Estimating the Relationship Between the Symptom-Free Waiting Period and Injury Rates After Return-to-Play from Concussion: A Simulation Analysis Using CARE Consortium Data.

BACKGROUND: A key component of return-to-play (RTP) from sport-related concussion is the symptom-free waiting period (SFWP), i.e., the period during which athletes must remain symptom-free before permitting RTP. Yet, the exact relationship between SFWP and post-RTP injury rates is unclear. OBJECTIVE: We design computational simulations to estimate the relationship between the SFWP and rates of repeat concussion and non-concussion time-loss injury up to 30 days post-RTP for male and female collegiate athletes across 13 sports. METHODS: We leverage N = 735 female and N = 1,094 male post-injury trajectories from the National Collegiate Athletic Association-Department of Defense Concussion Assessment, Research, and Education Consortium. RESULTS: With a 6-day SFWP, the mean [95% CI] rate of repeat concussion per 1,000 simulations was greatest in ice hockey for females (20.31, [20.16, 20.46]) and American football for males (24.16, [24.05, 24.28]). Non-concussion time-loss injury rates were greatest in field hockey for females (153.66, [152.59, 154.74]) and wrestling for males (247.34, [246.20, 248.48]). Increasing to a 13-day SFWP, ice hockey for females (18.88, [18.79, 18.98]) and American football for males (23.16, [23.09, 24.22]) exhibit the greatest decrease in repeat concussion rates across all sports within their respective sexes. Field hockey for females (143.24, [142.53, 143.94]) and wrestling for males (237.73, [236.67, 237.90]) exhibit the greatest decrease in non-concussion time-loss injury rates. Males receive marginally smaller reductions in injury rates for increased SFWP compared to females (OR = 1.003, p ≤ 0.002). CONCLUSION: Longer SFWPs lead to greater reductions in post-RTP injury rates for athletes in higher risk sports. Moreover, SFWPs should be tailored to sport-specific post-RTP injury risks.

Monitoring policy in the context of preventive treatment of cardiovascular disease.

Preventing chronic diseases is an essential aspect of medical care. To prevent chronic diseases, physicians focus on monitoring their risk factors and prescribing the necessary medication. The optimal monitoring policy depends on the patient's risk factors and demographics. Monitoring too frequently may be unnecessary and costly; on the other hand, monitoring the patient infrequently means the patient may forgo needed treatment and experience adverse events related to the disease. We propose a finite horizon and finite-state Markov decision process to define monitoring policies. To build our Markov decision process, we estimate stochastic models based on longitudinal observational data from electronic health records for a large cohort of patients seen in the national U.S. Veterans Affairs health system. We use our model to study policies for whether or when to assess the need for cholesterol-lowering medications. We further use our model to investigate the role of gender and race on optimal monitoring policies.

Sensitivity and Specificity of the ImPACT Neurocognitive Test in Collegiate Athletes and US Military Service Academy Cadets with ADHD and/or LD: Findings from the NCAA-DoD CARE Consortium.

BACKGROUND AND OBJECTIVE: Computer-based neurocognitive tests are widely used in sport-related concussion management, but the performance of these tests is not well understood in the participant population with attention-deficit/hyperactivity disorder (ADHD) and/or learning disorder (LD). This research estimates the sensitivity and specificity performance of the Immediate Post-Concussion Assessment and Cognitive Testing (ImPACT) computer-based neurocognitive test in identifying concussion in this population. METHODS: Study participants consisted of collegiate university athletes and military service academy cadets from the National Collegiate Athletic Association-Department of Defense CARE Consortium who completed the ImPACT test between 2014 and 2021. Participants who self-identified as belonging to one of the subgroups of interest (ADHD with or without LD [ADHD:LD+/-], LD with or without ADHD [LD:ADHD+/-], ADHD and/or LD [ADHD a/o LD]) and completed a baseline (1874 ADHD:LD+/-, 779 LD:ADHD+/-, 2338 ADHD a/o LD) or 24-48 h post-concussion (175 ADHD:LD+/-, 77 LD:ADHD+/-, 216 ADHD a/o LD) ImPACT assessment were included. Sensitivity and specificity were calculated using a normative data method and three machine learning classification methods: logistic regression, classification and regression tree, and random forest. RESULTS: Using the four methods, participants with ADHD:LD+/- had sensitivities that ranged from 0.474 to 0.697, and specificities that ranged from 0.538 to 0.686. Participants with LD:ADHD+/- had sensitivities that ranged from 0.455 to 0.688, and specificities that ranged from 0.456 to 0.588. For participants with ADHD a/o LD, sensitivities ranged from 0.542 to 0.755, and specificities ranged from 0.451 to 0.724. CONCLUSIONS: For all subgroups and analytical methods, the results illustrate sensitivity and specificity values below typically accepted levels indicative of clinical utility. These findings support that using ImPACT alone may be insufficient to inform concussion diagnoses and encourages the use of a multi-dimensional concussion assessment.

Augmenting Kalman Filter Machine Learning Models with Data from OCT to Predict Future Visual Field Loss: An Analysis Using Data from the African Descent and Glaucoma Evaluation Study and the Diagnostic Innovation in Glaucoma Study.

Purpose: To assess whether the predictive accuracy of machine learning algorithms using Kalman filtering for forecasting future values of global indices on perimetry can be enhanced by adding global retinal nerve fiber layer (RNFL) data and whether model performance is influenced by the racial composition of the training and testing sets. Design: Retrospective, longitudinal cohort study. Participants: Patients with open-angle glaucoma (OAG) or glaucoma suspects enrolled in the African Descent and Glaucoma Evaluation Study or Diagnostic Innovation in Glaucoma Study. Methods: We developed a Kalman filter (KF) with tonometry and perimetry data (KF-TP) and another KF with tonometry, perimetry, and global RNFL data (KF-TPO), comparing these models with one another and with 2 linear regression (LR) models for predicting mean deviation (MD) and pattern standard deviation values 36 months into the future for patients with OAG and glaucoma suspects. We also compared KF model performance when trained on individuals of European and African descent and tested on patients of the same versus the other race. Main Outcome Measures: Predictive accuracy (percentage of MD values forecasted within the 95% repeatability interval) differences among the models. Results: Among 362 eligible patients, the mean ± standard deviation age at baseline was 71.3 ± 10.4 years; 196 patients (54.1%) were women; 202 patients (55.8%) were of European descent, and 139 (38.4%) were of African descent. Among patients with OAG (n = 296), the predictive accuracy for 36 months in the future was higher for the KF models (73.5% for KF-TP, 71.2% for KF-TPO) than for the LR models (57.5%, 58.0%). Predictive accuracy did not differ significantly between KF-TP and KF-TPO (P = 0.20). If the races of the training and testing set patients were aligned (versus nonaligned), the mean absolute prediction error of future MD improved 0.39 dB for KF-TP and 0.48 dB for KF-TPO. Conclusions: Adding global RNFL data to existing KFs minimally improved their predictive accuracy. Although KFs attained better predictive accuracy when the races of the training and testing sets were aligned, these improvements were modest. These findings will help to guide implementation of KFs in clinical practice.

An Assessment of Ineligible Donor Use in Solid Organ Transplant.

BACKGROUND: In the United States, the demand for organ transplants far outpaces available organs. The use of Organ Procurement and Transplantation Network-defined ineligible donors is an immediate method for increasing donations. However, the use of ineligible donors varies across organ procurement organizations (OPOs), and its association with recipient survival remains unclear. METHODS: We evaluated ineligible donor use from 2008 to 2020 by OPO and its association with graft and recipient survival across demographics. RESULTS: In this study of 297 223 organ donations, 42 184 (14%) did not meet eligibility criteria as defined by the Organ Procurement and Transplantation Network. Log-rank tests on Kaplan-Meier curves suggested differences in graft and patient survival between eligible and ineligible recipients for kidney and liver transplants ( P ≤ 0.01 for all). Recipients of ineligible kidney and liver donations saw a 2.20% and 9.38% decrease in 10-y graft survival probability, respectively. There were no statistically significant graft and patient survival differences for recipients of ineligible heart, lung, and pancreas donations. Multivariate proportional hazard models showed eligibility was associated with kidney, liver, and lung graft survival ( P ≤ 0.02 for all). However, if OPOs increased ineligible donor use to meet the current 75th percentile use rate, there could be as many as 1000 transplants and 6291 life-years gained annually. CONCLUSIONS: Ineligible donor use can provide significant survival benefit for patients who would otherwise never receive a transplant. Methods to reduce regional heterogeneity in ineligible donor use could increase the number of transplants and improve outcomes for waiting patients.

Developing Insights for Possible and Probable Acute Concussions Using Cluster Analysis.

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 <6 h (n = 393 males, n = 265 females) and 24-48 h (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 that 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 <6 h and 24-48 h. 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 <6 h and 24-48 h. 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.

The Magnitude of the Health and Economic Impact of Increased Organ Donation on Patients With End-Stage Renal Disease.

Objectives. There are several approaches such as presumed consent and compensation for deceased donor organs that could reduce the gap between supply and demand for kidneys. Our objective is to evaluate the magnitude of the economic impact of policies to increase deceased donor organ donation in the United States. Methods. We built a Markov model and simulate an open cohort of end-stage renal disease patients awaiting kidney transplantation in the United States over 20 years. Model inputs were derived from the United States Renal Data System and published literature. We evaluate the magnitude of the health and economic impact of policies to increase deceased donor kidney donation in the United States. Results. Increasing deceased kidney donation by 5% would save $4.7 billion, and gain 30,870 quality-adjusted life years over the lifetime of an open cohort of patients on dialysis on the waitlist for kidney transplantation. With an increase in donations of 25%, the cost saved was $21 billion, and 145,136 quality-adjusted life years were gained. Policies increasing deceased kidney donation by 5% could pay donor estates $8000 or incur a onetime cost of up to $4 billion and still be cost-saving. Conclusions. Increasing deceased kidney donation could significantly impact national spending and health for end-stage renal disease patients.

A machine learning approach for the prediction of overall deceased donor organ yield.

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.

A Prognostic Model for Predicting One-Month Outcomes among Emergency Department Patients with Mild Traumatic Brain Injury and a Presenting Glasgow Coma Scale of Fifteen.

The lack of well-performing prognostic models for early prognostication of outcomes remains a major barrier to improving the clinical care of patients with mild traumatic brain injury (mTBI). We aimed to derive a prognostic model for predicting incomplete recovery at 1-month in emergency department (ED) patients with mTBI and a presenting Glasgow Coma Scale (GCS) score of 15 who were enrolled in the HeadSMART (Head Injury Serum Markers for Assessing Response to Trauma) study. The derivation cohort included 355 participants with complete baseline (day-of-injury) and follow-up data. The primary outcome measure was the Glasgow Outcome Scale Extended (GOSE) at 1-month and incomplete recovery was defined as a GOSE <8. At 1-month post-injury, incomplete recovery was present in 58% (n = 205) of participants. The final multi-variable logistic regression model included six variables: age in years (odds ratio [OR] = 0.98; 95% confidence interval [CI]: 0.97-1.00), positive head CT (OR = 4.42; 95% CI: 2.21-9.33), history of depression (OR = 2.59; 95% CI: 1.47-4.69), and self-report of moderate or severe headache (OR = 2.49; 95% CI: 1.49-4.18), difficulty concentrating (OR = 3.17; 95% CI: 1.53-7.04), and photophobia (OR = 4.17; 95% CI: 2.08-8.92) on the day-of-injury. The model was validated internally using bootstrap resampling (1000 resamples), which revealed a mean over-optimism value of 0.01 and an optimism-corrected area under the curve (AUC) of 0.79 (95% CI: 0.75-0.85). A prognostic model for predicting incomplete recovery among ED patients with mTBI and a presenting GCS of 15 using easily obtainable clinical and demographic variables has acceptable discriminative accuracy. External validation of this model is warranted.

Predicting rapid progression phases in glaucoma using a soft voting ensemble classifier exploiting Kalman filtering.

In managing patients with chronic diseases, such as open angle glaucoma (OAG), the case treated in this paper, medical tests capture the disease phase (e.g. regression, stability, progression, etc.) the patient is currently in. When medical tests have low residual variability (e.g. empirical difference between the patient's true and recorded value is small) they can effectively, without the use of sophisticated methods, identify the patient's current disease phase; however, when medical tests have moderate to high residual variability this may not be the case. This paper presents a framework for handling the latter case. The framework presented integrates the outputs of interacting multiple model Kalman filtering with supervised learning classification. The purpose of this integration is to estimate the true values of patients' disease metrics by allowing for rapid and non-rapid phases; and dynamically adapting to changes in these values over time. We apply our framework to classifying whether a patient with OAG will experience rapid progression over the next two or three years from the time of classification. The performance (AUC) of our model increased by approximately 7% (increased from 0.752 to 0.819) when the Kalman filtering results were incorporated as additional features in the supervised learning model. These results suggest the combination of filters and statistical learning methods in clinical health has significant benefits. Although this paper applies our methodology to OAG, the methodology developed is applicable to other chronic conditions.

Optimal cholesterol treatment plans and genetic testing strategies for cardiovascular diseases.

Atherosclerotic cardiovascular disease (ASCVD) is among the leading causes of death in the US. Although research has shown that ASCVD has genetic elements, the understanding of how genetic testing influences its prevention and treatment has been limited. To this end, we model the health trajectory of patients stochastically and determine treatment and testing decisions simultaneously. Since the cholesterol level of patients is one controllable risk factor for ASCVD events, we model cholesterol treatment plans as Markov decision processes. We determine whether and when patients should receive a genetic test using value of information analysis. By simulating the health trajectory of over 64 million adult patients, we find that 6.73 million patients undergo genetic testing. The optimal treatment plans informed with clinical and genetic information save 5,487 more quality-adjusted life-years while costing $1.18 billion less than the optimal treatment plans informed with clinical information only. As precision medicine becomes increasingly important, understanding the impact of genetic information becomes essential.

Sensitivity and Specificity of Computer-Based Neurocognitive Tests in Sport-Related Concussion: Findings from the NCAA-DoD CARE Consortium.

BACKGROUND: To optimally care for concussed individuals, a multi-dimensional approach is critical and a key component of this assessment in the athletic environment is computer-based neurocognitive testing. However, there continues to be concerns about the reliability and validity of these testing tools. The purpose of this study was to determine the sensitivity and specificity of three common computer-based neurocognitive tests (Immediate Post-Concussion Assessment and Cognitive Testing [ImPACT], CNS Vital Signs, and CogState Computerized Assessment Tool [CCAT]), to provide guidance on their clinical utility. METHODS: This study analyzed assessments from a cohort of collegiate athletes and non-varsity cadets from the NCAA-DoD CARE Consortium. The data were collected from 2014-2018. Study participants were divided into two testing groups [concussed, n = 1414 (baseline/24-48 h) and healthy, n = 8305 (baseline/baseline)]. For each test type, change scores were calculated for the components of interest. Then, the Normative Change method, which used normative data published in a similar cohort, and the Reliable Change Index (RCI) method were used to determine if the change scores were significant. RESULTS: Using the Normative Change method, ImPACT performed best with an 87.5%-confidence interval and 1 number of components failed (NCF; sensitivity = 0.583, specificity = 0.625, F1 = 0.308). CNS Vital Signs performed best with a 90%-confidence interval and 1 NCF (sensitivity = 0.587, specificity = 0.532, F1 = 0.314). CCAT performed best when using a 75%-confidence interval and 2 NCF (sensitivity = 0.513, specificity = 0.715, F1 = 0.290). When using the RCI method, ImPACT performed best with an 87.5%-confidence interval and 1 NCF (sensitivity = 0.626, specificity = 0.559, F1 = 0.297). CONCLUSION: When considering all three computer-based neurocognitive tests, the overall low sensitivity and specificity results provide additional evidence for the use of a multi-dimensional assessment for concussion diagnosis, including symptom evaluation, postural control assessment, neuropsychological status, and other functional assessments.

Comparing Perimetric Loss at Different Target Intraocular Pressures for Patients with High-Tension and Normal-Tension Glaucoma.

PURPOSE: To compare forecasted changes in mean deviation (MD) for patients with normal-tension glaucoma (NTG) and high-tension open-angle glaucoma (HTG) at different target intraocular pressures (IOPs) using Kalman filtering, a machine learning technique. DESIGN: Retrospective cohort study. PARTICIPANTS: From the Collaborative Initial Glaucoma Treatment Study or Advanced Glaucoma Intervention Study, 496 patients with HTG; from Japan, 262 patients with NTG. METHODS: Using the first 5 sets of tonometry and perimetry measurements, each patient was classified as a fast progressor, slow progressor, or nonprogressor. Using Kalman filtering, personalized forecasts of MD changes over 2.5 years' follow-up were generated for fast and slow progressors with HTG and NTG with IOPs maintained at hypothetical IOP targets of 9 to 21 mmHg. Future MD loss with different percentage IOP reductions from baseline (0%-50%) were also assessed for the groups. MAIN OUTCOME MEASURES: Mean forecasted MD change at different target IOPs. RESULTS: The mean (± standard deviation) patient age was 63.5 ± 10.5 years for NTG and 66.5 ± 10.9 years for HTG. Over the 2.5-year follow-up, at target IOPs of 9, 15, and 21 mmHg, respectively, the mean forecasted MD losses for fast progressors with NTG were 2.3 ± 0.2, 4.0 ± 0.2, and 5.7 ± 0.2 dB; for slow progressors with NTG, losses were 0.63 ± 0.02, 1.02 ± 0.03, and 1.49 ± 0.07 dB; for fast progressors with HTG, losses were 1.8 ± 0.1, 3.4 ± 0.1, and 5.1 ± 0.1 dB; and for slow progressors with HTG, losses were 0.55 ± 0.06, 1.04 ± 0.08, and 1.59 ± 0.10 dB. Fast progressors with NTG had greater MD decline than fast progressors with HTG at each target IOP (P ≤ 0.007 for all). The MD decline for slow progressors with HTG and NTG were similar (P ≥ 0.24 for all target IOPs). Fast progressors with HTG had greater MD loss than those with NTG with 0%-10% IOP reduction since baseline (P ≤ 0.01 for all), but not 25% (P = 0.07) or 50% (P = 0.76) reduction since baseline. CONCLUSIONS: Machine learning algorithms using Kalman filtering techniques demonstrate promise at forecasting future MD values at different target IOPs for patients with NTG and HTG.

Assessment of National Organ Donation Rates and Organ Procurement Organization Metrics.

Importance: Organ transplant is a life-saving procedure for patients with end-stage organ failure. In the US, organ procurement organizations (OPOs) are responsible for the evaluation and procurement of organs from donors who have died; however, there is controversy regarding what measures should be used to evaluate their performance. Objective: To evaluate OPO performance metrics using combined mortality and donation data and quantify the associations of population demographics with donation metrics. Design, Setting, and Participants: This national cohort study includes data from the US organ transplantation system from January 2008 through December 2017. All individuals who died within the US, as reported by the National Death index, were included. Exposures: Death, organ donation, and donation eligibility. Main Outcomes and Measures: Evaluation of the variation in donation metrics and the use of ineligible donors by OPO and demographic subgroup. Results: This study included 17 501 742 deaths and 75 769 deceased organ donors (45 040 men [59.4%]; 51 908 White individuals [68.5%]). Of these donors, 15 857 (20.9%) were not eligible, as defined by the OPOs. The median donation metrics by OPO were 0.004 (range, 0.002-0.012) donors per death, 0.89 (range, 0.68-1.30) donors per eligible death, and 0.72 (range, 0.57-0.86) eligible donors per eligible death. The OPOs in the upper quartile of the overall eligible donors per eligible death metric were in the upper quartile of annual rankings on 90 of 140 occasions (64.3%). There was little overlap in top-performing OPOs between metrics; an OPO in the upper quartile for 1 metric was also in the upper quartile for the other metrics on 37 of 570 occasions (6.5% of the time). The median donor eligibility rate, defined as the number of eligible donors per donor, was 0.79 (range, 0.61-0.95) across OPOs. Age (eg, 65 to 84 years, coefficient, -0.55 [SE, 0.03]; P < .001; vs those aged 18 to 34 years), sex (male individuals, -0.09 [SE, 0.02]; P < .001; vs female individuals), race (eg, Black individuals, 0.35 [SE, 0.02]; P < .001; vs White individuals), cause of death (eg, central nervous system tumor, 0.48 [SE, 0.08]; P < .001; vs anoxia), year (eg, 2016-2017: -0.10 [SE, 0.03]; P < .001; vs 2008-2009), and OPO were associated with the use of ineligible donors; OPO was a significant factor associated with performance in all metrics (χ256, 500.5; P < .001; coefficient range across individual OPOs, -0.15 [SE, 0.09] to 0.75 [SE, 0.09]), even after accounting for population differences. Female and non-White individuals were significantly less likely to be used as ineligible donors. Conclusions and Relevance: We demonstrate significant variability in OPO performance rankings, depending on which donation metric is used. There were significant differences in OPO performance, even after accounting for differences in potential donor populations. Our data suggest significant variation in use of ineligible donors among OPOs, a source for increased donors. The performance of OPOs should be evaluated using a range of donation metrics.

Comparison of readmission and early revision rates as a quality metric in total knee arthroplasty using the Nationwide Readmission Database.

BACKGROUND: After release of the Comprehensive Care for Joint Replacement bundle, there has been increased emphasis on reducing readmission rates for total knee arthroplasty (TKA). The potential for a separate, clinically-relevant metric, TKA revision rates within a year following surgery, has not been fully explored. Based on this, we compared rates and payments for TKA readmission and revision procedures as metrics for improving quality and cost. METHODS: We utilized the 2013 Nationwide Readmission Database (NRD) to examine national readmission and revision rates, the reasons for revision procedures, and associated costs for elective TKA procedures. As data are not linked across years, we examined revision rates for TKA completed in the month of January by capturing revision procedures in the subsequent following 11-month period to approximate a 1-year revision rate. Diagnosis and procedure codes for revision procedures were collected. Average readmission and revision procedure costs were then calculated, and the cost distributed across the entire TKA population. RESULTS: We identified 20,851 patients having TKA surgery. The mean unadjusted 30- and 90-day TKA readmission rates were 3.4% and 5.8%, respectively. In contrast, the mean unadjusted 3-month and approximate 1-year reoperation rates were 1.0% and 1.6%, respectively. The most common cause for revision was periprosthetic joint infection, which accounting for 62% of all reported revision procedures. The mean payment for 90-day readmission was roughly half ($10,589±$11,084) of the mean inpatient payment for single reoperation procedure at 90 days ($20,222±$17,799). Importantly, nearly half (46%) of all 90-day readmissions were associated with a reoperation event within the first year. CONCLUSIONS: Readmission following TKA is associated with a 1-year reoperation in approximately half of patients. These reoperations represent a significant patient burden and have a higher per episode cost. Early reoperation may represent a more clinically relevant target for quality improvement and cost containment.

Introduction to Metamodeling for Reducing Computational Burden of Advanced Analyses with Health Economic Models: A Structured Overview of Metamodeling Methods in a 6-Step Application Process.

Metamodels can be used to reduce the computational burden associated with computationally demanding analyses of simulation models, although applications within health economics are still scarce. Besides a lack of awareness of their potential within health economics, the absence of guidance on the conceivably complex and time-consuming process of developing and validating metamodels may contribute to their limited uptake. To address these issues, this article introduces metamodeling to the wider health economic audience and presents a process for applying metamodeling in this context, including suitable methods and directions for their selection and use. General (i.e., non-health economic specific) metamodeling literature, clinical prediction modeling literature, and a previously published literature review were exploited to consolidate a process and to identify candidate metamodeling methods. Methods were considered applicable to health economics if they are able to account for mixed (i.e., continuous and discrete) input parameters and continuous outcomes. Six steps were identified as relevant for applying metamodeling methods within health economics: 1) the identification of a suitable metamodeling technique, 2) simulation of data sets according to a design of experiments, 3) fitting of the metamodel, 4) assessment of metamodel performance, 5) conducting the required analysis using the metamodel, and 6) verification of the results. Different methods are discussed to support each step, including their characteristics, directions for use, key references, and relevant R and Python packages. To address challenges regarding metamodeling methods selection, a first guide was developed toward using metamodels to reduce the computational burden of analyses of health economic models. This guidance may increase applications of metamodeling in health economics, enabling increased use of state-of-the-art analyses (e.g., value of information analysis) with computationally burdensome simulation models.

Optimizing Components of the Sport Concussion Assessment Tool for Acute Concussion Assessment.

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 testing data. RESULTS: At <6 h and 24 to 48 h, most Opt-k and Opt-RS-k models included the following symptoms: do not feel right, headache, dizziness, sensitivity to noise, and whether physical or mental activity worsens symptoms. Opt-k models included SAC concentration and delayed recall change scores. Opt-k models had lower Brier scores (BS) and greater area under the curve (AUC) (<6 h: BS = 0.072-0.089, AUC = 0.95-0.96; 24-48 h: BS = 0.085-0.093, AUC = 0.94-0.95) than Opt-RS-k (<6 h: BS = 0.082-0.087, AUC = 0.93-0.95; 24-48 h: BS = 0.095-0.099, AUC = 0.92-0.93) and summary score models (<6 h: BS = 0.14, AUC = 0.89; 24-48 h: BS = 0.15, AUC = 0.87). CONCLUSION: We identified SCAT subsets that accurately assess acute concussion and improve administration time over the complete battery, highlighting the importance of eliminating "noisy" elements. These findings can direct clinicians to the SCAT components that are most sensitive to acute concussion.

Reframing Financial Incentives Around Reducing Readmission After Radical Cystectomy.

OBJECTIVE: To better understand the financial implications of readmission after radical cystectomy, an expensive surgery coupled with a high readmission rate. Currently, whether hospitals benefit financially from readmissions after radical cystectomy remains unclear, and potentially obscures incentives to invest in readmission reduction efforts. MATERIALS AND METHODS: Using a 20% sample of national Medicare beneficiaries, we identified 3544 patients undergoing radical cystectomy from January 2010 to November 2014. We compared price-standardized Medicare payments for index admissions and readmissions after surgery. We also examined the variable financial impact of length of stay and the proportion of Medicare payments coming from readmissions based on overall readmission rate. RESULTS: Medicare patients readmitted after cystectomy had higher index hospitalization payments ($19,164 readmitted vs $18,146 non-readmitted, P = .03) and an average readmission payment of $7356. Adjusted average Medicare readmission payments and length of stay varied significantly across hospitals, ranging from $2854 to $15,605, and 2.0 to 17.1 days, respectively (both P <.01), with longer length of stay associated with increased payments. After hospitals were divided into quartiles based on overall readmission rates, the percent of payments coming from readmissions ranged from 5% to 13%. CONCLUSION: Readmissions following radical cystectomy were associated with increased Medicare payments for the index hospitalization, and the readmission payment, potentially limiting incentives for readmission reduction programs. Our findings highlight opportunities to reframe efforts to support patients, caregivers, and providers through improving the discharge and readmission processes to create a patient-centered experience, rather than for fear of financial penalties.

Dynamic readmission prediction using routine postoperative laboratory results after radical cystectomy.

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.

Accuracy of Kalman Filtering in Forecasting Visual Field and Intraocular Pressure Trajectory in Patients With Ocular Hypertension.

Importance: Techniques that properly identify patients in whom ocular hypertension (OHTN) is likely to progress to open-angle glaucoma can assist clinicians with deciding on the frequency of monitoring and the potential benefit of early treatment. Objective: To test whether Kalman filtering (KF), a machine learning technique, can accurately forecast mean deviation (MD), pattern standard deviation, and intraocular pressure values 5 years into the future for patients with OHTN. Design, Setting, and Participants: This cohort study was a secondary analysis of data from patients with OHTN from the Ocular Hypertension Treatment Study, performed between February 1994 and March 2009. Patients underwent tonometry and perimetry every 6 months for up to 15 years. A KF (KF-OHTN) model was trained, validated, and tested to assess how well it could forecast MD, pattern standard deviation, and intraocular pressure at up to 5 years, and the forecasts were compared with results from the actual trial. Kalman filtering for OHTN was compared with a previously developed KF for patients with high-tension glaucoma (KF-HTG) and 3 traditional forecasting algorithms. Statistical analysis for the present study was performed between May 2018 and May 2019. Main Outcomes and Measures: Prediction error and root-mean-square error at 12, 24, 36, 48, and 60 months for MD, pattern standard deviation, and intraocular pressure. Results: Among 1407 eligible patients (2806 eyes), 809 (57.5%) were female and the mean (SD) age at baseline was 57.5 (9.6) years. For 2124 eyes with sufficient measurements, KF-OHTN forecast MD values 60 months into the future within 0.5 dB of the actual value for 696 eyes (32.8%), 1.0 dB for 1295 eyes (61.0%), and 2.5 dB for 1980 eyes (93.2%). Among the 5 forecasting algorithms tested, KF-OHTN achieved the lowest root-mean-square error (1.72 vs 1.85-4.28) for MD values 60 months into the future. For the subset of eyes that progressed to open-angle glaucoma, KF-OHTN and KF-HTG forecast MD values 60 months into the future within 1 dB of the actual value for 30 eyes (68.2%; 95% CI, 54.4%-82.0%) and achieved the lowest root-mean-square error among all models. Conclusions and Relevance: These findings suggest that machine learning algorithms such as KF can accurately forecast MD, pattern standard deviation, and intraocular pressure 5 years into the future for many patients with OHTN. These algorithms may aid clinicians in managing OHTN in their patients.