Predicting readmission and death after hospital discharge: a comparison of conventional frailty measurement with an electronic health record-based score.
Ontology highlight
ABSTRACT: Background
frailty measurement may identify patients at risk of decline after hospital discharge, but many measures require specialist review and/or additional testing.Objective
to compare validated frailty tools with routine electronic health record (EHR) data at hospital discharge, for associations with readmission or death.Design
observational cohort study.Setting
hospital ward.Subjects
consented cardiology inpatients ≥70 years old within 24 hours of discharge.Methods
patients underwent Fried, Short Physical Performance Battery (SPPB), PRISMA-7 and Clinical Frailty Scale (CFS) assessments. An EHR risk score was derived from the proportion of 31 possible frailty markers present. Electronic follow-up was completed for a primary outcome of 90-day readmission or death. Secondary outcomes were mortality and days alive at home ('home time') at 12 months.Results
in total, 186 patients were included (79 ± 6 years old, 64% males). The primary outcome occurred in 55 (30%) patients. Fried (hazard ratio [HR] 1.47 per standard deviation [SD] increase, 95% confidence interval [CI] 1.18-1.81, P < 0.001), CFS (HR 1.24 per SD increase, 95% CI 1.01-1.51, P = 0.04) and EHR risk scores (HR 1.35 per SD increase, 95% CI 1.02-1.78, P = 0.04) were independently associated with the primary outcome after adjustment for age, sex and co-morbidity, but the SPPB and PRISMA-7 were not. The EHR risk score was independently associated with mortality and home time at 12 months.Conclusions
frailty measurement at hospital discharge identifies patients at risk of poorer outcomes. An EHR-based risk score appeared equivalent to validated frailty tools and may be automated to screen patients at scale, but this requires further validation.
SUBMITTER: Tew YY
PROVIDER: S-EPMC8437069 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:BackgroundIdentifying patients at high risk for readmission early during hospitalization may aid efforts in reducing readmissions. We sought to develop an early readmission risk predictive model using automated clinical data available at hospital admission.MethodsWe developed an early readmission risk model using a derivation cohort and validated the model with a validation cohort. We used a published Acute Laboratory Risk of Mortality Score as an aggregated measure of clinical severity at admission and the number of hospital discharges in the previous 90 days as a measure of disease progression. We then evaluated the administrative data-enhanced model by adding principal and secondary diagnoses and other variables. We examined the c-statistic change when additional variables were added to the model.ResultsThere were 1,195,640 adult discharges from 70 hospitals with 39.8% male and the median age of 63 years (first and third quartile: 43, 78). The 30-day readmission rate was 11.9% (n=142,211). The early readmission model yielded a graded relationship of readmission and the Acute Laboratory Risk of Mortality Score and the number of previous discharges within 90 days. The model c-statistic was 0.697 with good calibration. When administrative variables were added to the model, the c-statistic increased to 0.722.ConclusionsAutomated clinical data can generate a readmission risk score early at hospitalization with fair discrimination. It may have applied value to aid early care transition. Adding administrative data increases predictive accuracy. The administrative data-enhanced model may be used for hospital comparison and outcome research.
| S-EPMC5318151 | biostudies-literature
Project description:RationalePatients transferred from the intensive care unit to the wards who are later readmitted to the intensive care unit have increased length of stay, healthcare expenditure, and mortality compared with those who are never readmitted. Improving risk stratification for patients transferred to the wards could have important benefits for critically ill hospitalized patients.ObjectivesWe aimed to use a machine-learning technique to derive and validate an intensive care unit readmission prediction model with variables available in the electronic health record in real time and compare it to previously published algorithms.MethodsThis observational cohort study was conducted at an academic hospital in the United States with approximately 600 inpatient beds. A total of 24,885 intensive care unit transfers to the wards were included, with 14,962 transfers (60%) in the training cohort and 9,923 transfers (40%) in the internal validation cohort. Patient characteristics, nursing assessments, International Classification of Diseases, Ninth Revision codes from prior admissions, medications, intensive care unit interventions, diagnostic tests, vital signs, and laboratory results were extracted from the electronic health record and used as predictor variables in a gradient-boosted machine model. Accuracy for predicting intensive care unit readmission was compared with the Stability and Workload Index for Transfer score and Modified Early Warning Score in the internal validation cohort and also externally using the Medical Information Mart for Intensive Care database (n = 42,303 intensive care unit transfers).ResultsEleven percent (2,834) of discharges to the wards were later readmitted to the intensive care unit. The machine-learning-derived model had significantly better performance (area under the receiver operating curve, 0.76) than either the Stability and Workload Index for Transfer score (area under the receiver operating curve, 0.65), or Modified Early Warning Score (area under the receiver operating curve, 0.58; P value < 0.0001 for all comparisons). At a specificity of 95%, the derived model had a sensitivity of 28% compared with 15% for Stability and Workload Index for Transfer score and 7% for the Modified Early Warning Score. Accuracy improvements with the derived model over Modified Early Warning Score and Stability and Workload Index for Transfer were similar in the Medical Information Mart for Intensive Care-III cohort.ConclusionsA machine learning approach to predicting intensive care unit readmission was significantly more accurate than previously published algorithms in both our internal validation and the Medical Information Mart for Intensive Care-III cohort. Implementation of this approach could target patients who may benefit from additional time in the intensive care unit or more frequent monitoring after transfer to the hospital ward.
| S-EPMC6207111 | biostudies-literature
Project description:Natural language processing tools allow the characterization of sentiment--that is, terms expressing positive and negative emotion--in text. Applying such tools to electronic health records may provide insight into meaningful patient or clinician features not captured in coded data alone. We performed sentiment analysis on 2,484 hospital discharge notes for 2,010 individuals from a psychiatric inpatient unit, as well as 20,859 hospital discharges for 15,011 individuals from general medical units, in a large New England health system between January 2011 and 2014. The primary measures of sentiment captured intensity of subjective positive or negative sentiment expressed in the discharge notes. Mean scores were contrasted between sociodemographic and clinical groups in mixed effects regression models. Discharge note sentiment was then examined for association with risk for readmission in Cox regression models. Discharge notes for individuals with greater medical comorbidity were modestly but significantly lower in positive sentiment among both psychiatric and general medical cohorts (p<0.001 in each). Greater positive sentiment at discharge was associated with significantly decreased risk of hospital readmission in each cohort (~12% decrease per standard deviation above the mean). Automated characterization of discharge notes in terms of sentiment identifies differences between sociodemographic groups, as well as in clinical outcomes, and is not explained by differences in diagnosis. Clinician sentiment merits investigation to understand why and how it reflects or impacts outcomes.
| S-EPMC4547711 | biostudies-literature
Project description:BackgroundAccurate, timely and automated identification of patients at high risk for severe clinical deterioration using readily available clinical information in the electronic medical record (EMR) could inform health systems to target scarce resources and save lives.MethodsWe identified 7,466 patients admitted to a large, public, urban academic hospital between May 2009 and March 2010. An automated clinical prediction model for out of intensive care unit (ICU) cardiopulmonary arrest and unexpected death was created in the derivation sample (50% randomly selected from total cohort) using multivariable logistic regression. The automated model was then validated in the remaining 50% from the total cohort (validation sample). The primary outcome was a composite of resuscitation events, and death (RED). RED included cardiopulmonary arrest, acute respiratory compromise and unexpected death. Predictors were measured using data from the previous 24 hours. Candidate variables included vital signs, laboratory data, physician orders, medications, floor assignment, and the Modified Early Warning Score (MEWS), among other treatment variables.ResultsRED rates were 1.2% of patient-days for the total cohort. Fourteen variables were independent predictors of RED and included age, oxygenation, diastolic blood pressure, arterial blood gas and laboratory values, emergent orders, and assignment to a high risk floor. The automated model had excellent discrimination (c-statistic=0.85) and calibration and was more sensitive (51.6% and 42.2%) and specific (94.3% and 91.3%) than the MEWS alone. The automated model predicted RED 15.9 hours before they occurred and earlier than Rapid Response Team (RRT) activation (5.7 hours prior to an event, p=0.003)ConclusionAn automated model harnessing EMR data offers great potential for identifying RED and was superior to both a prior risk model and the human judgment-driven RRT.
| S-EPMC3599266 | biostudies-literature
Project description:The ability to predict psychiatric readmission would facilitate the development of interventions to reduce this risk, a major driver of psychiatric health-care costs. The symptoms or characteristics of illness course necessary to develop reliable predictors are not available in coded billing data, but may be present in narrative electronic health record (EHR) discharge summaries. We identified a cohort of individuals admitted to a psychiatric inpatient unit between 1994 and 2012 with a principal diagnosis of major depressive disorder, and extracted inpatient psychiatric discharge narrative notes. Using these data, we trained a 75-topic Latent Dirichlet Allocation (LDA) model, a form of natural language processing, which identifies groups of words associated with topics discussed in a document collection. The cohort was randomly split to derive a training (70%) and testing (30%) data set, and we trained separate support vector machine models for baseline clinical features alone, baseline features plus common individual words and the above plus topics identified from the 75-topic LDA model. Of 4687 patients with inpatient discharge summaries, 470 were readmitted within 30 days. The 75-topic LDA model included topics linked to psychiatric symptoms (suicide, severe depression, anxiety, trauma, eating/weight and panic) and major depressive disorder comorbidities (infection, postpartum, brain tumor, diarrhea and pulmonary disease). By including LDA topics, prediction of readmission, as measured by area under receiver-operating characteristic curves in the testing data set, was improved from baseline (area under the curve 0.618) to baseline+1000 words (0.682) to baseline+75 topics (0.784). Inclusion of topics derived from narrative notes allows more accurate discrimination of individuals at high risk for psychiatric readmission in this cohort. Topic modeling and related approaches offer the potential to improve prediction using EHRs, if generalizability can be established in other clinical cohorts.
| S-EPMC5315537 | biostudies-literature
Project description:Frailty, a clinical syndrome of decreased physiologic reserve and dysregulation in multiple physiologic systems, is associated with increased risk for adverse outcomes.The aim of this retrospective, cross-sectional, correlational study was to characterize frailty in older adults admitted to a tertiary-care hospital using a biopsychosocial frailty assessment and to determine associations between frailty and time to in-hospital mortality and 30-day rehospitalization.The sample included 278 patients ?55 years old admitted to medicine units. Frailty was determined using clinical data from the electronic health record (EHR) for symptoms, syndromes, and conditions and laboratory data for four serum biomarkers. A frailty risk score (FRS) was created from 16 risk factors, and relationships between the FRS and outcomes were examined.The mean age of the sample was 70.2 years and mean FRS was 9.4 ( SD, 2.2). Increased FRS was significantly associated with increased risk of death (hazard ratio = 1.77-2.27 for 3 days ? length of stay (LOS) ?7 days), but depended upon LOS ( p < .001). Frailty was marginally associated with rehospitalization for those who did not die in hospital (adjusted odds ratio = 1.18, p = .086, area under the curve [AUC] = 0.66, 95% confidence interval for AUC = [0.57, 0.76]).Clinical data in the EHR can be used for frailty assessment. Informatics may facilitate data aggregation and decision support. Because frailty is potentially preventable and treatable, early detection is crucial to delivery of tailored interventions and optimal patient outcomes.
| S-EPMC5801547 | biostudies-literature
Project description:BackgroundWe aimed to assess the utility of the combination of the mini-mental state examination (MMSE) + clock drawing test (CDT) and the Fried phenotype for predicting non-elective hospital readmission or death within 6 months in elderly inpatients with cardiovascular disease (CVD).MethodsA single-center prospective cohort was conducted from September 2018 to February 2019. Inpatients ≥65 years old were recruited. Predictive validity was tested using a Cox proportional hazards regression model analysis, and the discriminative ability was evaluated by the receiver operating characteristic (ROC) curve.ResultsA total of 542 patients were included. Overall, 12% (64/542) screened positive for cognitive impairment, 16% (86/542) were physically frail and 8% (44/542) had cognitive impairment combined with physical frailty, showing an older age (P < 0.001) and a lower education level (P < 0.001) than physically frail patients. A total of 113 patients (20.9%) died or were readmitted at 6 months. Frail participants with a normal (hazard ratio [HR]: 1.73, 95% confidence interval [CI]: 1.06-2.82, P = 0.028) or impaired cognition (HR: 2.50, 95% CI: 1.27-4.91, P = 0.008) had a higher risk of non-elective hospital readmission or death than robust patients after adjusting for the age, sex, education level, marital status, the presence of diabetes mellitus, heart failure, and history of stroke. The area under the ROC curve (AUC) showed that the discriminative ability in relation to 6 months readmission and death for the MMSE + CDT + Fried phenotype was 0.65 (95% CI: 0.60-0.71), and the AUC for men was 0.71 (95% CI: 0.63-0.78), while that for women was 0.60 (95% CI: 0.51-0.69).ConclusionsAccounting for cognitive impairment in the frailty phenotype may allow for the better prediction of non-elective hospital readmission or death in elderly inpatients with CVD in the short term.Trial registrationChiCTR1800017204; date of registration: 07/18/2018.
| S-EPMC7309999 | biostudies-literature
Project description:In a general inpatient population, we predicted patient-specific medication orders based on structured information in the electronic health record (EHR). Data on over three million medication orders from an academic medical center were used to train two machine-learning models: A deep learning sequence model and a logistic regression model. Both were compared with a baseline that ranked the most frequently ordered medications based on a patient's discharge hospital service and amount of time since admission. Models were trained to predict from 990 possible medications at the time of order entry. Fifty-five percent of medications ordered by physicians were ranked in the sequence model's top-10 predictions (logistic model: 49%) and 75% ranked in the top-25 (logistic model: 69%). Ninety-three percent of the sequence model's top-10 prediction sets contained at least one medication that physicians ordered within the next day. These findings demonstrate that medication orders can be predicted from information present in the EHR.
| S-EPMC7325318 | biostudies-literature
Project description:Backgroundfrailty is an especially problematic expression of population ageing. International guidelines recommend routine identification of frailty to provide evidence-based treatment, but currently available tools require additional resource.Objectivesto develop and validate an electronic frailty index (eFI) using routinely available primary care electronic health record data.Study design and settingretrospective cohort study. Development and internal validation cohorts were established using a randomly split sample of the ResearchOne primary care database. External validation cohort established using THIN database.Participantspatients aged 65-95, registered with a ResearchOne or THIN practice on 14 October 2008.Predictorswe constructed the eFI using the cumulative deficit frailty model as our theoretical framework. The eFI score is calculated by the presence or absence of individual deficits as a proportion of the total possible. Categories of fit, mild, moderate and severe frailty were defined using population quartiles.Outcomesoutcomes were 1-, 3- and 5-year mortality, hospitalisation and nursing home admission.Statistical analysishazard ratios (HRs) were estimated using bivariate and multivariate Cox regression analyses. Discrimination was assessed using receiver operating characteristic (ROC) curves. Calibration was assessed using pseudo-R(2) estimates.Resultswe include data from a total of 931,541 patients. The eFI incorporates 36 deficits constructed using 2,171 CTV3 codes. One-year adjusted HR for mortality was 1.92 (95% CI 1.81-2.04) for mild frailty, 3.10 (95% CI 2.91-3.31) for moderate frailty and 4.52 (95% CI 4.16-4.91) for severe frailty. Corresponding estimates for hospitalisation were 1.93 (95% CI 1.86-2.01), 3.04 (95% CI 2.90-3.19) and 4.73 (95% CI 4.43-5.06) and for nursing home admission were 1.89 (95% CI 1.63-2.15), 3.19 (95% CI 2.73-3.73) and 4.76 (95% CI 3.92-5.77), with good to moderate discrimination but low calibration estimates.Conclusionsthe eFI uses routine data to identify older people with mild, moderate and severe frailty, with robust predictive validity for outcomes of mortality, hospitalisation and nursing home admission. Routine implementation of the eFI could enable delivery of evidence-based interventions to improve outcomes for this vulnerable group.
| S-EPMC4846793 | biostudies-literature
Project description:AimsThis study aimed to review the performance of machine learning (ML) methods compared with conventional statistical models (CSMs) for predicting readmission and mortality in patients with heart failure (HF) and to present an approach to formally evaluate the quality of studies using ML algorithms for prediction modelling.Methods and resultsFollowing Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines, we performed a systematic literature search using MEDLINE, EPUB, Cochrane CENTRAL, EMBASE, INSPEC, ACM Library, and Web of Science. Eligible studies included primary research articles published between January 2000 and July 2020 comparing ML and CSMs in mortality and readmission prognosis of initially hospitalized HF patients. Data were extracted and analysed by two independent reviewers. A modified CHARMS checklist was developed in consultation with ML and biostatistics experts for quality assessment and was utilized to evaluate studies for risk of bias. Of 4322 articles identified and screened by two independent reviewers, 172 were deemed eligible for a full-text review. The final set comprised 20 articles and 686 842 patients. ML methods included random forests (n = 11), decision trees (n = 5), regression trees (n = 3), support vector machines (n = 9), neural networks (n = 12), and Bayesian techniques (n = 3). CSMs included logistic regression (n = 16), Cox regression (n = 3), or Poisson regression (n = 3). In 15 studies, readmission was examined at multiple time points ranging from 30 to 180 day readmission, with the majority of studies (n = 12) presenting prediction models for 30 day readmission outcomes. Of a total of 21 time-point comparisons, ML-derived c-indices were higher than CSM-derived c-indices in 16 of the 21 comparisons. In seven studies, mortality was examined at 9 time points ranging from in-hospital mortality to 1 year survival; of these nine, seven reported higher c-indices using ML. Two of these seven studies reported survival analyses utilizing random survival forests in their ML prediction models. Both reported higher c-indices when using ML compared with CSMs. A limitation of studies using ML techniques was that the majority were not externally validated, and calibration was rarely assessed. In the only study that was externally validated in a separate dataset, ML was superior to CSMs (c-indices 0.913 vs. 0.835).ConclusionsML algorithms had better discrimination than CSMs in most studies aiming to predict risk of readmission and mortality in HF patients. Based on our review, there is a need for external validation of ML-based studies of prediction modelling. We suggest that ML-based studies should also be evaluated using clinical quality standards for prognosis research. Registration: PROSPERO CRD42020134867.
| S-EPMC7835549 | biostudies-literature