Trends in tobacco use and tobacco cessation counselling codes among Medicare beneficiaries, 2001-2014

Machine learning to identify chronic cough from administrative claims data

Accurate identification of patient populations is an essential component of clinical research, especially for medical conditions such as chronic cough that are inconsistently defined and diagnosed. We aimed to develop and compare machine learning models to identify chronic cough from medical and pharmacy claims data. In this retrospective observational study, we compared 3 machine learning algorithms based on XG Boost, logistic regression, and neural network approaches using a large claims and electronic health record database. Of the 327,423 patients who met the study criteria, 4,818 had chronic cough based on linked claims-electronic health record data. The XG Boost model showed the best performance, achieving a Receiver-Operator Characteristic Area Under the Curve (ROC-AUC) of 0.916. We selected a cutoff that favors a high positive predictive value (PPV) to minimize false positives, resulting in a sensitivity, specificity, PPV, and negative predictive value of 18.0%, 99.6%, 38.7%, and 98.8%, respectively on the held-out testing set (n = 82,262). Logistic regression and neural network models achieved slightly lower ROC-AUCs of 0.907 and 0.838, respectively. The XG Boost and logistic regression models maintained their robust performance in subgroups of individuals with higher rates of chronic cough. Machine learning algorithms are one way of identifying conditions that are not coded in medical records, and can help identify individuals with chronic cough from claims data with a high degree of classification value.

Characteristics and Factors Associated With Mortality in Patients With Coronavirus Disease 2019 and Pneumothorax

Objective

To describe the incidence, clinical characteristics, and factors associated with mortality in patients hospitalized for coronavirus disease 2019 (COVID-19) in whom pneumothorax developed.

Patients and Methods

This study was a retrospective analysis conducted using a large administrative database of adult patients hospitalized for COVID-19 in the United States from February 1, 2020, to June 10, 2021. We characterized the clinical features of patients in whom pneumothorax developed and the factors associated with mortality and stratified pneumothorax by the timing of the initiation of invasive mechanical ventilation (IMV) and by the time of hospital admission (early versus late).

Results

A total of 811,065 adult patients had a positive test result for severe acute respiratory syndrome coronavirus 2, of whom 103,858 (12.8%) were hospitalized. Pneumothorax occurred in 1915 patients (0.24% overall and 1.84% among hospitalized patients). Over time, the use of steroids and remdesivir increased, whereas the use of IMV, pneumothorax rates, and mortality decreased. The clinical characteristics associated with pneumothorax were male sex; the receipt of IMV; and treatment with steroids, remdesivir, or convalescent plasma. Most patients with pneumothorax received IMV, but pneumothorax developed before the initiation of IMV and/or early during hospitalization in majority. Multivariable analysis revealed that pneumothorax increased the risk of death (adjusted hazard ratio [aHR], 1.15; 95% CI, 1.06-1.24). In patients who did not receive IMV, pneumothorax led to nearly twice the mortality (aHR, 1.99; 95% CI, 1.56-2.54). Increased mortality was also noted when pneumothorax occurred before IMV (aHR, 1.37; 95% CI, 1.11-1.69) and within 7 days of hospital admission (aHR, 1.60; 95% CI, 1.29-1.98).

Conclusion

The overall incidence of pneumothorax in patients hospitalized for COVID-19 was low. Pneumothorax is an independent risk factor for death.

Tabagismo em idosos

Introdução: o tabagismo é um grave problema de saúde pública em âmbito mundial que afeta a todas as faixas etárias, causando altas taxas de morbimortalidade evitáveis.Objetivo: descrever o que vem sendo publicado sobre o tabagismo na população idosa nos últimos cinco anos na esfera internacional.Metodologia: trata-se de uma revisão integrativa da literatura, onde foram realizadas buscas de artigos nas seguintes bases de dados: PUBMED/MEDLINE, BVS/LILACS, SCOPUS e SCIELO, utilizando os seguintes Descritores em Ciências da Saúde em inglês: “Tobacco Use Cessation” OR “Tobacco Use Disorder” AND “Health of the Elderly” OR “Aged” OR “Aged, 80 and over”. O recorte temporal foi de 2016 a 2020.Resultados: dos 1.642 trabalhos recuperados das bases, houve o afunilamento para um número total de 18 artigos, com a seguinte categorização: mortalidade e outros desfechos clínicos negativos (5); o tabagismo, as síndromes geriátricas e outras patologias (4); políticas públicas para o controle do tabaco (3); qualidade de vida e tabagismo (3); e fatores preditores para cessação tabágica (3).Conclusões: apenas um estudo selecionado foi realizado no Brasil, ressaltando a necessidade de mais estudos brasileiros envolvendo o tabagismo na população idosa objetivando uma melhor compreensão dos aspectos envolvidos e futuras capacitações e otimização de políticas públicas específicas.