Ya Su1, Michiko Yuki2, Kengo Hirayama3, Mika Otsuki4. 1. Graduate School of Health Sciences, Hokkaido University, Kita 12, Nishi 5, Kita-ku, Sapporo, Hokkaido, 060-0812, Japan. Electronic address: swanvivi@eis.hokudai.ac.jp. 2. Faculty of Health Sciences, Hokkaido University, Kita 12, Nishi 5, Kita-ku, Sapporo, Hokkaido, 060-0812, Japan. Electronic address: yukimck@hs.hokudai.ac.jp. 3. Faculty of Health Sciences, Hokkaido University, Kita 12, Nishi 5, Kita-ku, Sapporo, Hokkaido, 060-0812, Japan. Electronic address: khirayama@hs.hokudai.ac.jp. 4. Faculty of Health Sciences, Hokkaido University, Kita 12, Nishi 5, Kita-ku, Sapporo, Hokkaido, 060-0812, Japan. Electronic address: lasteroideb612@pop.med.hokudai.ac.jp.
Abstract
OBJECTIVES: We aimed to develop and validate a nomogram for the individualized prediction of the risk of post-stroke fatigue (PSF) after discharge. MATERIALS AND METHODS: Fatigue was measured using the Fatigue Assessment Scale. Multivariable logistic regression analysis was applied to build a prediction model incorporating the feature selected in the least absolute shrinkage and selection operator regression model. Discrimination, calibration, and clinical usefulness of the predictive model were assessed using the C-index, calibration plot, and decision curve analysis. Internal validation was conducted using bootstrapping validation. Finally, a web application was developed to facilitate the use of the nomogram. RESULTS: We developed a nomogram based on 95 stroke patients. The predictors included in the nomogram were sex, pre-stroke sarcopenia, acute phase fatigue, dysphagia, and depression. The model displayed good discrimination, with a C-index of 0.801 (95% confidence interval: 0.700-0.902) and good calibration. A high C-index value of 0.762 could still be reached in the interval validation. Decision curve analysis showed that the risk of PSF after discharge was clinically useful when the intervention was decided at the PSF risk possibility threshold of 10% to 90%. CONCLUSION: This nomogram could be conveniently used to provide an individual, visual, and precise prediction of the risk probability of PSF after being discharged home. Thus, as an aid in decision-making, physicians and other healthcare professionals can use this predictive method to provide early intervention or a discharge plan for stroke patients during the hospitalization period.
OBJECTIVES: We aimed to develop and validate a nomogram for the individualized prediction of the risk of post-stroke fatigue (PSF) after discharge. MATERIALS AND METHODS:Fatigue was measured using the Fatigue Assessment Scale. Multivariable logistic regression analysis was applied to build a prediction model incorporating the feature selected in the least absolute shrinkage and selection operator regression model. Discrimination, calibration, and clinical usefulness of the predictive model were assessed using the C-index, calibration plot, and decision curve analysis. Internal validation was conducted using bootstrapping validation. Finally, a web application was developed to facilitate the use of the nomogram. RESULTS: We developed a nomogram based on 95 strokepatients. The predictors included in the nomogram were sex, pre-stroke sarcopenia, acute phase fatigue, dysphagia, and depression. The model displayed good discrimination, with a C-index of 0.801 (95% confidence interval: 0.700-0.902) and good calibration. A high C-index value of 0.762 could still be reached in the interval validation. Decision curve analysis showed that the risk of PSF after discharge was clinically useful when the intervention was decided at the PSF risk possibility threshold of 10% to 90%. CONCLUSION: This nomogram could be conveniently used to provide an individual, visual, and precise prediction of the risk probability of PSF after being discharged home. Thus, as an aid in decision-making, physicians and other healthcare professionals can use this predictive method to provide early intervention or a discharge plan for strokepatients during the hospitalization period.