New Utility for an Old Tool

Odonkor, Charles A.; Schonberger, Robert B.; Dai, Feng; Shelley, Kirk H.; Silverman, David G.; Barash, Paul G.

doi:10.1097/phm.0b013e3182a51ac5

Cited by 11 publications

(4 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The LOS studies were also conducted for patients undergoing an operation. Odonkor proposed the need for a study after the surgery and found that age, the type of surgery, and medical histories were better LOS predictors than laboratory tests [17]. Further, Wang revealed that general anesthesia was associated with a longer LOS [18].…”

Section: Related Workmentioning

confidence: 99%

Explainable predictions of a machine learning model to forecast the postoperative length of stay for severe patients: Machine Learning Model Development and Evaluation

Cho

Ahn

Gwon

et al. 2023

Preprint

View full text Add to dashboard Cite

Background Predicting the length of stay in advance will not only benefit the hospitals both clinically and financially but enable healthcare providers to better decision-making for improved quality of care. More importantly, understanding the length of stay of severe patients who require general anesthesia is key to enhancing health outcomes. Objective Here, we aim to discover how machine learning can support resource allocation management and decision-making resulting from the length of stay prediction. Methods A retrospective cohort study was conducted from January 2018 to October 2020. A total cohort of 240,000 patients’ medical records was collected. The data were collected exclusively for preoperative variables to accurately analyze the predictive factors impacting the postoperative length of stay. The main outcome of this study is an analysis of the length of stay (in days) after surgery until discharge. The prediction was performed with ridge regression, random forest, XGBoost, and multi-layer perceptron neural network models. Results The XGBoost resulted in the best performance with an average error within 3 days. Moreover, we explain each feature’s contribution over the XGBoost model and further display distinct predictors affecting the overall prediction outcome at the patient level. The risk factors that most importantly contributed to the stay after surgery were as follows: a direct bilirubin laboratory test, department change, calcium chloride medication, gender, and diagnosis with the removal of other organs. Our results suggest that healthcare providers take into account the risk factors such as the laboratory blood test, distributing patients, and the medication prescribed prior to the surgery. Conclusion We successfully predicted the length of stay after surgery and provide explainable models with supporting analyses. In summary, we demonstrate the interpretation with the XGBoost model presenting insights on preoperative features and defining higher risk predictors to the length of stay outcome. Our development in explainable models supports the current in-depth knowledge for the future length of stay prediction on electronic medical records that aids the decision-making and facilitation of the operation department.

show abstract

Section: Related Workmentioning

confidence: 99%

Explainable predictions of a machine learning model to forecast the postoperative length of stay for severe patients: Machine Learning Model Development and Evaluation

Cho

Ahn

Gwon

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…After the repetition of the gait speed test, patients were divided into two groups: slow and non-slow. The cutoff point used was 1.0 m / s based on the study by Odonkor et al 10 Those who were not discharged walked less than 1.0 m / s occupied the slow group and those who were above 1.0 m / s were classified as not slow. Patients were followed for six months to observe the primary outcome, which was the need for hospital readmission.…”

Section: Study Protocolmentioning

confidence: 99%

Gait Speed and Hospital Reinternation After Coronary Artery Bypass Grafting

Santos¹,

Soares²,

Guimarães³

et al. 2020

Preprint

View full text Add to dashboard Cite

Introduction: Gait speed can be applied, predicting outcomes associated with hospital stay such as length of stay and/or discharge. Despite these studies that correlate gait speed with the aforementioned outcomes, when we deal with cardiac surgery there is a gap. Objective: Verify whether gait speed is associated with the risk of hospital readmission in the postoperative period of coronary artery bypass grafting. Methodology: This is a prospective cohort study. In the preoperative period, all patients underwent a 10-meter gait speed test and repeated at hospital discharge. After the repetition of the gait speed test, patients were divided into two groups: slow and non-slow. Those who were not discharged walked less than 1.0 m/s occupied the slow group and those who were above 1.0 m/s were classified as not slow. Patients were followed for six months to observe the primary outcome, which was the need for hospital readmission. Results: The 6 months rate of readmission was 58%(14/24;95%CI49%to80%) among slow walkers and 17% (6/36;95%CI13%to46%) among non-slow walkers(p=0.002).In univariate analysis, gait speed, treated as a continuous variable, was associated with the primary outcome (HR0.6;95%CI0.2to0.9), while age, gender, BMI, MV and CPB time were not. In the multivariate model including age, gender, BMI, MV and CPB time, gait speed remained the only variable associated with readmission (multivariate HR:0.5,95%CI0.1to0.7p=0.02). Conclusion: Our data suggest that gait speed is associated with hospital readmission in patients undergoing to coronary artery bypass grafting.

show abstract

“…Destaca-se entre os marcadores a força de preensão manual (FPM) e a velocidade da marcha (VM) como importantes preditores do nível de fragilidade física em idosos (4) . Como indicadores de força muscular geral, a mensuração destes componentes é considerada instrumento eficiente na predição da morbidade e mortalidade (5) .…”

Section: Introductionunclassified

Fatores Sociodemográficos E Clínicos Associados À Força De Preensão Manual E Velocidade Da Marcha Em Longevos

Lenardt¹,

Grden²,

Sousa³

et al. 2017

Cogitare Enferm.

View full text Add to dashboard Cite

RESUMO: Pesquisa transversal com o objetivo de investigar a associação entre fatores sociodemográficos e clínicos e os componentes força de preensão manual e velocidade da marcha em idosos longevos. A amostra contemplou 243 longevos, de três Unidades Básicas de Saúde de Curitiba, Paraná, entre janeiro de 2013 e setembro de 2015. Identificou-se associação significativa entre força de preensão manual e sexo (p=0,001), idade (p=0,001), estado civil (p=0,001), moradia (p=0,001), quedas no último ano (p=0,03), perda de urina (p=0,001), uso de bengala (p=0,001) e andador (p=0,001). A velocidade da marcha apresentou associação com sexo (p=0,001), idade (p=0,001), estado civil (p=0,001), moradia (p=0,001), quedas no último ano (p=0,03), perda de urina (p=0,001), uso de bengala (p=0,001) e andador (p=0,001). Destaca-se que a avaliação da força de preensão manual e velocidade da marcha auxiliam na identificação de alterações funcionais em longevos e constitui-se como parte fundamental na gestão da síndrome da fragilidade física. DESCRITORES: Idoso fragilizado; Força da mão; Marcha; Enfermagem geriátrica. FATORES SOCIODEMOGRÁFICOS E CLÍNICOS ASSOCIADOS SOCIODEMOGRAPHIC AND CLINICAL FACTORS ASSOCIATED WITH HAND GRIP STRENGTH AND GAIT SPEED IN LONG-LIVING ELDERLYABSTRACT: Cross-sectional research to investigate the association between sociodemographic and clinical factors and the components hand grip strength and gait speed in long-living elderly. The sample included 243 long-living elderly from three primary health care services in Curitiba, Paraná, between January 2013 and September 2015. A significant association was identified between hand grip strength and sex (p=0.001), age (p=0.001), marital status (p=0.001), housing (p=0.001), falls in previous year (p=0.03), urine loss (p=0.001), use of cane (p=0.001) and walker (p=0.001). The gait speed was associated with sex (p=0.001), age (p=0.001), marital status (p=0.001), housing (p=0.001), falls in previous year (p=0.03), urine loss (p=0.001), use of cane (p=0.001) and walker (p=0.001). It is highlighted that the assessment of hand grip strength and gait speed helps to identify functional changes in long-living elderly and plays a fundamental role in the management of the physical frailty syndrome.

show abstract

New Utility for an Old Tool

Cited by 11 publications

References 36 publications

Explainable predictions of a machine learning model to forecast the postoperative length of stay for severe patients: Machine Learning Model Development and Evaluation

Explainable predictions of a machine learning model to forecast the postoperative length of stay for severe patients: Machine Learning Model Development and Evaluation

Gait Speed and Hospital Reinternation After Coronary Artery Bypass Grafting

Fatores Sociodemográficos E Clínicos Associados À Força De Preensão Manual E Velocidade Da Marcha Em Longevos

Contact Info

Product

Resources

About