Deans' stroke musings: Development and validation of a nomogram for predicting ADL outcomes in patients undergoing subacute stroke rehabilitation based on machine learning and standard bedside clinical data: a retrospective cohort study

Changing stroke rehab and research worldwide now.Time is Brain! trillions and trillions of neurons that DIE each day because there are NO effective hyperacute therapies besides tPA(only 12% effective). I have 523 posts on hyperacute therapy, enough for researchers to spend decades proving them out. These are my personal ideas and blog on stroke rehabilitation and stroke research. Do not attempt any of these without checking with your medical provider. Unless you join me in agitating, when you need these therapies they won't be there.

What this blog is for:

My blog is not to help survivors recover, it is to have the 10 million yearly stroke survivors light fires underneath their doctors, stroke hospitals and stroke researchers to get stroke solved. 100% recovery. The stroke medical world is completely failing at that goal, they don't even have it as a goal. Shortly after getting out of the hospital and getting NO information on the process or protocols of stroke rehabilitation and recovery I started searching on the internet and found that no other survivor received useful information. This is an attempt to cover all stroke rehabilitation information that should be readily available to survivors so they can talk with informed knowledge to their medical staff. It lays out what needs to be done to get stroke survivors closer to 100% recovery. It's quite disgusting that this information is not available from every stroke association and doctors group.

Monday, June 29, 2026

Development and validation of a nomogram for predicting ADL outcomes in patients undergoing subacute stroke rehabilitation based on machine learning and standard bedside clinical data: a retrospective cohort study

What fucking stupidity, predicting failure to recover; RATHER THAN DELIVERING PROTOCOLS THAT GET YOU RECOVERED! You're all fired! Hope your comeuppance hits you really really hard when you become the 1 in 4 per WHO that has a stroke!

Development and validation of a nomogram for predicting ADL outcomes in patients undergoing subacute stroke rehabilitation based on machine learning and standard bedside clinical data: a retrospective cohort study

X
Xinye Chen 1†
Juming Liu 2†
Jiawei Qin 3
Xi Qin 2
C
Changyu Ju 2
S
Suchen Zhao 2*
Qianqian Sun 2,4*

1. School of Computer Science, Guangdong Polytechnic Normal University, Guangzhou, China
2. Hubei University of Arts and Science Affiliated Xiangyang Central Hospital, Xiangyang, Hubei, China

Abstract

Background:

The subacute phase is a key period for stroke recovery, yet there is a lack of simple and effective indicators to predict rehabilitation outcomes. This study aims to develop and validate a predictive model for assessing patients’ activities of daily living (ADL) recovery at 3 months, providing valuable insights to guide clinical rehabilitation decisions.

Methods:

This retrospective cohort study included patients admitted to rehabilitation within 7 to 30 days after their first stroke. Data were obtained from the electronic medical record system. Patients were divided into a training cohort (270 patients, 2021–2022) and a validation cohort (165 patients, 2023–2024). ADL independence was defined by a Barthel Index (BI) score of ≥60. The primary outcome was the ADL status at 3 months after the initiation of rehabilitation. Feature selection was performed using univariate analysis and Elastic Net regression, followed by logistic regression modeling. The optimal model was selected based on its AUC in the validation cohort, ensuring a balance between sensitivity and specificity. The final model was presented as a nomogram.

Results:

The 3-month prediction model (ADL-3 M) includes the Braden score, baseline BI score, and age. SHAP analysis revealed that the Braden score was the most significant predictor for the 3-month outcome. The AUC for ADL-3 M was 0.832 (95% CI: 0.779–0.885) in the training cohort and 0.866 (95% CI: 0.806–0.926) in the validation cohort.

Conclusion:

The simplified model constructed using routine bedside indicators (age, baseline BI score, and Braden score) effectively predicts the ADL recovery of subacute stroke patients at 3 months post-rehabilitation. This nomogram tool is intuitive and easy to use, providing clinical support for individualized rehabilitation plan development, patient prognosis communication, and resource allocation.