David Scheinker is the Executive Director of Systems Design and Collaborative Research at the Stanford Lucile Packard Children's Hospital. He is the Founder and Director of SURF Stanford Medicine, a group that brings together students and faculty from the university with physicians, nurses, and administrators from the hospitals. SURF has implemented and published dozens of projects demonstrating improvements to the quality and efficiency of care. His areas of focus include clinical care delivery, technical improvements to hospital operations, sensor-based and algorithm-enabled telemedicine, and the socioeconomic factors that shape healthcare cost and quality.
Before coming to Stanford, he was a Joint Research Fellow at The MIT Sloan School of Management and Massachusetts General Hospital. He received a PhD in theoretical math from The University of California San Diego under Jim Agler. His current areas of research include applications of operations research in healthcare, type 1 diabetes management with continuous glucose monitor data, and healthcare policy. He advises Carta Healthcare, a healthcare analytics company started by former students.
Clinical Associate Professor, Pediatrics - Endocrinology and Diabetes
Executive Director of Systems Design and Collaborative Research, Lucile Packard Children's Hospital Stanford (2015 - Present)
Founder and Director, SURF Stanford Medicine (2015 - Present)
Faculty, Clinical Excellence Research Center (CERC) (2018 - Present)
Faculty, Master of Science in Clinical Informatics Management (MCiM) (2020 - Present)
Faculty, Clinical Excellence Leadership Training (CELT) (2016 - Present)
Boards, Advisory Committees, Professional Organizations
Advisor, Carta Healthcare (2017 - Present)
- Healthcare Operations Management
MS&E 263, PEDS 263 (Win)
- Healthcare Systems Design
MS&E 463 (Spr)
- Independent Studies (3)
Prior Year Courses
Reducing administrative costs in US health care: Assessing single payer and its alternatives.
Health services research
OBJECTIVE: Excess administrative costs in the US health care system are routinely referenced as a justification for comprehensive reform. While there is agreement that these costs are too high, there is little understanding of what generates administrative costs and what policy options might mitigate them.DATA SOURCES: Literature review and national utilization and expenditure data.STUDY DESIGN: We developed a simulation model of physician billing and insurance-related (BIR) costs to estimate how certain policy reforms would generate savings. Our model is based on structural elements of the payment process in the United States and considers each provider's number of health plan contracts, the number of features in each health plan, the clinical and nonclinical processes required to submit a bill for payment, and the compliance costs associated with medical billing.DATA EXTRACTION: For several types of visits, we estimated fixed and variable costs of the billing process. We used the model to estimate the BIR costs at a national level under a variety of policy scenarios, including variations of a single payer "Medicare-for-All" model that extends fee-for-service Medicare to the entire population and policy efforts to reduce administrative costs in a multi-payer model. We conducted sensitivity analyses of a wide variety of model parameters.PRINCIPAL FINDINGS: Our model estimates that national BIR costs are reduced between 33% and 53% in Medicare-for-All style single-payer models and between 27% and 63% in various multi-payer models. Under a wide range of assumptions and sensitivity analyses, standardizing contracts generates larger savings with less variance than savings from single-payer strategies.CONCLUSION: Although moving toward a single-payer system will reduce BIR costs, certain reforms to payer-provider contracts could generate at least as many administrative cost savings without radically reforming the entire health system. BIR costs can be meaningfully reduced without abandoning a multi-payer system.
View details for DOI 10.1111/1475-6773.13649
View details for PubMedID 33788283
The development and deployment of a model for hospital-level COVID-19 associated patient demand intervals from consistent estimators (DICE).
Health care management science
Hospitals commonly project demand for their services by combining their historical share of regional demand with forecasts of total regional demand. Hospital-specific forecasts of demand that provide prediction intervals, rather than point estimates, may facilitate better managerial decisions, especially when demand overage and underage are associated with high, asymmetric costs. Regional point forecasts of patient demand are commonly available, e.g., for the number of people requiring hospitalization due to an epidemic such as COVID-19. However, even in this common setting, no probabilistic, consistent, computationally tractable forecast is available for the fraction of patients in a region that a particular institution should expect. We introduce such a forecast, DICE (Demand Intervals from Consistent Estimators). We describe its development and deployment at an academic medical center in California during the 'second wave' of COVID-19 in the Unite States. We show that DICE is consistent under mild assumptions and suitable for use with perfect, biased and unbiased regional forecasts. We evaluate its performance on empirical data from a large academic medical center as well as on synthetic data.
View details for DOI 10.1007/s10729-021-09555-3
View details for PubMedID 33751281
The design and evaluation of a novel algorithm for automated preference card optimization.
Journal of the American Medical Informatics Association : JAMIA
BACKGROUND: Inaccurate surgical preference cards (supply lists) are associated with higher direct costs, waste, and delays. Numerous preference card improvement projects have relied on institution-specific, manual approaches of limited reproducibility. We developed and tested an algorithm to facilitate the first automated, informatics-based, fully reproducible approach.METHODS: The algorithm cross-references the supplies used in each procedure and listed on each preference card and uses a time-series regression to estimate the likelihood that each quantity listed on the preference card is inaccurate. Algorithm performance was evaluated by measuring changes in direct costs between preference cards revised with the algorithm and preference cards that were not revised or revised without use of the algorithm. Results were evaluated with a difference-in-differences (DID) multivariate fixed-effects model of costs during an 8-month pre-intervention and a 15-month post-intervention period.RESULTS: The accuracies of the quantities of 469155 surgeon-procedure-specific items were estimated. Nurses used these estimates to revise 309 preference cards across eight surgical services corresponding to, respectively, 1777 and 3106 procedures in the pre- and post-intervention periods. The average direct cost of supplies per case decreased by 8.38% ($352, SD $6622) for the intervention group and increased by 13.21% ($405, SD $14706) for the control group (P<.001). The DID analysis showed significant cost reductions only in the intervention group during the intervention period (P<.001).CONCLUSION: The optimization of preference cards with a variety of institution-specific, manually intensive approaches has led to cost savings. The automated algorithm presented here produced similar results that may be more readily reproducible.
View details for DOI 10.1093/jamia/ocaa275
View details for PubMedID 33497439
- Differences in Central Line-Associated Bloodstream Infection Rates Based on the Criteria Used to Count Central Line Days. JAMA 2020; 323 (2): 183–85
- Identification of Factors Associated With Variation in US County-Level Obesity Prevalence Rates Using Epidemiologic vs Machine Learning Models JAMA NETWORK OPEN 2019; 2 (4)
Development and Implementation of a Real-time Bundle-adherence Dashboard for Central Line-associated Bloodstream Infections.
Pediatric quality & safety
2021; 6 (4): e431
Introduction: Central line-associated bloodstream infections (CLABSIs) are the most common hospital-acquired infection in pediatric patients. High adherence to the CLABSI bundle mitigates CLABSIs. At our institution, there did not exist a hospital-wide system to measure bundle-adherence. We developed an electronic dashboard to monitor CLABSI bundle-adherence across the hospital and in real time.Methods: Institutional stakeholders and areas of opportunity were identified through interviews and data analyses. We created a data pipeline to pull adherence data from twice-daily bundle checks and populate a dashboard in the electronic health record. The dashboard was developed to allow visualization of overall and individual element bundle-adherence across units. Monthly dashboard accesses and element-level bundle-adherence were recorded, and the nursing staff's feedback about the dashboard was obtained.Results: Following deployment in September 2018, the dashboard was primarily accessed by quality improvement, clinical effectiveness and analytics, and infection prevention and control. Quality improvement and infection prevention and control specialists presented dashboard data at improvement meetings to inform unit-level accountability initiatives. All-element adherence across the hospital increased from 25% in September 2018 to 44% in December 2019, and average adherence to each bundle element increased between 2018 and 2019.Conclusions: CLABSI bundle-adherence, overall and by element, increased across the hospital following the deployment of a real-time electronic data dashboard. The dashboard enabled population-level surveillance of CLABSI bundle-adherence that informed bundle accountability initiatives. Data transparency enabled by electronic dashboards promises to be a useful tool for infectious disease control.
View details for DOI 10.1097/pq9.0000000000000431
View details for PubMedID 34235355
Improved individual and population-level HbA1c estimation using CGM data and patient characteristics.
Journal of diabetes and its complications
Machine learning and linear regression models using CGM and participant data reduced HbA1c estimation error by up to 26% compared to the GMI formula, and exhibit superior performance in estimating the median of HbA1c at the cohort level, potentially of value for remote clinical trials interrupted by COVID-19.
View details for DOI 10.1016/j.jdiacomp.2021.107950
View details for PubMedID 34127370
Prediction of Prolonged Opioid Use After Surgery in Adolescents: Insights From Machine Learning.
Anesthesia and analgesia
BACKGROUND: Long-term opioid use has negative health care consequences. Patients who undergo surgery are at risk for prolonged opioid use after surgery (POUS). While risk factors have been previously identified, no methods currently exist to determine higher-risk patients. We assessed the ability of a variety of machine-learning algorithms to predict adolescents at risk of POUS and to identify factors associated with this risk.METHODS: A retrospective cohort study was conducted using a national insurance claims database of adolescents aged 12-21 years who underwent 1 of 1297 surgeries, with general anesthesia, from January 1, 2011 to December 30, 2017. Logistic regression with an L2 penalty and with a logistic regression with an L1 lasso (Lasso) penalty, random forests, gradient boosting machines, and extreme gradient boosted models were trained using patient and provider characteristics to predict POUS (≥1 opioid prescription fill within 90-180 days after surgery) risk. Predictive capabilities were assessed using the area under the receiver-operating characteristic curve (AUC)/C-statistic, mean average precision (MAP); individual decision thresholds were compared using sensitivity, specificity, Youden Index, F1 score, and number needed to evaluate. The variables most strongly associated with POUS risk were identified using permutation importance.RESULTS: Of 186,493 eligible patient surgical visits, 8410 (4.51%) had POUS. The top-performing algorithm achieved an overall AUC of 0.711 (95% confidence interval [CI], 0.699-0.723) and significantly higher AUCs for certain surgeries (eg, 0.823 for spinal fusion surgery and 0.812 for dental surgery). The variables with the strongest association with POUS were the days' supply of opioids and oral morphine milligram equivalents of opioids in the year before surgery.CONCLUSIONS: Machine-learning models to predict POUS risk among adolescents show modest to strong results for different surgeries and reveal variables associated with higher risk. These results may inform health care system-specific identification of patients at higher risk for POUS and drive development of preventative measures.
View details for DOI 10.1213/ANE.0000000000005527
View details for PubMedID 33939656
Quantifying Pediatric Intensive Care Unit Staffing Levels at a Pediatric Academic Medical Center: A Mixed Methods Approach.
Journal of nursing management
AIM: Identify, simulate, and evaluate the formal and informal patient-level and unit-level factors that nurse managers use to determine the number of nurses for each shift.BACKGROUND: Nurse staffing schedules are commonly set based on metrics such as midnight census that do not account for seasonality or midday turnover, resulting in last-minute adjustments or inappropriate staffing levels.METHODS: Staffing schedules at a pediatric intensive care unit (PICU) were simulated based on nurse-to-patient assignment rules from interviews with nursing management. Multivariate regression modeled the discrepancies between scheduled and historical staffing levels and constructed rules to reduce these discrepancies. The primary outcome was the median difference between simulated and historical staffing levels.RESULTS: Nurse-to-patient ratios underestimated staffing by a median of 1.5 nurses per shift. Multivariate regression identified patient turnover as the primary factor accounting for this difference and subgroup analysis revealed that patient age and weight were also important. New rules reduced the difference to a median of 0.07 nurses per shift.CONCLUSION: Measurable, predictable indicators of patient acuity and historical trends may allow for schedules that better match demand.IMPLICATIONS FOR NURSING MANAGEMENT: Data-driven methods can quantify what drives unit demand and generate nurse schedules that require fewer last-minute adjustments.
View details for DOI 10.1111/jonm.13346
View details for PubMedID 33894027
- Racial and Ethnic Disparities in Household Contact with Individuals at Higher Risk of Exposure to COVID-19. Journal of general internal medicine 2021
County-Level Factors Associated With Cardiovascular Mortality by Race/Ethnicity.
Journal of the American Heart Association
Background Persistent racial/ethnic disparities in cardiovascular disease (CVD) mortality are partially explained by healthcare access and socioeconomic, demographic, and behavioral factors. Little is known about the association between race/ethnicity-specific CVD mortality and county-level factors. Methods and Results Using 2017 county-level data, we studied the association between race/ethnicity-specific CVD age-adjusted mortality rate (AAMR) and county-level factors (demographics, census region, socioeconomics, CVD risk factors, and healthcare access). Univariate and multivariable linear regressions were used to estimate the association between these factors; R2 values were used to assess the factors that accounted for the greatest variation in CVD AAMR by race/ethnicity (non-Hispanic White, non-Hispanic Black, and Hispanic/Latinx individuals). There were 659740 CVD deaths among non-Hispanic White individuals in 2698 counties; 100475 deaths among non-Hispanic Black individuals in 717 counties; and 49493 deaths among Hispanic/Latinx individuals across 267 counties. Non-Hispanic Black individuals had the highest mean CVD AAMR (320.04 deaths per 100000 individuals), whereas Hispanic/Latinx individuals had the lowest (168.42 deaths per 100000 individuals). The highest CVD AAMRs across all racial/ethnic groups were observed in the South. In unadjusted analyses, the greatest variation (R2) in CVD AAMR was explained by physical inactivity for non-Hispanic White individuals (32.3%), median household income for non-Hispanic Black individuals (24.7%), and population size for Hispanic/Latinx individuals (28.4%). In multivariable regressions using county-level factor categories, the greatest variation in CVD AAMR was explained by CVD risk factors for non-Hispanic White individuals (35.3%), socioeconomic factors for non-Hispanic Black (25.8%), and demographic factors for Hispanic/Latinx individuals (34.9%). Conclusions The associations between race/ethnicity-specific age-adjusted CVD mortality and county-level factors differ significantly. Interventions to reduce disparities may benefit from being designed accordingly.
View details for DOI 10.1161/JAHA.120.018835
View details for PubMedID 33653083
Quantifying Electronic Health Record Data: A Potential Risk for Cognitive Overload.
OBJECTIVES: To quantify and describe patient-generated health data.METHODS: This is a retrospective, single-center study of patients hospitalized in the pediatric cardiovascular ICU between February 1, 2020, and February 15, 2020. The number of data points generated over a 24-hour period per patient was collected from the electronic health record. Data were analyzed by type, and frontline provider exposure to data was extrapolated on the basis of patient-to-provider ratios.RESULTS: Thirty patients were eligible for inclusion. Nineteen were hospitalized after cardiac surgery, whereas 11 were medical patients. Patients generated an average of 1460 (SD 509) new data points daily, resulting in frontline providers being presented with an average of 4380 data points during a day shift (7:00 am to 7:00 pm). Overnight, because of a higher patient-to-provider ratio, frontline providers were exposed to an average of 16060 data points. There was no difference in data generation between medical and surgical patients. Structured data accounted for >80% of the new data generated.CONCLUSIONS: Health care providers face significant generation of new data daily through the contemporary electronic health record, likely contributing to cognitive burden and putting them at risk for cognitive overload. This study represents the first attempt to quantify this volume in the pediatric setting. Most data generated are structured and amenable to data-optimization systems to mitigate the potential for cognitive overload and its deleterious effects on patient safety and health care provider well-being.
View details for DOI 10.1542/hpeds.2020-002402
View details for PubMedID 33500357
The Hispanic paradox in the prevalence of obesity at the county-level.
Obesity science & practice
2021; 7 (1): 14–24
The percentage of Hispanics in a county has a negative association with prevalence of obesity. Because Hispanic individuals are unevenly distributed in the United States, this study examined whether this protective association persists when stratifying counties into quartiles based on the size of the Hispanic population and after adjusting for county-level demographic, socioeconomic, healthcare, and environmental factors.Data were extracted from the 2018 Robert Wood Johnson Foundation County Health Rankings. Counties were categorized into quartiles based on their percentage of Hispanics, 0%-5% (n = 1794), 5%-20% (n = 962), 20%-50% (n = 283), and >50% (n = 99). For each quartile, univariate and multivariate regression models were used to evaluate the association between prevalence of obesity and demographic, socioeconomic, healthcare, and environmental factors.Counties with the top quartile of Hispanic individuals had the lowest prevalence of obesity compared to counties at the bottom quartile (28.4 ± 3.6% vs. 32.7 ± 4.0%). There was a negative association between county-level percentage of Hispanics and prevalence of obesity in unadjusted analyses that persisted after adjusting for all county-level factors.Counties with a higher percentage of Hispanics have lower levels of obesity, even after controlling for demographic, socioeconomic, healthcare, and environmental factors. More research is needed to elucidate why having more Hispanics in a county may be protective against county-level obesity.
View details for DOI 10.1002/osp4.461
View details for PubMedID 33680488
View details for PubMedCentralID PMC7909595
Clinically serious hypoglycemia is rare and not associated with time-in-range in youth with new-onset type 1 diabetes.
The Journal of clinical endocrinology and metabolism
Early initiation of continuous glucose monitoring (CGM) is advocated for youth with type 1 diabetes (T1D). Data to guide CGM use on time-in-range (TIR), hypoglycemia, and the role of partial clinical remission (PCR) are limited. Our aims were to assess whether: 1) an association between increased TIR and hypoglycemia exists, and 2) how time in hypoglycemia varies by PCR status.We analyzed 80 youth who were started on CGM shortly after T1D diagnosis and were followed for up to 1-year post-diagnosis. TIR and hypoglycemia rates were determined by CGM data and retrospectively analyzed. PCR was defined as (visit-HbA1c)+(4*units/kg/day) <9.Youth were started on CGM 8.0 (IQR 6.0-13.0) days post-diagnosis. Time spent <70mg/dL remained low despite changes in TIR (highest TIR 74.6±16.7%, 2.4±2.4% hypoglycemia at 1 month post-diagnosis; lowest TIR 61.3±20.3%, 2.1±2.7% hypoglycemia at 12 months post-diagnosis). No events of severe hypoglycemia occurred. Hypoglycemia was rare and there was minimal difference for PCR versus non-PCR youth (54-70mg/dL: 1.8% vs 1.2%, p=0.04; <54mg/dL: 0.3% vs 0.3%, p=0.55). Approximately 50% of the time spent in hypoglycemia was in the 65-70mg/dL range.As TIR gradually decreased over 12 months post-diagnosis, hypoglycemia was limited with no episodes of severe hypoglycemia. Hypoglycemia rates did not vary in a clinically meaningful manner by PCR status. With CGM being started earlier, consideration needs to be given to modifying CGM hypoglycemia education, including alarm settings. These data support a trial in the year post-diagnosis to determine alarm thresholds for youth who wear CGM.
View details for DOI 10.1210/clinem/dgab522
View details for PubMedID 34265059
Multimethod, multidataset analysis reveals paradoxical relationships between sociodemographic factors, Hispanic ethnicity and diabetes.
BMJ open diabetes research & care
2020; 8 (2)
INTRODUCTION: Population-level and individual-level analyses have strengths and limitations as do 'blackbox' machine learning (ML) and traditional, interpretable models. Diabetes mellitus (DM) is a leading cause of morbidity and mortality with complex sociodemographic dynamics that have not been analyzed in a way that leverages population-level and individual-level data as well as traditional epidemiological and ML models. We analyzed complementary individual-level and county-level datasets with both regression and ML methods to study the association between sociodemographic factors and DM.RESEARCH DESIGN AND METHODS: County-level DM prevalence, demographics, and socioeconomic status (SES) factors were extracted from the 2018 Robert Wood Johnson Foundation County Health Rankings and merged with US Census data. Analogous individual-level data were extracted from 2007 to 2016 National Health and Nutrition Examination Survey studies and corrected for oversampling with survey weights. We used multivariate linear (logistic) regression and ML regression (classification) models for county (individual) data. Regression and ML models were compared using measures of explained variation (area under the receiver operating characteristic curve (AUC) and R2).RESULTS: Among the 3138 counties assessed, the mean DM prevalence was 11.4% (range: 3.0%-21.1%). Among the 12824 individuals assessed, 1688 met DM criteria (13.2% unweighted; 10.2% weighted). Age, gender, race/ethnicity, income, and education were associated with DM at the county and individual levels. Higher county Hispanic ethnic density was negatively associated with county DM prevalence, while Hispanic ethnicity was positively associated with individual DM. ML outperformed regression in both datasets (mean R2 of 0.679 vs 0.610, respectively (p<0.001) for county-level data; mean AUC of 0.737 vs 0.727 (p<0.0427) for individual-level data).CONCLUSIONS: Hispanic individuals are at higher risk of DM, while counties with larger Hispanic populations have lower DM prevalence. Analyses of population-level and individual-level data with multiple methods may afford more confidence in results and identify areas for further study.
View details for DOI 10.1136/bmjdrc-2020-001725
View details for PubMedID 33229378
- The Hispanic paradox in the prevalence of obesity at the county-level OBESITY SCIENCE & PRACTICE 2020
Target Based Care: An Intervention to Reduce Variation in Postoperative Length of Stay.
The Journal of pediatrics
OBJECTIVES: To derive care targets and evaluate the impact of displaying them at the point of care on postoperative length of stay (LOS).STUDY DESIGN: A prospective cohort study using 2 years of historical controls within a freestanding, academic children's hospital. Patients undergoing benchmark cardiac surgery between May 4, 2014 and August 15, 2016 (preintervention) and September 6, 2016 to September 30, 2018 (postintervention) were included. The intervention consisted of displaying at the point of care targets for the timing of extubation, transfer from the intensive care unit (ICU), and hospital discharge. Family satisfaction, reintubation, and readmission rates were tracked.RESULTS: The postintervention cohort consisted of 219 consecutive patients. There was a reduction in variation for ICU (difference in SD -2.56, p < 0.01), and total LOS (difference in SD -2.84, P < .001). Patients stayed on average 0.97 fewer days (p<0.001) in the ICU (median -1.01 [IQR -2.15,-0.39], 0.7 fewer days (p<0.001) on mechanical ventilation (median -0.54 [IQR -0.77,-0.50], and 1.18 fewer days (p<0.001) for the total LOS (median -2.25 [IQR -3.69,-0.15]. Log transformed multivariable linear regression demonstrated the intervention to be associated with shorter ICU LOS (beta coefficient -0.19, SE 0.059, p<0.001), total postoperative LOS (beta coefficient -0.12, SE 0.052, p=0.02), and ventilator duration (beta coefficient -0.21, SE 0.048, p<0.001). Balancing metrics did not differ after the intervention.CONCLUSIONS: Target based care is a simple, novel intervention associated with reduced variation in LOS and absolute LOS across a diverse spectrum of complex cardiac surgeries.
View details for DOI 10.1016/j.jpeds.2020.09.017
View details for PubMedID 32920104
Uninterrupted Continuous Glucose Monitoring Access is Associated with a Decrease in HbA1c in Youth with Type 1 Diabetes and Public Insurance.
OBJECTIVE: Continuous glucose monitor (CGM) use is associated with improved glucose control. We describe the effect of continued and interrupted CGM use on hemoglobin A1c (HbA1c) in youth with public insurance.METHODS: We reviewed 956 visits from 264 youth with type 1 diabetes (T1D) and public insurance. Demographic data, HbA1c and two-week CGM data were collected. Youth were classified as never user, consistent user, insurance discontinuer, and self-discontinuer. Visits were categorized as never-user visit, visit before CGM start, visit after CGM start, visit with continued CGM use, visit with initial loss of CGM, visit with continued loss of CGM, and visit where CGM is regained after loss. Multivariate regression adjusting for age, sex, race, diabetes duration, initial HbA1c, and BMI were used to calculate adjusted mean and delta HbA1c.RESULTS: Adjusted mean HbA1c was lowest for the consistent user group (HbA1c 8.6%;[95%CI 7.9,9.3]). Delta HbA1c (calculated from visit before CGM start) was lower for visit after CGM start (-0.39%;[95%CI -0.78,-0.02]) and visit with continued CGM use (-0.29%;[95%CI -0.61,0.02]) whereas it was higher for visit with initial loss of CGM (0.40%;[95%CI -0.06,0.86]), visit with continued loss of CGM (0.46%;[95%CI 0.06,0.85]), and visit where CGM is regained after loss (0.57%;[95%CI 0.06,1.10]).CONCLUSIONS: Youth with public insurance using CGM have improved HbA1c, but only when CGM use is uninterrupted. Interruptions in use, primarily due to gaps in insurance coverage of CGM, were associated with increased HbA1c. These data support both initial and ongoing coverage of CGM for youth with T1D and public insurance. This article is protected by copyright. All rights reserved.
View details for DOI 10.1111/pedi.13082
View details for PubMedID 32681582
- Clinically Significant Hypoglycemia Is Rare in Youth with T1D during Partial Clinical Remission AMER DIABETES ASSOC. 2020
- The Association between Time-in-Range, Mean Glucose, and Incidence of Hypoglycemia in Youth with Newly Diagnosed T1D AMER DIABETES ASSOC. 2020
- A Telemedicine-CGM Recommendation System for Personalized Population Health Management AMER DIABETES ASSOC. 2020
- Newly Diagnosed Pediatric Patients with Type 1 Diabetes Show Steady Decline in Glucose Time-in-Range (TIR) over 1 Year: Pilot Study AMER DIABETES ASSOC. 2020
- Early CGM Initiation Improves HbA1c in T1D Youth over the First 15 Months AMER DIABETES ASSOC. 2020
- Implementing Analytics Projects in a Hospital: Successes, Failures, and Opportunities INTERFACES 2020; 50 (3): 176–89
COUNTY-LEVEL FACTORS ASSOCIATED WITH CARDIOVASCULAR MORTALITY DISAGGREGATED BY RACE/ETHNICITY
ELSEVIER SCIENCE INC. 2020: 1884
View details for Web of Science ID 000522979101871
PERSONALIZED INTER-DONATION INTERVALS TO MANAGE RISK OF IRON-RELATED ADVERSE EVENTS IN REPEAT BLOOD DONORS
SAGE PUBLICATIONS INC. 2020: E111–E112
View details for Web of Science ID 000509275600101
Baseline creatinine determination method impacts association between acute kidney injury and clinical outcomes.
Pediatric nephrology (Berlin, Germany)
Current consensus definition for acute kidney injury (AKI) does not specify how baseline serum creatinine should be determined. We assessed how baseline determination impacted AKI incidence and association between AKI and clinical outcomes.We retrospectively applied empirical (measured serum creatinine) and imputed (age/height) baseline estimation methods to pediatric patients discharged between 2014 and 2019 from an academic hospital. Using each method, we estimated AKI incidence and assessed area under ROC curve (AUROC) for AKI as a predictor of three clinical outcomes: application of AKI billing code (proxy for more clinically overt disease), inpatient mortality, and post-hospitalization chronic kidney disease.Incidence was highly variable across baseline methods (12.2-26.7%). Incidence was highest when lowest pre-admission creatinine was used if available and Schwartz bedside equation was used to impute one otherwise. AKI was more predictive of application of an AKI billing code when baseline was imputed universally, regardless of pre-admission values (AUROC 80.7-84.9%) than with any empirical approach (AUROC 64.5-76.6%). AKI was predictive of post-hospitalization CKD when using universal imputation baseline methods (AUROC 67.0-74.6%); AKI was not strongly predictive of post-hospitalization CKD when using empirical baseline methods (AUROC 46.4-58.5%). Baseline determination method did not affect the association between AKI and inpatient mortality.Method of baseline determination influences AKI incidence and association between AKI and clinical outcomes, illustrating the need for standard criteria. Imputing baseline for all patients, even when preadmission creatinine is available, may identify a more clinically relevant subset of the disease.
View details for DOI 10.1007/s00467-020-04789-9
View details for PubMedID 33095322
Machine learning and atherosclerotic cardiovascular disease risk prediction in a multi-ethnic population.
NPJ digital medicine
2020; 3: 125
The pooled cohort equations (PCE) predict atherosclerotic cardiovascular disease (ASCVD) risk in patients with characteristics within prespecified ranges and has uncertain performance among Asians or Hispanics. It is unknown if machine learning (ML) models can improve ASCVD risk prediction across broader diverse, real-world populations. We developed ML models for ASCVD risk prediction for multi-ethnic patients using an electronic health record (EHR) database from Northern California. Our cohort included patients aged 18 years or older with no prior CVD and not on statins at baseline (n = 262,923), stratified by PCE-eligible (n = 131,721) or PCE-ineligible patients based on missing or out-of-range variables. We trained ML models [logistic regression with L2 penalty and L1 lasso penalty, random forest, gradient boosting machine (GBM), extreme gradient boosting] and determined 5-year ASCVD risk prediction, including with and without incorporation of additional EHR variables, and in Asian and Hispanic subgroups. A total of 4309 patients had ASCVD events, with 2077 in PCE-ineligible patients. GBM performance in the full cohort, including PCE-ineligible patients (area under receiver-operating characteristic curve (AUC) 0.835, 95% confidence interval (CI): 0.825-0.846), was significantly better than that of the PCE in the PCE-eligible cohort (AUC 0.775, 95% CI: 0.755-0.794). Among patients aged 40-79, GBM performed similarly before (AUC 0.784, 95% CI: 0.759-0.808) and after (AUC 0.790, 95% CI: 0.765-0.814) incorporating additional EHR data. Overall, ML models achieved comparable or improved performance compared to the PCE while allowing risk discrimination in a larger group of patients including PCE-ineligible patients. EHR-trained ML models may help bridge important gaps in ASCVD risk prediction.
View details for DOI 10.1038/s41746-020-00331-1
View details for PubMedID 33043149
View details for PubMedCentralID PMC7511400
Extremum Seeking for Creating Optimal Feedback Controls of Unknown Systems by Tuning Basis Functions
IEEE. 2020: 44–49
View details for Web of Science ID 000618079800003
Improving Clinical Outcomes in Newly Diagnosed Pediatric Type 1 Diabetes: Teamwork, Targets, Technology, and Tight Control-The 4T Study.
Frontiers in endocrinology
2020; 11: 360
Many youth with type 1 diabetes (T1D) do not achieve hemoglobin A1c (HbA1c) targets. The mean HbA1c of youth in the USA is higher than much of the developed world. Mean HbA1c in other nations has been successfully modified following benchmarking and quality improvement methods. In this review, we describe the novel 4T approach-teamwork, targets, technology, and tight control-to diabetes management in youth with new-onset T1D. In this program, the diabetes care team (physicians, nurse practitioners, certified diabetes educators, dieticians, social workers, psychologists, and exercise physiologists) work closely to deliver diabetes education from diagnosis. Part of the education curriculum involves early integration of technology, specifically continuous glucose monitoring (CGM), and developing a curriculum around using the CGM to maintain tight control and optimize quality of life.
View details for DOI 10.3389/fendo.2020.00360
View details for PubMedID 32733375
View details for PubMedCentralID PMC7363838
- Improving the efficiency of the operating room environment with an optimization and machine learning model HEALTH CARE MANAGEMENT SCIENCE 2019; 22 (4): 756–67
- Practice Characteristics of Board-certified Pediatric Anesthesiologists in the US: A Nationwide Survey CUREUS 2019; 11 (9)
- Personalized Diabetes Management Using Data from Continuous Glucose Monitors AMER DIABETES ASSOC. 2019
Non-clinical delays in transfer out of the surgical ICU are associated with increased hospital length of stay and delayed progress of care
JOURNAL OF CRITICAL CARE
2019; 50: 126–31
The impact of non-clinical transfer delay (TD) from the ICU to a general care unit on the progress of the patient's care is unknown. We measured the association between TD and: (1) the patient's subsequent hospital length of stay (LOS); (2) the timing of care decisions that would advance patient care.This was a single center retrospective study in the United States of patients admitted to the surgical and neurosurgical ICUs during 2013 and 2015. The primary outcome was hospital LOS after transfer request. The secondary outcome was the timing of provider orders representing care decisions (milestones) that would advance the patient's care. Patient, surgery, and bed covariates were accounted for in a multivariate regression and propensity matching analysis.Out of the cohort of 4,926 patients, 1,717 met inclusion criteria. 670 (39%) experienced ≥12 hours of TD. For each day of TD, there was an average increase of 0.70 days in LOS (P < 0.001). The last milestone occurred on average 0.35 days later (P < 0.001). Propensity matching analyses were confirmatory (P < 0.001, P < 0.001).TD is associated with longer LOS and delays in milestone clinical decisions that progress care. Eliminating delays in milestones could mitigate TD's impact on LOS.
View details for DOI 10.1016/j.jcrc.2018.11.025
View details for Web of Science ID 000458375800021
View details for PubMedID 30530264
Identification of Factors Associated With Variation in US County-Level Obesity Prevalence Rates Using Epidemiologic vs Machine Learning Models.
JAMA network open
2019; 2 (4): e192884
Obesity is a leading cause of high health care expenditures, disability, and premature mortality. Previous studies have documented geographic disparities in obesity prevalence.To identify county-level factors associated with obesity using traditional epidemiologic and machine learning methods.Cross-sectional study using linear regression models and machine learning models to evaluate the associations between county-level obesity and county-level demographic, socioeconomic, health care, and environmental factors from summarized statistical data extracted from the 2018 Robert Wood Johnson Foundation County Health Rankings and merged with US Census data from each of 3138 US counties. The explanatory power of the linear multivariate regression and the top performing machine learning model were compared using mean R2 measured in 30-fold cross validation.County-level demographic factors (population; rural status; census region; and race/ethnicity, sex, and age composition), socioeconomic factors (median income, unemployment rate, and percentage of population with some college education), health care factors (rate of uninsured adults and primary care physicians), and environmental factors (access to healthy foods and access to exercise opportunities).County-level obesity prevalence in 2018, its association with each county-level factor, and the percentage of variation in county-level obesity prevalence explained by linear multivariate and gradient boosting machine regression measured with R2.Among the 3138 counties studied, the mean (range) obesity prevalence was 31.5% (12.8%-47.8%). In multivariate regressions, demographic factors explained 44.9% of variation in obesity prevalence; socioeconomic factors, 33.0%; environmental factors, 15.5%; and health care factors, 9.1%. The county-level factors with the strongest association with obesity were census region, median household income, and percentage of population with some college education. R2 values of univariate regressions of obesity prevalence were 0.238 for census region, 0.218 for median household income, and 0.160 for percentage of population with some college education. Multivariate linear regression and gradient boosting machine regression (the best-performing machine learning model) of obesity prevalence using all county-level demographic, socioeconomic, health care, and environmental factors had R2 values of 0.58 and 0.66, respectively (P < .001).Obesity prevalence varies significantly between counties. County-level demographic, socioeconomic, health care, and environmental factors explain the majority of variation in county-level obesity prevalence. Using machine learning models may explain significantly more of the variation in obesity prevalence..
View details for PubMedID 31026030
Hospitalization Patterns for Inpatient Surgery and Procedures in California:2000 – 2016
Anesthesia and Analgesia
View details for DOI 10.1213/ANE.0000000000004552
- CGM Initiation Soon After Type 1 Diabetes Diagnosis Results in Sustained CGM Use and Wear Time. Diabetes care 2019
Anesthesiologist Surgery Assignments Using Policy Learning
View details for Web of Science ID 000492038800103
Practice Characteristics of Board-certified Pediatric Anesthesiologists in the US: A Nationwide Survey.
2019; 11 (9): e5745
Introduction We conducted a survey to describe the practice characteristics of anesthesiologists who have passed the American Board of Anesthesiology (ABA) Pediatric Anesthesiology Certification Examination. Methods In July 2017, a list of anesthesiologists who had taken the ABA Pediatric Anesthesiology Certification Examination (hereafter referred to as "pediatric anesthesiologists") was obtained from the American Board of Anesthesiologists (theaba.org). Email contact information for these individuals was collected from departmental rosters, email distribution lists, hospital or anesthesia group profiles, manuscript author contact information, website source code, and other publicly available online sources. The survey was designed using Qualtrics (Qualtrics, Provo, Utah; Seattle, Washington), a web-based tool, to ascertain residency/fellowship training history and current practice characteristics that includes: years in practice, clinical work hours per week, primary hospital setting, practice type, supervision model, estimated percentage of cases by patient age group, and percentage of respondents who cared for any patient undergoing a fellowship-level index cases within the previous year. The invitation to complete the survey included a financial incentive - the chance to win one of twenty $50 Amazon gift cards. Results There were 3,492 anesthesiologists who had taken the Pediatric Anesthesiology Certification Examination since 2013. Surveys were sent to those whom an email address was identified (2,681) and 962 complete survey responses were received (35.9%, 962/2,681). Over 80% (785) of respondents completed a pediatric anesthesiology fellowship. Of these, 485 respondents (50.4%) work in academic practice, 212 (22.0%) in private practice, 233 (24.2%) in private practice and have academic affiliations, and 32 (3.3%) as locum tenens or in other practice settings. The majority of respondents (64.3%) in academic practice work in freestanding children's hospitals. Pediatric anesthesiologists in academic practice and private practice with academic affiliations reported caring for a greater number of younger children and doing a wider variety of index cases than respondents in private practice. Conclusion The extent to which pediatric anesthesiologists care for pediatric patients - particularly young children and those undergoing complex cases - varies. The variability in practice characteristics is likely a result of differences in hospital type, anesthesia practice type, geographic location, and other factors.
View details for DOI 10.7759/cureus.5745
View details for PubMedID 31723506
View details for PubMedCentralID PMC6825435
Hemoglobin A1c Trajectory in Pediatric Patients with Newly Diagnosed Type 1 Diabetes.
Diabetes technology & therapeutics
Despite advances in diabetes technology and treatment, a majority of children and adolescents with type 1 diabetes (T1D) fail to meet hemoglobin A1c (HbA1c) targets. Among high-income nations, the United States has one of the highest mean HbA1c values. We tracked the HbA1c values of 261 patients diagnosed with T1D in our practice over a 2.5-year period to identify inflection points in the HbA1c trajectory. The HbA1c declined until 5 months postdiagnosis. There was a rise in the HbA1c between the fifth and sixth month postdiagnosis. The HbA1c continued to steadily rise and by 18 months postdiagnosis, the mean HbA1c was 8.2%, which is also our clinic mean. Understanding the HbA1c trajectory early in the course of diabetes has helped to identify opportunities for intensification of diabetes management to flatten the trajectory of HbA1c and improve clinical outcomes.
View details for DOI 10.1089/dia.2019.0065
View details for PubMedID 31180244
A Retrospective Review of a Bed-mounted Projection System for Managing Pediatric Preoperative Anxiety.
Pediatric quality & safety
2018; 3 (4): e087
Introduction: Most children undergoing anesthesia experience significant preoperative anxiety. We developed a bedside entertainment and relaxation theater (BERT) as an alternative to midazolam for appropriate patients undergoing anesthesia. The primary aim of this study was to determine if BERT was as effective as midazolam in producing cooperative patients at anesthesia induction. Secondary aims reviewed patient emotion and timeliness of BERT utilization.Methods: We conducted a retrospective cohort study of pediatric patients undergoing anesthesia at Lucile Packard Children's Hospital Stanford between February 1, 2016, and October 1, 2016. Logistic regression compared induction cooperation between groups. Multinomial logistic regression compared patients' emotion at induction. Ordinary least squares regression compared preoperative time.Results: Of the 686 eligible patients, 163 were in the BERT group and 150 in the midazolam. Ninety-three percentage of study patients (290/313) were cooperative at induction, and the BERT group were less likely to be cooperative (P = 0.04). The BERT group was more likely to be "playful" compared with "sedated" (P < 0.001). There was a reduction of 14.7 minutes in preoperative patient readiness associated with BERT (P = 0.001).Conclusions: Although most patients were cooperative for induction in both groups, the midazolam group was more cooperative. The BERT reduced the preinduction time and was associated with an increase in patients feeling "playful."
View details for PubMedID 30229198
The Pediatric Anesthesiology Workforce: Projecting Supply and Trends 2015-2035
ANESTHESIA AND ANALGESIA
2018; 126 (2): 568–78
A workforce analysis was conducted to predict whether the projected future supply of pediatric anesthesiologists is balanced with the requirements of the inpatient pediatric population. The specific aims of our analysis were to (1) project the number of pediatric anesthesiologists in the future workforce; (2) project pediatric anesthesiologist-to-pediatric population ratios (0-17 years); (3) project the mean number of inpatient pediatric procedures per pediatric anesthesiologist; and (4) evaluate the effect of alternative projections of individual variables on the model projections through 2035.The future number of pediatric anesthesiologists is determined by the current supply, additions to the workforce, and departures from the workforce. We previously compiled a database of US pediatric anesthesiologists in the base year of 2015. The historical linear growth rate for pediatric anesthesiology fellowship positions was determined using the Accreditation Council for Graduate Medical Education Data Resource Books from 2002 to 2016. The future number of pediatric anesthesiologists in the workforce was projected given growth of pediatric anesthesiology fellowship positions at the historical linear growth rate, modeling that 75% of graduating fellows remain in the pediatric anesthesiology workforce, and anesthesiologists retire at the current mean retirement age of 64 years old. The baseline model projections were accompanied by age- and gender-adjusted anesthesiologist supply, and sensitivity analyses of potential variations in fellowship position growth, retirement, pediatric population, inpatient surgery, and market share to evaluate the effect of each model variable on the baseline model. The projected ratio of pediatric anesthesiologists to pediatric population was determined using the 2012 US Census pediatric population projections. The projected number of inpatient pediatric procedures per pediatric anesthesiologist was determined using the Kids' Inpatient Database historical data to project the future number of inpatient procedures (including out of operating room procedures).In 2015, there were 5.4 pediatric anesthesiologists per 100,000 pediatric population and a mean (±standard deviation [SD]) of 262 ±8 inpatient procedures per pediatric anesthesiologist. If historical trends continue, there will be an estimated 7.4 pediatric anesthesiologists per 100,000 pediatric population and a mean (±SD) 193 ±6 inpatient procedures per pediatric anesthesiologist in 2035. If pediatric anesthesiology fellowship positions plateau at 2015 levels, there will be an estimated 5.7 pediatric anesthesiologists per 100,000 pediatric population and a mean (±SD) 248 ±7 inpatient procedures per pediatric anesthesiologist in 2035.If historical trends continue, the growth in pediatric anesthesiologist supply may exceed the growth in both the pediatric population and inpatient procedures in the 20-year period from 2015 to 2035.
View details for PubMedID 29116973
- Constrained extremum seeking stabilization of systems not affine in control INTERNATIONAL JOURNAL OF ROBUST AND NONLINEAR CONTROL 2018; 28 (2): 568–81
Promise and Perils of Big Data and Artificial Intelligence in Clinical Medicine and Biomedical Research.
2018; 123 (12): 1282–84
View details for PubMedID 30566055
A quality improvement initiative to optimize dosing of surgical antimicrobial prophylaxis.
2017; 27 (7): 702-710
The risk of surgical site infections is reduced with appropriate timing and dosing of preoperative antimicrobials. Based on evolving national guidelines, we increased the preoperative dose of cefazolin from 25 to 30 mg·kg(-1) . This quality improvement project describes an improvement initiative to develop standard work processes to ensure appropriate dosing.The primary aim was to deliver cefazolin 30 mg·kg(-1) to at least 90% of indicated patients. The secondary aim was to determine differences between accuracy of cefazolin doses when given as an electronic order compared to a verbal order.Data were collected from January 1, 2012 to May 31, 2016. A quality improvement team of perioperative physicians, nurses, and pharmacists implemented a series of interventions including new electronic medical record order sets, personal provider antibiotic dose badges, and utilization of pharmacists to prepare antibiotics to increase compliance with the recommended dose. Process compliance was measured using a statistical process control chart, and dose compliance was measured through electronic analysis of the electronic medical record. Secondary aim data were displayed as percentage of dose compliance. An unpaired t-test was used to determine differences between groups.Between January 1, 2012 and May 31, 2016, cefazolin was administered to 9086 patients. The mean compliance of cefazolin at 30 mg·kg(-1) from May 2013 to March 2014 was 40%, which prompted initiation of this project. From April 2014 to May 2016, a series of interventions were deployed. The mean compliance from September 2015 to May 2016 was 93% with significantly reduced variation and no special cause variation, indicating that the process was in control at the target primary aim. There were 649 cefazolin administrations given verbally and 1929 given with an electronic order between October 1, 2014 and May 31, 2016. During this time period, the rate of compliance of administering cefazolin at 30 mg·kg(-1) was significantly higher when given after an electronic order than when given verbally, 94% vs 76%.This comprehensive quality improvement project improved practitioner compliance with evidence-based preoperative antimicrobial dosing recommendations to reduce the risk of surgical site infections.
View details for DOI 10.1111/pan.13137
View details for PubMedID 28321988
- Detecting Inaccurate Predictions of Pediatric Surgical Durations IEEE. 2016: 452–57