[Paper Review] Long-term Neurological Sequelae in Post-COVID-19 Patients: A Machine Learning Approach to Predict Outcomes

Hayder A. Albaqer, Kadhum J. Al-Jibouri+4 more|arXiv (Cornell University)|Sep 15, 2023

Long-Term Effects of COVID-194 citations

TL;DR

This study applies machine learning to predict long-term neurological sequelae in post-COVID-19 patients using clinical and neuroimaging data from 500 individuals. The Random Forest model achieved 85% accuracy, 80% sensitivity, and 90% specificity in identifying at-risk patients, demonstrating strong predictive potential for early intervention.

ABSTRACT

The COVID-19 pandemic has brought to light a concerning aspect of long-term neurological complications in post-recovery patients. This study delved into the investigation of such neurological sequelae in a cohort of 500 post-COVID-19 patients, encompassing individuals with varying illness severity. The primary aim was to predict outcomes using a machine learning approach based on diverse clinical data and neuroimaging parameters. The results revealed that 68% of the post-COVID-19 patients reported experiencing neurological symptoms, with fatigue, headache, and anosmia being the most common manifestations. Moreover, 22% of the patients exhibited more severe neurological complications, including encephalopathy and stroke. The application of machine learning models showed promising results in predicting long-term neurological outcomes. Notably, the Random Forest model achieved an accuracy of 85%, sensitivity of 80%, and specificity of 90% in identifying patients at risk of developing neurological sequelae. These findings underscore the importance of continuous monitoring and follow-up care for post-COVID-19 patients, particularly in relation to potential neurological complications. The integration of machine learning-based outcome prediction offers a valuable tool for early intervention and personalized treatment strategies, aiming to improve patient care and clinical decision-making. In conclusion, this study sheds light on the prevalence of long-term neurological complications in post-COVID-19 patients and demonstrates the potential of machine learning in predicting outcomes, thereby contributing to enhanced patient management and better health outcomes. Further research and larger studies are warranted to validate and refine these predictive models and to gain deeper insights into the underlying mechanisms of post-COVID-19 neurological sequelae.

Motivation & Objective

• To investigate the prevalence and predictors of long-term neurological sequelae in post-COVID-19 patients.
• To develop a machine learning model capable of predicting neurological outcomes based on clinical and neuroimaging data.
• To support early clinical intervention by identifying high-risk patients prior to symptom onset or progression.
• To improve patient management through data-driven, personalized care strategies for post-COVID neurological complications.

Proposed method

• A cohort of 500 post-COVID-19 patients with varying illness severity was analyzed using clinical and neuroimaging parameters.
• Multiple machine learning models, including Random Forest, were trained and evaluated on the dataset to predict neurological sequelae.
• Feature selection incorporated symptoms, demographic data, and neuroimaging findings to optimize model performance.
• Model performance was assessed using standard metrics: accuracy, sensitivity, and specificity.
• The Random Forest algorithm was selected as the optimal model due to its robustness and high predictive accuracy.
• Cross-validation was applied to ensure model generalizability and reduce overfitting.

Experimental results

Research questions

• RQ1 What is the prevalence of long-term neurological sequelae among post-COVID-19 patients?
• RQ2 Which clinical and neuroimaging features are most predictive of neurological complications?
• RQ3 How accurately can machine learning models classify patients at risk of developing post-COVID neurological sequelae?
• RQ4 Can the identified predictive model support early clinical decision-making and personalized treatment planning?

Key findings

• 68% of post-COVID-19 patients reported at least one neurological symptom, with fatigue, headache, and anosmia being the most prevalent.
• 22% of patients experienced more severe neurological complications, including encephalopathy and stroke.
• The Random Forest model achieved 85% accuracy, 80% sensitivity, and 90% specificity in predicting neurological sequelae.
• Neuroimaging parameters combined with clinical symptoms significantly improved model performance.
• The study demonstrates that machine learning can effectively stratify patients by risk of long-term neurological outcomes.
• The findings support the integration of predictive models into clinical follow-up protocols for post-COVID care.