RESUMEN
RATIONALE & OBJECTIVE: Acute kidney injury (AKI) carries high rates of morbidity and mortality. This study quantified various short- and long-term outcomes after hospitalization with AKI. STUDY DESIGN: Retrospective propensity score (PS)-matched cohort study. SETTING & PARTICIPANTS: Optum Clinformatics, a national claims database, was used to identify patients hospitalized with and without an AKI discharge diagnosis between January 2007 and September 2020. EXPOSURE: Among patients with prior continuous enrollment for at least 2years without AKI hospitalization, 471,176 patients hospitalized with AKI were identified and PS-matched to 471,176 patients hospitalized without AKI. OUTCOME(S): All-cause and selected-cause rehospitalizations and mortality 90 and 365 days after index hospitalization. ANALYTICAL APPROACH: After PS matching, rehospitalization and death incidences were estimated using the cumulative incidence function method and compared using Gray's test. The association of AKI hospitalization with each outcome was tested using Cox models for all-cause mortality and, with mortality as competing risk, cause-specific hazard modeling for all-cause and selected-cause rehospitalization. Overall and stratified analyses were performed to evaluate for interaction between an AKI hospitalization and preexisting chronic kidney disease (CKD). RESULTS: After PS matching, AKI was associated with higher rates of rehospitalization for any cause (hazard ratio [HR], 1.62; 95% CI, 1.60-1.65), end-stage renal disease (HR, 6.21; 95% CI, 1.04-36.92), heart failure (HR, 2.81; 95% CI, 2.66, 2.97), sepsis (HR, 2.62; 95% CI, 2.49-2.75), pneumonia (HR, 1.47; 95% CI, 1.37-1.57), myocardial infarction (HR, 1.48; 95% CI, 1.33-1.65), and volume depletion (HR, 1.64; 95% CI, 1.37-1.96) at 90 days after discharge compared with the group without AKI, with similar findings at 365 days. Mortality rate was higher in the group with AKI than in the group without AKI at 90 (HR, 2.66; 95% CI, 2.61-2.72) and 365 days (HR, 2.11; 95% CI, 2.08-2.14). The higher risk of outcomes persisted when participants were stratified by CKD status (P<0.01). LIMITATIONS: Causal associations between AKI and the reported outcomes cannot be inferred. CONCLUSIONS: AKI during hospitalization in patients with and without CKD is associated with increased risk of 90- and 365-day all-cause/selected-cause rehospitalization and death.
Asunto(s)
Lesión Renal Aguda , Insuficiencia Renal Crónica , Humanos , Readmisión del Paciente , Estudios de Cohortes , Estudios Retrospectivos , Hospitalización , Insuficiencia Renal Crónica/epidemiología , Lesión Renal Aguda/diagnóstico , Factores de RiesgoRESUMEN
Injury narratives are now available real time and include useful information for injury surveillance and prevention. However, manual classification of the cause or events leading to injury found in large batches of narratives, such as workers compensation claims databases, can be prohibitive. In this study we compare the utility of four machine learning algorithms (Naïve Bayes, Single word and Bi-gram models, Support Vector Machine and Logistic Regression) for classifying narratives into Bureau of Labor Statistics Occupational Injury and Illness event leading to injury classifications for a large workers compensation database. These algorithms are known to do well classifying narrative text and are fairly easy to implement with off-the-shelf software packages such as Python. We propose human-machine learning ensemble approaches which maximize the power and accuracy of the algorithms for machine-assigned codes and allow for strategic filtering of rare, emerging or ambiguous narratives for manual review. We compare human-machine approaches based on filtering on the prediction strength of the classifier vs. agreement between algorithms. Regularized Logistic Regression (LR) was the best performing algorithm alone. Using this algorithm and filtering out the bottom 30% of predictions for manual review resulted in high accuracy (overall sensitivity/positive predictive value of 0.89) of the final machine-human coded dataset. The best pairings of algorithms included Naïve Bayes with Support Vector Machine whereby the triple ensemble NBSW=NBBI-GRAM=SVM had very high performance (0.93 overall sensitivity/positive predictive value and high accuracy (i.e. high sensitivity and positive predictive values)) across both large and small categories leaving 41% of the narratives for manual review. Integrating LR into this ensemble mix improved performance only slightly. For large administrative datasets we propose incorporation of methods based on human-machine pairings such as we have done here, utilizing readily-available off-the-shelf machine learning techniques and resulting in only a fraction of narratives that require manual review. Human-machine ensemble methods are likely to improve performance over total manual coding.
Asunto(s)
Accidentes de Trabajo/estadística & datos numéricos , Algoritmos , Bases de Datos Factuales/estadística & datos numéricos , Vigilancia en Salud Pública/métodos , Heridas y Lesiones/epidemiología , Teorema de Bayes , Codificación Clínica/métodos , Humanos , Modelos Logísticos , Aprendizaje Automático , Modelos Teóricos , Narración , Indemnización para Trabajadores/estadística & datos numéricosRESUMEN
INTRODUCTION: Falls are the leading cause of unintentional injuries in the U.S.; however, national estimates for all community-dwelling adults are lacking. This study estimated the national incidence of falls and fall-related injuries among community-dwelling U.S. adults by age and gender and the trends in fall-related injuries across the adult life span. METHODS: Nationally representative data from the National Health Interview Survey (NHIS) 2008 Balance and Dizziness supplement was used to develop national estimates of falls, and pooled data from the NHIS was used to calculate estimates of fall-related injuries in the U.S. and related trends from 2004-2013. Costs of unintentional fall-related injuries were extracted from the CDC's Web-based Injury Statistics Query and Reporting System. RESULTS: Twelve percent of community-dwelling U.S. adults reported falling in the previous year for a total estimate of 80 million falls at a rate of 37.2 falls per 100 person-years. On average, 9.9 million fall-related injuries occurred each year with a rate of 4.38 fall-related injuries per 100 person-years. In the previous three months, 2.0% of older adults (65+), 1.1% of middle-aged adults (45-64) and 0.7% of young adults (18-44) reported a fall-related injury. Of all fall-related injuries among community-dwelling adults, 32.3% occurred among older adults, 35.3% among middle-aged adults and 32.3% among younger adults. The age-adjusted rate of fall-related injuries increased 4% per year among older women (95% CI 1%-7%) from 2004 to 2013. Among U.S. adults, the total lifetime cost of annual unintentional fall-related injuries that resulted in a fatality, hospitalization or treatment in an emergency department was 111 billion U.S. dollars in 2010. CONCLUSIONS: Falls and fall-related injuries represent a significant health and safety problem for adults of all ages. The findings suggest that adult fall prevention efforts should consider the entire adult lifespan to ensure a greater public health benefit.
Asunto(s)
Accidentes por Caídas , Heridas y Lesiones/etiología , Adolescente , Adulto , Anciano , Humanos , Persona de Mediana Edad , Estados UnidosRESUMEN
OBJECTIVE: Vast amounts of injury narratives are collected daily and are available electronically in real time and have great potential for use in injury surveillance and evaluation. Machine learning algorithms have been developed to assist in identifying cases and classifying mechanisms leading to injury in a much timelier manner than is possible when relying on manual coding of narratives. The aim of this paper is to describe the background, growth, value, challenges and future directions of machine learning as applied to injury surveillance. METHODS: This paper reviews key aspects of machine learning using injury narratives, providing a case study to demonstrate an application to an established human-machine learning approach. RESULTS: The range of applications and utility of narrative text has increased greatly with advancements in computing techniques over time. Practical and feasible methods exist for semiautomatic classification of injury narratives which are accurate, efficient and meaningful. The human-machine learning approach described in the case study achieved high sensitivity and PPV and reduced the need for human coding to less than a third of cases in one large occupational injury database. CONCLUSIONS: The last 20â years have seen a dramatic change in the potential for technological advancements in injury surveillance. Machine learning of 'big injury narrative data' opens up many possibilities for expanded sources of data which can provide more comprehensive, ongoing and timely surveillance to inform future injury prevention policy and practice.
Asunto(s)
Accidentes de Trabajo/clasificación , Minería de Datos/métodos , Aprendizaje Automático , Traumatismos Ocupacionales/clasificación , Vigilancia de la Población/métodos , Bases de Datos Factuales , Humanos , Modelos TeóricosRESUMEN
INTRODUCTION: Although occupational injuries are among the leading causes of death and disability around the world, the burden due to occupational injuries has historically been under-recognized, obscuring the need to address a major public health problem. METHODS: We established the Liberty Mutual Workplace Safety Index (LMWSI) to provide a reliable annual metric of the leading causes of the most serious workplace injuries in the United States based on direct workers compensation (WC) costs. RESULTS: More than $600 billion in direct WC costs were spent on the most disabling compensable non-fatal injuries and illnesses in the United States from 1998 to 2010. The burden in 2010 remained similar to the burden in 1998 in real terms. The categories of overexertion ($13.6B, 2010) and fall on same level ($8.6B, 2010) were consistently ranked 1st and 2nd. PRACTICAL APPLICATION: The LMWSI was created to establish the relative burdens of events leading to work-related injury so they could be better recognized and prioritized. Such a ranking might be used to develop research goals and interventions to reduce the burden of workplace injury in the United States.
Asunto(s)
Accidentes por Caídas/economía , Accidentes de Trabajo/economía , Personas con Discapacidad , Gastos en Salud , Enfermedades Profesionales/economía , Traumatismos Ocupacionales/economía , Seguridad/economía , Adulto , Costos de la Atención en Salud , Humanos , Salud Pública , Estados Unidos , Trabajo , Indemnización para Trabajadores/economía , Lugar de Trabajo/economíaRESUMEN
Public health surveillance programs in the U.S. are undergoing landmark changes with the availability of electronic health records and advancements in information technology. Injury narratives gathered from hospital records, workers compensation claims or national surveys can be very useful for identifying antecedents to injury or emerging risks. However, classifying narratives manually can become prohibitive for large datasets. The purpose of this study was to develop a human-machine system that could be relatively easily tailored to routinely and accurately classify injury narratives from large administrative databases such as workers compensation. We used a semi-automated approach based on two Naïve Bayesian algorithms to classify 15,000 workers compensation narratives into two-digit Bureau of Labor Statistics (BLS) event (leading to injury) codes. Narratives were filtered out for manual review if the algorithms disagreed or made weak predictions. This approach resulted in an overall accuracy of 87%, with consistently high positive predictive values across all two-digit BLS event categories including the very small categories (e.g., exposure to noise, needle sticks). The Naïve Bayes algorithms were able to identify and accurately machine code most narratives leaving only 32% (4853) for manual review. This strategy substantially reduces the need for resources compared with manual review alone.
Asunto(s)
Accidentes de Trabajo/estadística & datos numéricos , Bases de Datos Factuales/estadística & datos numéricos , Vigilancia en Salud Pública/métodos , Indemnización para Trabajadores/estadística & datos numéricos , Heridas y Lesiones/epidemiología , Adulto , Anciano , Algoritmos , Teorema de Bayes , Codificación Clínica , Femenino , Humanos , Incidencia , Masculino , Persona de Mediana Edad , Narración , Prevalencia , Reproducibilidad de los Resultados , Estados Unidos/epidemiologíaRESUMEN
OBJECTIVES: Slips and falls are a leading cause of injury at work. Several studies have indicated that slip-resistant shoes can reduce the risk of occupational slips and falls. Few studies, however, have examined the determinants of slip-resistant shoe use. This study examined the individual and workplace factors associated with slip-resistant shoe use. METHODS: 475 workers from 36 limited-service restaurants in the USA participated in a study of workplace slipping. Demographic and job characteristic information about each participant was collected. Restaurant managers provided information on whether slip-resistant shoes were provided and paid for by the employer and whether any guidance was given regarding slip-resistant shoe use when they were not provided. Kitchen floor coefficient of friction was measured. Slip-resistant status of the shoes was determined by noting the presence of a 'slip-resistant' marking on the sole. Poisson regression with robust SE was used to calculate prevalence ratios. RESULTS: 320 participants wore slip-resistant shoes (67%). In the multivariate analysis, the prevalence of slip-resistant shoe use was lowest in 15-19-year age group. Women were more likely to wear slip-resistant shoes (prevalence ratio 1.18, 95% CI 1.07 to 1.31). The prevalence of slip-resistant shoe use was lower when no guidance regarding slip-resistant shoes was given as compared to when they were provided by the employer (prevalence ratio 0.66, 95% CI 0.55 to 0.79). Education level, job tenure and the mean coefficient of friction had no significant effects on the use of slip-resistant shoes. CONCLUSION: Provision of slip-resistant shoes was the strongest predictor of their use. Given their effectiveness and low cost, employers should consider providing slip-resistant shoes at work.