Machine learning to predict mortality after rehabilitation among patients with severe stroke

Scrutinio, Domenico; Ricciardi, Carlo; Donisi, Leandro; Losavio, Ernesto; Battista, Petronilla; Guida, Pietro; Cesarelli, Mario; Pagano, Gaetano; D’Addio, Giovanni

doi:10.1038/s41598-020-77243-3

Cited by 59 publications

(37 citation statements)

References 65 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several tools can be used to perform ML analyses: Tougui et al performed a study on these tools in the context of heart disease classification [41] and identified Knime analytics platform as the best tool in terms of data manipulation, creating complex workflows, parameter tuning, and control of the algorithms. Moreover, this tool has already been used to perform biomedical studies also in fields such as ophthalmology and signal processing [42][43][44], and in cardiology [45,46].…”

Section: Machine Learning: Tool and Algorithmsmentioning

confidence: 99%

Extracting Features from Poincaré Plots to Distinguish Congestive Heart Failure Patients According to NYHA Classes

et al. 2021

Self Cite

View full text Add to dashboard Cite

Heart-rate variability has proved a valid tool in prognosis definition of patients with congestive heart failure (CHF). Previous research has documented Poincaré plot analysis as a valuable approach to study heart-rate variability performance among different subjects. In this paper, we explored the possibility to feed machine-learning (ML) algorithms using unconventional quantitative parameters extracted from Poincaré plots (generated from 24-h electrocardiogram recordings) to classify patients with CHF belonging to different New York Heart Association (NYHA) classes. We performed in sequence the following investigations: first, a statistical analysis was carried out on 9 morphological parameters, automatically measured from Poincaré plots. Subsequently, a feature selection through a wrapper with a 10-fold cross-validation method was performed to find the best subset of features which maximized the classification accuracy for each considered ML algorithm. Finally, patient classification was assessed through a ML analysis using AdaBoost of Decision Tree, k-Nearest Neighbors and Naive Bayes algorithms. A univariate statistical analysis proved 5 out of 9 parameters presented statistically significant differences among patients of distinct NYHA classes; similarly, a multivariate logistic regression confirmed the importance of the parameter ρy in the separability between low-risk and high-risk classes. The ML analysis achieved promising results in terms of evaluation metrics (especially the Naive Bayes algorithm), with accuracies greater than 80% and Area Under the Receiver Operating Curve indices greater than 0.7 for the overall three algorithms. The study indicates the proposed features have a predictive power to discriminate the NYHA classes, to which the features seem evenly correlated. Despite the NYHA classification being subjective and easily recognized by cardiologists, the potential relevance in the clinical cardiology of the proposed features and the promising ML results implies the methodology could be a valuable approach to automatically classify CHF. Future investigations on enriched datasets may further confirm the presented evidence.

show abstract

Section: Machine Learning: Tool and Algorithmsmentioning

confidence: 99%

Extracting Features from Poincaré Plots to Distinguish Congestive Heart Failure Patients According to NYHA Classes

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…Stroke is the second most common cause of death and disability worldwide. [1][2][3] Globally, there were 80.1 million prevalent cases of stroke, with 84.4% ischemic stroke (IS). 4 In 2016, 5.5 million died of stroke, and IS accounted for 49.1% of all stroke deaths.…”

Section: Introductionmentioning

confidence: 99%

Length of Stay, Hospital Costs and Mortality Associated With Comorbidity According to the Charlson Comorbidity Index in Immobile Patients After Ischemic Stroke in China: A National Study

Liu

Song

Jin

et al. 2021

Int J Health Policy Manag

View full text Add to dashboard Cite

Background: In this study, we examined the length of stay (LoS)-predictive comorbidities, hospital costs-predictive comorbidities, and mortality-predictive comorbidities in immobile ischemic stroke (IS) patients; second, we used the Charlson Comorbidity Index (CCI) to assess the association between comorbidity and the LoS and hospitalization costs of stroke; third, we assessed the magnitude of excess IS mortality related to comorbidities. Methods: Between November 2015 and July 2017, 5114 patients hospitalized for IS in 25 general hospitals from six provinces in eastern, western, and central China were evaluated. LoS was the period from the date of admission to the date of discharge or date of death. Costs were collected from the hospital information system (HIS) after the enrolled patients were discharged or died in hospital. The HIS belongs to the hospital's financial system, which records all the expenses of the patient during the hospital stay. Cause of death was recorded in the HIS for 90 days after admission regardless of whether death occurred before or after discharge. Using the CCI, a comorbidity index was categorized as zero, one, two, and three or more CCI diseases. A generalized linear model with a gamma distribution and a log link was used to assess the association of LoS and hospital costs with the comorbidity index. Kaplan-Meier survival curves was used to examine overall survival rates. Results: We found that 55.2% of IS patients had a comorbidity. Prevalence of peripheral vascular disease (21.7%) and diabetes without end-organ damage (18.8%) were the major comorbidities. A high CCI=3+ score was an effective predictor of a high risk of longer LoS and death compared with a low CCI score; and CCI=2 score and CCI=3+ score were efficient predictors of a high risk of elevated hospital costs. Specifically, the most notable LoS-specific comorbidities, and cost-specific comorbidities was dementia, while the most notable mortality-specific comorbidities was moderate or severe renal disease. Conclusion: CCI has significant predictive value for clinical outcomes in IS. Due to population aging, the CCI should be used to identify, monitor and manage chronic comorbidities among immobile IS populations.

show abstract

“…The generalization was unsatisfied under the mismatched testing condition. The possible reasons were as follows: (1) The limited sample size of the recruited subjects (n = 29) hindered the model's effective generalization, i.e., recognizing completely new inputs, compared to those achieved this in the literatures usually with larger sample sizes (e.g., n > 100) (Kim et al, 2020;Scrutinio et al, 2020).…”

Section: Mapping the Semg Data To Masmentioning

confidence: 99%

A Data-Driven Investigation on Surface Electromyography Based Clinical Assessment in Chronic Stroke

Yang

Nam

et al. 2021

Front. Neurorobot.

View full text Add to dashboard Cite

Background: Surface electromyography (sEMG) based robot-assisted rehabilitation systems have been adopted for chronic stroke survivors to regain upper limb motor function. However, the evaluation of rehabilitation effects during robot-assisted intervention relies on traditional manual assessments. This study aimed to develop a novel sEMG data-driven model for automated assessment.Method: A data-driven model based on a three-layer backpropagation neural network (BPNN) was constructed to map sEMG data to two widely used clinical scales, i.e., the Fugl–Meyer Assessment (FMA) and the Modified Ashworth Scale (MAS). Twenty-nine stroke participants were recruited in a 20-session sEMG-driven robot-assisted upper limb rehabilitation, which consisted of hand reaching and withdrawing tasks. The sEMG signals from four muscles in the paretic upper limbs, i.e., biceps brachii (BIC), triceps brachii (TRI), flexor digitorum (FD), and extensor digitorum (ED), were recorded before and after the intervention. Meanwhile, the corresponding clinical scales of FMA and MAS were measured manually by a blinded assessor. The sEMG features including Mean Absolute Value (MAV), Zero Crossing (ZC), Slope Sign Change (SSC), Root Mean Square (RMS), and Wavelength (WL) were adopted as the inputs to the data-driven model. The mapped clinical scores from the data-driven model were compared with the manual scores by Pearson correlation.Results: The BPNN, with 15 nodes in the hidden layer and sEMG features, i.e., MAV, ZC, SSC, and RMS, as the inputs to the model, was established to achieve the best mapping performance with significant correlations (r > 0.9, P < 0.001), according to the FMA. Significant correlations were also obtained between the mapped and manual FMA subscores, i.e., FMA-wrist/hand and FMA-shoulder/elbow, before and after the intervention (r > 0.9, P < 0.001). Significant correlations (P < 0.001) between the mapped and manual scores of MASs were achieved, with the correlation coefficients r = 0.91 at the fingers, 0.88 at the wrist, and 0.91 at the elbow after the intervention.Conclusion: An sEMG data-driven BPNN model was successfully developed. It could evaluate upper limb motor functions in chronic stroke and have potential application in automated assessment in post-stroke rehabilitation, once validated with large sample sizes.Clinical Trial Registration:www.ClinicalTrials.gov, identifier: NCT02117089.

show abstract

Machine learning to predict mortality after rehabilitation among patients with severe stroke

Cited by 59 publications

References 65 publications

Extracting Features from Poincaré Plots to Distinguish Congestive Heart Failure Patients According to NYHA Classes

Extracting Features from Poincaré Plots to Distinguish Congestive Heart Failure Patients According to NYHA Classes

Length of Stay, Hospital Costs and Mortality Associated With Comorbidity According to the Charlson Comorbidity Index in Immobile Patients After Ischemic Stroke in China: A National Study

A Data-Driven Investigation on Surface Electromyography Based Clinical Assessment in Chronic Stroke

Contact Info

Product

Resources

About