TY  - JOUR
AU  - Walders, Julia
AU  - Wetz, Sophie
AU  - Costa, Ana Sofia
AU  - Hofmann, Anna
AU  - Schulz, Jörg B
AU  - Reetz, Kathrin
AU  - Dadsena, Ravi
TI  - Longitudinal modeling of Post-COVID-19 condition over three years: A machine learning approach using clinical, neuropsychological, and fluid markers.
JO  - Scientific reports
VL  - 16
IS  - 1
SN  - 2045-2322
CY  - [London]
PB  - Springer Nature
M1  - DZNE-2026-00200
SP  - 6517
PY  - 2026
AB  - Post-COVID-19 condition (PCC) manifests with prolonged, heterogeneous symptoms challenging both, diagnosis and therapeutic management. This three-year longitudinal study analyzed data from 93 adults (mean age of 48.9 ± 14.0, 60 female) after confirmed SARS-CoV-2 infection. Every follow-up visit included clinical, neuropsychological, and laboratory assessments, capturing multidimensional indicators of patient health. A machine learning framework was implemented to classify temporal stage of patient health status, identify visit-specific predictive markers, and manage incomplete data using both native handling in tree-based models and explicit imputation techniques. Gradient boosting methods consistently achieved the best performance across all visit comparisons, achieving F1-scores close to or above 90
KW  - Humans
KW  - Machine Learning
KW  - COVID-19: complications
KW  - COVID-19: psychology
KW  - Female
KW  - Middle Aged
KW  - Longitudinal Studies
KW  - Male
KW  - Biomarkers
KW  - Adult
KW  - SARS-CoV-2: isolation & purification
KW  - Neuropsychological Tests
KW  - Aged
KW  - Clinical biomarkers (Other)
KW  - Long COVID-19 (Other)
KW  - Longitudinal data (Other)
KW  - Machine learning (Other)
KW  - Predictive modeling (Other)
KW  - Biomarkers (NLM Chemicals)
LB  - PUB:(DE-HGF)16
C6  - pmid:41690938
DO  - DOI:10.1038/s41598-026-37635-3
UR  - https://pub.dzne.de/record/285258
ER  -