Stroke Administrative Severity Index: using administrative data for 30-day poststroke outcomes prediction.
Ontology highlight
ABSTRACT:
SUBMITTER: Simpson AN
PROVIDER: S-EPMC6615407 | biostudies-literature | 2018 Apr
REPOSITORIES: biostudies-literature
Publications
Stroke Administrative Severity Index: using administrative data for 30-day poststroke outcomes prediction.
Simpson Annie N AN Wilmskoetter Janina J Hong Ickpyo I Li Chih-Ying CY Jauch Edward C EC Bonilha Heather S HS Anderson Kelly K Harvey Jillian J Simpson Kit N KN
Journal of comparative effectiveness research 20171023 4
<h4>Aim</h4>Current stroke severity scales cannot be used for archival data. We develop and validate a measure of stroke severity at hospital discharge (Stroke Administrative Severity Index [SASI]) for use in billing data.<h4>Methods</h4>We used the NIH Stroke Scale (NIHSS) as the theoretical framework and identified 285 relevant International Classification of Diseases, 9th Revision diagnosis and procedure codes, grouping them into 23 indicator variables using cluster analysis. A 60% sample of ...[more]
Similar Datasets
Project description:Predicting unplanned rehospitalizations has traditionally employed logistic regression models. Machine learning (ML) methods have been introduced in health service research and may improve the prediction of health outcomes. The objective of this work was to develop a ML model to predict 30-day all-cause rehospitalizations based on the French hospital medico-administrative database.This was a retrospective cohort study of all discharges in the year 2015 from acute-care inpatient hospitalizations in a tertiary-care university center comprising 4 French hospitals. The study endpoint was unplanned 30-day all-cause rehospitalization. Logistic regression (LR), classification and regression trees (CART), random forest (RF), gradient boosting (GB), and neural networks (NN) were applied to the collected data. The predictive performance of the models was evaluated using the H-measure and the area under the ROC curve (AUC).Our analysis included 118,650 hospitalizations, of which 4127 (3.5%) led to rehospitalizations via emergency departments. The RF model was the most performant model according to the H-measure (0.29) and the AUC (0.79). The performances of the RF, GB and NN models (H-measures ranged from 0.18 to 0. 29, AUC ranged from 0.74 to 0.79) were better than those of the LR model (H-measure = 0.18, AUC = 0.74); all P values <.001. In contrast, LR was superior to CART (H-measure = 0.16, AUC = 0.70), P < .0001.The use of ML may be an alternative to regression models to predict health outcomes. The integration of ML, particularly the RF algorithm, in the prediction of unplanned rehospitalization may help health service providers target patients at high risk of rehospitalizations and propose effective interventions at the hospital level.
| S-EPMC7717815 | biostudies-literature
Project description:AimsThe LE index (Length of hospitalization plus number of Emergent visits ≤6 months) predicts 30 day all-cause readmission or death following hospitalization for heart failure (HF). We combined N-terminal pro-B type natriuretic peptide (NT-proBNP) levels with the LE index to derive and validate the LENT index for risk prediction at the point of care on the day of hospital discharge.Methods and resultsIn this prospective cohort sub-study of the Patient-centred Care Transitions in HF clinical trial, we used log-binomial regression models with LE index and either admission or discharge NT-proBNP as the predictors and 30 day composite all-cause readmission or death as the primary outcome. No other variables were added to the model. We used regression coefficients to derive the LENT index and bootstrapping analysis for internal validation. There were 772 patients (mean [SD] age 77.0 [12.4] years, 49.9% female). Each increment in the LE index was associated with a 25% increased risk of the primary outcome (RR 1.25, 95% CI 1.16-1.35; C-statistic 0.63). Adjusted for the LE index, every 10-fold increase in admission and discharge NT-proBNP was associated with a 48% (RR 1.48; 95% CI 1.10, 1.99; C-statistic 0.64; net reclassification index [NRI] 0.19) and 56% (RR 1.56; 95% CI 1.08, 2.25; C-statistic 0.64; NRI 0.21) increased risk of the primary outcome, respectively. The predicted probability of the primary outcome increased to a similar extent with incremental LENT, regardless of whether admission or discharge NT-proBNP level was used.ConclusionsThe point-of-care LENT index predicts 30 day composite all-cause readmission or death among patients hospitalized with HF, with improved risk reclassification compared with the LE index. The performance of this simple, 3-variable index - without adjustment for comorbidities - is comparable to complex risk prediction models in HF.
| S-EPMC7835596 | biostudies-literature
Project description:BackgroundAvailable COVID-19 mortality indices are limited to acute inpatient data. Using nationwide medical administrative data available prior to SARS-CoV-2 infection from the US Veterans Health Administration (VA), we developed the VA COVID-19 (VACO) 30-day mortality index and validated the index in two independent, prospective samples.Methods and findingsWe reviewed SARS-CoV-2 testing results within the VA between February 8 and August 18, 2020. The sample was split into a development cohort (test positive between March 2 and April 15, 2020), an early validation cohort (test positive between April 16 and May 18, 2020), and a late validation cohort (test positive between May 19 and July 19, 2020). Our logistic regression model in the development cohort considered demographics (age, sex, race/ethnicity), and pre-existing medical conditions and the Charlson Comorbidity Index (CCI) derived from ICD-10 diagnosis codes. Weights were fixed to create the VACO Index that was then validated by comparing area under receiver operating characteristic curves (AUC) in the early and late validation cohorts and among important validation cohort subgroups defined by sex, race/ethnicity, and geographic region. We also evaluated calibration curves and the range of predictions generated within age categories. 13,323 individuals tested positive for SARS-CoV-2 (median age: 63 years; 91% male; 42% non-Hispanic Black). We observed 480/3,681 (13%) deaths in development, 253/2,151 (12%) deaths in the early validation cohort, and 403/7,491 (5%) deaths in the late validation cohort. Age, multimorbidity described with CCI, and a history of myocardial infarction or peripheral vascular disease were independently associated with mortality-no other individual comorbid diagnosis provided additional information. The VACO Index discriminated mortality in development (AUC = 0.79, 95% CI: 0.77-0.81), and in early (AUC = 0.81 95% CI: 0.78-0.83) and late (AUC = 0.84, 95% CI: 0.78-0.86) validation. The VACO Index allows personalized estimates of 30-day mortality after COVID-19 infection. For example, among those aged 60-64 years, overall mortality was estimated at 9% (95% CI: 6-11%). The Index further discriminated risk in this age stratum from 4% (95% CI: 3-7%) to 21% (95% CI: 12-31%), depending on sex and comorbid disease.ConclusionPrior to infection, demographics and comorbid conditions can discriminate COVID-19 mortality risk overall and within age strata. The VACO Index reproducibly identified individuals at substantial risk of COVID-19 mortality who might consider continuing social distancing, despite relaxed state and local guidelines.
| S-EPMC7657526 | biostudies-literature
Project description:BackgroundGiven the increased attention to sepsis at the population level there is a need to assess hospital performance in the care of sepsis patients using widely-available administrative data. The goal of this study was to develop an administrative risk-adjustment model suitable for profiling hospitals on their 30-day mortality rates for patients with sepsis.MethodsWe conducted a retrospective cohort study using hospital discharge data from general acute care hospitals in Pennsylvania in 2012 and 2013. We identified adult patients with sepsis as determined by validated diagnosis and procedure codes. We developed an administrative risk-adjustment model in 2012 data. We then validated this model in two ways: by examining the stability of performance assessments over time between 2012 and 2013, and by examining the stability of performance assessments in 2012 after the addition of laboratory variables measured on day one of hospital admission.ResultsIn 2012 there were 115,213 sepsis encounters in 152 hospitals. The overall unadjusted mortality rate was 18.5%. The final risk-adjustment model had good discrimination (C-statistic = 0.78) and calibration (slope and intercept of the calibration curve = 0.960 and 0.007, respectively). Based on this model, hospital-specific risk-standardized mortality rates ranged from 12.2 to 24.5%. Comparing performance assessments between years, correlation in risk-adjusted mortality rates was good (Pearson's correlation = 0.53) and only 19.7% of hospitals changed by more than one quintile in performance rankings. Comparing performance assessments after the addition of laboratory variables, correlation in risk-adjusted mortality rates was excellent (Pearson's correlation = 0.93) and only 2.6% of hospitals changed by more than one quintile in performance rankings.ConclusionsA novel claims-based risk-adjustment model demonstrated wide variation in risk-standardized 30-day sepsis mortality rates across hospitals. Individual hospitals' performance rankings were stable across years and after the addition of laboratory data. This model provides a robust way to rank hospitals on sepsis mortality while adjusting for patient risk.
| S-EPMC6458755 | biostudies-literature
Project description:INTRODUCTION:There are currently no robust tools available for risk stratification of emergency department (ED) patients with lower gastrointestinal bleed (LGIB). Our aim was to identify risk factors and develop a preliminary model to predict 30-day serious adverse events among ED LGIB patients. METHODS:We conducted a health records review including adult ED patients with acute LGIB. We used a composite outcome of 30-day all-cause death, recurrent LGIB, need for intervention to control the bleeding, and severe adverse events resulting in intensive care unit admission. One researcher collected data for variables and a second researcher independently collected 10% of the variables for inter-observer reliability. We used backward multivariable logistic regression analysis and SELECTION=SCORE option to create a preliminary risk-stratification tool. We assessed the diagnostic accuracy of the final model. RESULTS:Of 372 patients, 48 experienced an adverse outcome. We found that age ≥75 years, hemoglobin ≤100 g/L, international normalized ratio ≥2.0, ongoing bleed in the ED, and a medical history of colorectal polyps were statistically significant predictors in the multivariable regression analysis. The area under the curve (AUC) for the model was 0.83 (95% confidence interval, 0.77-0.89). We developed a scoring system based on the logistic regression model and found a sensitivity 0.96 (0.90-1.00) and specificity 0.53 (0.48-0.59) for a cut-off score of 1. CONCLUSION:This model showed good ability to differentiate patients with and without serious outcomes as evidenced by the high AUC and sensitivity. The results of this study could be used in the prospective derivation of a clinical decision tool.
| S-EPMC7081856 | biostudies-literature
Project description:BackgroundExisting readmission reduction solutions tend to focus on complementing inpatient care with enhanced care transition and postdischarge interventions. These solutions are initiated near or after discharge, when clinicians' impact on inpatient care is ending. Preventive intervention during hospitalization is an underexplored area that holds potential for reducing readmission risk. However, it is challenging to predict readmission risk at the early stage of hospitalization because few data are available.ObjectiveThe objective of this study was to build an early prediction model of unplanned 30-day hospital readmission using a large and diverse sample. We were also interested in identifying novel readmission risk factors and protective factors.MethodsWe extracted the medical records of 96,550 patients in 205 participating Cerner client hospitals across four US census regions in 2016 from the Health Facts database. The model was built with index admission data that can become available within 24 hours and data from previous encounters up to 1 year before the index admission. The candidate models were evaluated for performance, timeliness, and generalizability. Multivariate logistic regression analysis was used to identify readmission risk factors and protective factors.ResultsWe developed six candidate readmission models with different machine learning algorithms. The best performing model of extreme gradient boosting (XGBoost) achieved an area under the receiver operating characteristic curve of 0.753 on the development data set and 0.742 on the validation data set. By multivariate logistic regression analysis, we identified 14 risk factors and 2 protective factors of readmission that have never been reported.ConclusionsThe performance of our model is better than that of the most widely used models in US health care settings. This model can help clinicians identify readmission risk at the early stage of hospitalization so that they can pay extra attention during the care process of high-risk patients. The 14 novel risk factors and 2 novel protective factors can aid understanding of the factors associated with readmission.
| S-EPMC8077543 | biostudies-literature
Project description:PurposeTo develop prediction models for short-term mortality risk assessment following colorectal cancer surgery.MethodsData was harmonized from four Danish observational health databases into the Observational Medical Outcomes Partnership Common Data Model. With a data-driven approach using the Least Absolute Shrinkage and Selection Operator logistic regression on preoperative data, we developed 30-day, 90-day, and 1-year mortality prediction models. We assessed discriminative performance using the area under the receiver operating characteristic and precision-recall curve and calibration using calibration slope, intercept, and calibration-in-the-large. We additionally assessed model performance in subgroups of curative, palliative, elective, and emergency surgery.ResultsA total of 57,521 patients were included in the study population, 51.1% male and with a median age of 72 years. The model showed good discrimination with an area under the receiver operating characteristic curve of 0.88, 0.878, and 0.861 for 30-day, 90-day, and 1-year mortality, respectively, and a calibration-in-the-large of 1.01, 0.99, and 0.99. The overall incidence of mortality were 4.48% for 30-day mortality, 6.64% for 90-day mortality, and 12.8% for 1-year mortality, respectively. Subgroup analysis showed no improvement of discrimination or calibration when separating the cohort into cohorts of elective surgery, emergency surgery, curative surgery, and palliative surgery.ConclusionWe were able to train prediction models for the risk of short-term mortality on a data set of four combined national health databases with good discrimination and calibration. We found that one cohort including all operated patients resulted in better performing models than cohorts based on several subgroups.
| S-EPMC10904562 | biostudies-literature
Project description:Background and Purpose- Kidney dysfunction is common among patients hospitalized for ischemic stroke. Understanding the association of kidney disease with poststroke outcomes is important to properly adjust for case mix in outcome studies, payment models and risk-standardized hospital readmission rates. Methods- In this cohort study of fee-for-service Medicare patients admitted with ischemic stroke to 1579 Get With The Guidelines-Stroke participating hospitals between 2009 and 2014, adjusted multivariable Cox proportional hazards models were used to determine the independent associations of estimated glomerular filtration rate (eGFR) and dialysis status with 30-day and 1-year postdischarge mortality and rehospitalizations. Results- Of 204?652 patients discharged alive (median age [25th-75th percentile] 80 years [73.0-86.0], 57.6% women, 79.8% white), 48.8% had an eGFR ?60, 26.5% an eGFR 45 to 59, 16.3% an eGFR 30 to 44, 5.1% an eGFR 15 to 29, 0.6% an eGFR <15 without dialysis, and 2.8% were receiving dialysis. Compared with eGFR ?60, and after adjusting for relevant variables, eGFR <45 was associated with increased 30-day mortality with the risk highest among those with eGFR <15 without dialysis (hazard ratio [HR], 2.09; 95% CI, 1.66-2.63). An eGFR <60 was associated with increased 1-year poststroke mortality that was highest among patients on dialysis (HR, 2.65; 95% CI, 2.49-2.81). Dialysis was also associated with the highest 30-day and 1-year rehospitalization rates (HR, 2.10; 95% CI, 1.95-2.26 and HR, 2.55; 95% CI, 2.44-2.66, respectively) and 30-day and 1-year composite of mortality and rehospitalization (HR, 2.04; 95% CI, 1.90-2.18 and HR, 2.46; 95% CI, 2.36-2.56, respectively). Conclusions- Within the first year after index hospitalization for ischemic stroke, eGFR and dialysis status on admission are associated with poststroke mortality and hospital readmissions. Kidney function should be included in risk-stratification models for poststroke outcomes.
| S-EPMC6338440 | biostudies-literature
Project description:ObjectiveDelirium is associated with poor outcomes among critically ill patients. However, it is not well characterized among patients with ischemic or hemorrhagic stroke (IS and HS). We provide the population-level frequency of in-hospital delirium and assess its association with in-hospital outcomes and with 30-day readmission among IS and HS patients.MethodsWe analyzed Nationwide in-hospital and readmission data for years 2010-2015 and identified stroke patients using ICD-9 codes. Delirium was identified using validated algorithms. Outcomes were in-hospital mortality, length of stay, unfavorable discharge disposition, and 30-day readmission. We used survey design logistic regression methods to provide national estimates of proportions and 95% confidence intervals (CI) for delirium, and odds ratios (OR) for association between delirium and poor outcomes.ResultsWe identified 3,107,437 stroke discharges of whom 7.45% were coded to have delirium. This proportion significantly increased between 2010 (6.3%) and 2015 (8.7%) (aOR, 95% CI: 1.04, 1.03-1.05). Delirium proportion was higher among HS patients (ICH: 10.0%, SAH: 9.8%) as compared to IS patients (7.0%). Delirious stroke patients had higher in-hospital mortality (12.3% vs. 7.8%), longer in-hospital stay (11.6 days vs. 7.3 days) and a significantly greater adjusted risk of 30-day-readmission (16.7%) as compared to those without delirium (12.2%) (aRR, 95% CI: 1.13, 1.11-1.15). Upon readmission, patients with delirium at initial admission continued to have a longer length of stay (7.7 days vs. 6.6 days) and a higher in-hospital mortality (9.3% vs. 6.4%).ConclusionDelirium identified through claims data in stroke patients is independently associated with poor in-hospital outcomes both at index admission and readmission. Identification and management of delirium among stroke patients provides an opportunity to improve outcomes.
| S-EPMC6855446 | biostudies-literature
Project description:Backgrounds We aimed to develop and validate machine learning (ML) models for 30-day stroke mortality for mortality risk stratification and as benchmarking models for quality improvement in stroke care. Methods Data from the UK Sentinel Stroke National Audit Program between 2013 to 2019 were used. Models were developed using XGBoost, Logistic Regression (LR), LR with elastic net with/without interaction terms using 80% randomly selected admissions from 2013 to 2018, validated on the 20% remaining admissions, and temporally validated on 2019 admissions. The models were developed with 30 variables. A reference model was developed using LR and 4 variables. Performances of all models was evaluated in terms of discrimination, calibration, reclassification, Brier scores and Decision-curves. Results In total, 488,497 stroke patients with a 12.3% 30-day mortality rate were included in the analysis. In 2019 temporal validation set, XGBoost model obtained the lowest Brier score (0.069 (95% CI: 0.068–0.071)) and the highest area under the ROC curve (AUC) (0.895 (95% CI: 0.891–0.900)) which outperformed LR reference model by 0.04 AUC (p < 0.001) and LR with elastic net and interaction term model by 0.003 AUC (p < 0.001). All models were perfectly calibrated for low (< 5%) and moderate risk groups (5–15%) and ≈1% underestimation for high-risk groups (> 15%). The XGBoost model reclassified 1648 (8.1%) low-risk cases by the LR reference model as being moderate or high-risk and gained the most net benefit in decision curve analysis. Conclusions All models with 30 variables are potentially useful as benchmarking models in stroke-care quality improvement with ML slightly outperforming others. Supplementary Information The online version contains supplementary material available at 10.1186/s12883-022-02722-1.
| S-EPMC9137068 | biostudies-literature