmission Database to examine national readmission rates, predictors of readmission, and associated readmission costs for elective TKA procedures. We fit a multivariable logistic regression model to examine factors associated with readmission. Then, we determined mean readmission costs and calculated the readmission cost when distributed across the entire TKA population. We identified 224,465 patients having TKA across all states participating in the Nationwide Readmission Database. The mean unadjusted 30-day TKA readmission rate was 4%. The greatest predictors of readmission were congestiv...
Research Interests:
mortality, length of stay (LOS), and total cost after radical cystectomy with IC vs CD were compared. Chi square test and multivariable logistic regression were used to analyze patient and hospital characteristics. Student’s t-test and... more
mortality, length of stay (LOS), and total cost after radical cystectomy with IC vs CD were compared. Chi square test and multivariable logistic regression were used to analyze patient and hospital characteristics. Student’s t-test and Wilcoxon rank sum test were used to evaluate continuous variables. RESULTS: Between 2001-2012, an estimated 69,049 ICs and 6,991 CDs were performed. The total number of CDs increased from 2001 to 2012 (p < 0.0001), but peaked in 2008 and subsequently declined every year thereafter. Patients of all ages received ICs at a higher rate than CDs (Table 1), including younger age groups (40-59 and 60-69). Males and Caucasians were more likely to have CD compared to females (p<0.001) and African Americans (p<0.0001), respectively. The rate of CDs was highest in the West (12.1%, p<0.001), at urban teaching centers (10.85%, p<0.001), and in large hospitals (9.71%, p<0.001). On logistic regression analysis, when accounting for age, gender, comorbidities, and hospital characteristics, ICs were associated with higher rates of overall (OR 1.06, p1⁄40.0185) and infectious (OR 1.13, p1⁄40.002) complications and in-hospital mortality (OR 1.87, p<0.0001). There was no difference in LOS between the two groups. CONCLUSIONS: The number of CDs performed has declined since 2008. Patients of all ages, including young patients, are more likely to receive IC than CD. Gender, socioeconomic factors, and geographic location may influence diversion type. CDs are associated with comparable rates of complications and in-hospital mortality. Potential causes for declining incidence of continent diversions may include physician reimbursement, length of surgical time, and higher incidence of robotic surgery. These factors should be the subject for further study.
Research Interests:
Research Interests:
The Hospital Readmissions Reduction Program reduces payments to hospitals with excess readmissions for three common medical conditions and recently extended its readmission program to surgical patients. We sought to investigate... more
The Hospital Readmissions Reduction Program reduces payments to hospitals with excess readmissions for three common medical conditions and recently extended its readmission program to surgical patients. We sought to investigate readmission intensity as measured by readmission cost for high-risk surgeries and examine predictors of higher readmission costs. We used the Healthcare Cost and Utilization Project&amp;amp;amp;amp;amp;amp;#39;s State Inpatient Database to perform a retrospective cohort study of patients undergoing major chest (aortic valve replacement, coronary artery bypass grafting, lung resection) and major abdominal (abdominal aortic aneurysm repair [open approach], cystectomy, esophagectomy, pancreatectomy) surgery in 2009 and 2010. We fit a multivariable logistic regression model with generalized estimation equations to examine patient and index admission factors associated with readmission costs. The 30-d readmission rate was 16% for major chest and 22% for major abdominal surgery (P &amp;amp;amp;amp;amp;amp;lt; 0.001). Discharge to a skilled nursing facility was associated with higher readmission costs for both chest (odds ratio [OR]: 1.99; 95% confidence interval [CI]: 1.60-2.48) and abdominal surgeries (OR: 1.86; 95% CI: 1.24-2.78). Comorbidities, length of stay, and receipt of blood or imaging was associated with higher readmission costs for chest surgery patients. Readmission &amp;amp;amp;amp;amp;amp;gt;3 wk after discharge was associated with lower costs among abdominal surgery patients. Readmissions after high-risk surgery are common, affecting about one in six patients. Predictors of higher readmission costs differ among major chest and abdominal surgeries. Better identifying patients susceptible to higher readmission costs may inform future interventions to either reduce the intensity of these readmissions or eliminate them altogether.
Research Interests:
Renal transplantation is a lifesaving intervention for end-stage renal disease. The demand for renal transplantation outweighs the availability of organs; however, up to 20% of recovered kidneys are discarded before transplantation. We... more
Renal transplantation is a lifesaving intervention for end-stage renal disease. The demand for renal transplantation outweighs the availability of organs; however, up to 20% of recovered kidneys are discarded before transplantation. We aimed to better characterize the risk factors for deceased donor kidney discard. We performed a secondary analysis of the Organ Procurement and Transplantation Network database from 2000 to 2012 of all solid organ donors. The cohort was split into training (80%) and validation (20%) subsets. We performed a stepwise logistic regression to develop a multivariate risk prediction model for kidney graft discard and validated the model. The performance of the models was evaluated with respect to calibration, and area under the curve (AUC) of receiver operating characteristic curves. There were no significant baseline differences between the training (n = 57 474) and validation (n = 14 368) cohorts. The multivariate model validation showed very good discriminant function in predicting kidney discard (AUC = 0.84). Predictors of increased discard included age older than 50 years, performance of a kidney biopsy, cytomegalovirus seropositive status, donation after cardiac death, hepatitis B and C seropositive status, cigarette use, diabetes, hypertension, terminal creatinine greater than 1.5 mg/dL and AB blood type. The model outperformed the Kidney Donor Risk Index in predicting discard (P &amp;amp;amp;amp;amp;amp;lt; 0.001). Subgroup analysis of expanded criteria donor kidneys demonstrated good discrimination with an AUC of 0.70. We have characterized several important predictors of deceased donor kidney discard. Better understanding of factors that lead to increased deceased donor kidney discard can allow for targeted interventions to reduce discard.
Research Interests: Kidney transplantation, Adolescent, Medicine, Multivariate Analysis, Humans, and 15 moreFemale, Male, Registries, Aged, Middle Aged, Adult, Odds ratio, Risk Assessment, Logistic Models, Area Under Curve, Predictive value of tests, Postoperative Complications, Decision Support Techniques, Cause of death, and Medical and Health Sciences
Research Interests:
Research Interests:
RATIONALE High mortality and resource use burden are associated with hospitalization of critically ill children transferred from level II pediatric intensive care units (PICUs) to level I PICUs for escalated care. Guidelines urge transfer... more
RATIONALE High mortality and resource use burden are associated with hospitalization of critically ill children transferred from level II pediatric intensive care units (PICUs) to level I PICUs for escalated care. Guidelines urge transfer of the most severely ill children to level I PICUs without specification of either the criteria or the best timing of transfer to achieve good outcomes. OBJECTIVES To identify factors associated with transfer, develop a modeling framework that uses those factors to determine thresholds to guide transfer decisions, and test these thresholds against actual patient transfer data to determine if delay in transfer could be reduced. METHODS A multistep approach was adopted, with initial identification of factors associated with transfer status using data from a prior case-control study conducted with children with respiratory failure admitted to six level II PICUs between January 1, 1997, and December 31, 2007. To identify when to transfer a patient, thresholds for transfer were created using generalized estimating equations and discrete event simulation. The transfer policies were then tested against actual transfer data. MEASUREMENTS AND MAIN RESULTS Multivariate logistic regression revealed that the absolute difference of a patient's pediatric logistic organ dysfunction score from the admission value, high-frequency oscillatory ventilation use, antibiotic use, and blood transfusions were all significantly associated with transfer status. The resulting threshold policies led to average transfer delay reduction ranging from 0.5 to 2.3 days in the testing dataset. CONCLUSIONS Current transfer guidelines are devoid of criteria to identify critically ill children who might benefit from transfer and when the best time to transfer might be. In this study, we used innovative methods to create thresholds of transfer that might reduce delay in transfer.
Research Interests:
Radical cystectomy has one of the highest readmission rates across all surgical procedures at approximately 25%. Our objective is to develop a mathematical model to optimize outpatient follow-up regimens for radical cystectomy. We used... more
Radical cystectomy has one of the highest readmission rates across all surgical procedures at approximately 25%. Our objective is to develop a mathematical model to optimize outpatient follow-up regimens for radical cystectomy. We used delay-time analysis, a systems engineering approach, to maximize the probability of detecting patients susceptible to readmission through office visits and telephone calls. Our data source includes patients readmitted after radical cystectomy from the Healthcare Cost and Utilization Project's State Inpatient Database in 2009 and 2010 as well as from our institutional bladder cancer database from 2007 to 2011. We measured the time interval from hospital discharge to the point when a patient first exhibits concerning symptoms. Our primary endpoint is 30-day hospital readmission. Our model optimized the timing and sequence of follow-up care after radical cystectomy. The timing of office visits and telephone calls is more important in detecting a pati...
Research Interests:
Research Interests:
This article provides an introduction to the use of linear programming in strategic health human resource planning. We focus on a multiperiod linear programming approach that compares all feasible human resource strategies to identify... more
This article provides an introduction to the use of linear programming in strategic health human resource planning. We focus on a multiperiod linear programming approach that compares all feasible human resource strategies to identify education, recruitment, and promotion plans that achieve a supply–demand balance at the least cost to the system. The approach applies to a wide range of healthcare provider groups contingent on data availability (potential sources include regulatory, educational, employer, government and administrative databases, and research publications). Its ease of use and strong mathematical foundation make this model ideal for “What-if?” analysis and assessments of sensitivity of decisions to assumptions and data accuracy. Keywords: health workforce planning; linear programming; large healthcare systems; HHR planning; attrition rate
Research Interests:
Purpose: We investigated how using filtered longitudinal data as input for logistic regression to predict glaucoma progression affects the classification ability of the logistic regression function. Methods: A Kalman filter was developed... more
Purpose: We investigated how using filtered longitudinal data as input for logistic regression to predict glaucoma progression affects the classification ability of the logistic regression function. Methods: A Kalman filter was developed to reduce the process and measurement noise present in longitudinal data from the Collaborative Initial Glaucoma Treatment Study (CIGTS), a randomized clinical trial of patients with early to moderate open angle glaucoma (OAG). These filtered repeated measures estimates were then used as data input for logistic regression via generalized estimating equations in order to predict OAG progression in patients. Analysis of the receiver operating characteristic (ROC) curve was used to compare this Kalman filter-based model against the standard methodology of using raw observations from the clinical trial as data input for logistic regression. Results: The Kalman filter-based model resulted in higher specificity and sensitivity compared to the standard raw...
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
To assess the current pediatric nurse practitioner (PNP) workforce and to investigate the impact of potential policy changes to address forecasted shortages. We modeled the admission of students into nursing bachelor's programs and... more
To assess the current pediatric nurse practitioner (PNP) workforce and to investigate the impact of potential policy changes to address forecasted shortages. We modeled the admission of students into nursing bachelor's programs and followed them through advanced clinical programs. Prediction models were combined with optimal decision-making to determine best-case scenario admission levels. We computed 2 measures: (1) the absolute shortage and (2) the expected number of years until the PNP workforce will be able to fully satisfy PNP demand (ie, self-sufficiency). There is a forecasted shortage of PNPs in the workforce over the next 13 years. Under the best-case scenario, it would take at least 13 years for the workforce to fully satisfy demand. Our analysis of potential policy changes revealed that increasing the specialization rate for PNPs by 4% would decrease the number of years required until there are enough PNPs from 13 years to 5 years. Increasing the certification examina...
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Hospital readmissions after radical cystectomy vary with respect to intensity in terms of impact on patients and health care systems. Therefore, we conducted a population based study to examine factors associated with increasing... more
Hospital readmissions after radical cystectomy vary with respect to intensity in terms of impact on patients and health care systems. Therefore, we conducted a population based study to examine factors associated with increasing readmission intensity after radical cystectomy for bladder cancer. Using SEER (Surveillance, Epidemiology, and End Results)-Medicare data we identified 1,782 patients who underwent radical cystectomy from 2003 to 2009. We defined readmission intensity in terms of length of stay (days) divided into quartiles of less than 3 (lowest), 3 to 4, 5 to 7 and more than 7 (highest). We used logistic regression to examine factors associated with readmission intensity. More than half of the patients with the highest intensity readmissions were readmitted within the first week and 77% were readmitted within 2 weeks of discharge. Patients with the highest intensity readmissions were similar in age, gender, race, socioeconomic status, pathological stage, comorbidity, neoadjuvant chemotherapy use and urinary diversion type compared to patients with the lowest intensity readmissions. After multivariable adjustment, complications during the index cystectomy admission (p &amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;lt;0.001), readmission week (p=0.04), and the interaction between index length of stay and discharge to a skilled nursing facility (p=0.04) were associated with the highest readmission intensity. Readmission intensity differs widely after discharge following radical cystectomy. As postoperative efforts to minimize the readmission burden increase, a better understanding of the factors that contribute to the highest intensity readmissions will help direct limited resources (eg telephone calls, office visits) toward high yield areas.
Research Interests:
Research Interests:
We investigate the problem faced by a healthcare system wishing to allocate its constrained screening resources across a population at risk for developing a disease. A... more
We investigate the problem faced by a healthcare system wishing to allocate its constrained screening resources across a population at risk for developing a disease. A patient&amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;#39;s risk of developing the disease depends on his/her biomedical dynamics. However, knowledge of these dynamics must be learned by the system over time. Three classes of reinforcement learning policies are designed to address this problem of simultaneously gathering and utilizing information across multiple patients. We investigate a case study based upon the screening for Hepatocellular Carcinoma (HCC), and optimize each of the three classes of policies using the indifference zone method. A simulation is built to gauge the performance of these policies, and their performance is compared to current practice. We then demonstrate how the benefits of learning-based screening policies differ across various levels of resource scarcity and provide metrics of policy performance.