Clinical and Radiomics Predictors of Post-stroke Longitudinal Mortality: A Prospective Cohort Study from a Tertiary Care Hospital in India
- 1Laboratory of Translational Neuroscience, Division of Neuroscience, Yenepoya Research Center, Yenepoya (Deemed to be University), Mangalore 575018, Karnataka, I
Abstract
BackgroundStroke imposes substantial mortality and socioeconomic burden in India, particularly among younger adults. However, prospective evidence on the prognostic value of baseline clinical and radiomics features for mortality prediction remains limited.
ObjectiveTo assess mortality at 28, 90, 180, and 365 days after stroke; characterize survival patterns across stroke subtypes and vascular territories; and identify baseline demographic, clinical, and radiomics predictors of mortality.
MethodsThis prospective cohort study recruited consecutive patients with stroke admitted to a tertiary care hospital in Mangalore, India. Demographic, clinical, laboratory, and radiomics features were collected at admission, and mortality was assessed at 28, 90, 180, and 365 days. Kaplan-Meier analysis was used to compare survival across stroke subtypes and vascular territories, while Cox proportional hazards regression was used to identify independent baseline predictors of mortality.
ResultsAmong 63 confirmed stroke cases, 38 (60%) had ischemic stroke (IS) and 25 (40%) had haemorrhagic stroke (HS). Within the middle cerebral artery (MCA) territory, HS patients demonstrated better survival than IS patients due to a greater burden of adverse baseline characteristics such as previous stroke, atrial fibrillation, and higher lesion volume in the IS-MCA subgroup. The combined clinical-radiomics model demonstrated superior prognostic performance than individual models, with higher concordance indices and consistently lower Akaike Information Criterion values. In the combined model, stroke severity (aHR = 2.35, 3.0, 2.93, 2.41) and DWI texture heterogeneity of lesion (aHR = 2.35, 2.11, 2.24, 2.10) were the strongest predictors of mortality across all time points. The CT attenuation heterogeneity (aHR = 1.81, 28 days; 1.76, 90 days; 1.80, 180 days) of lesion and age (aHR = 1.48, 365 days) were also significant predictors.
ConclusionThe radiomics features provide critical complementary information to clinical parameters for predicting 28-day mortality, unlike during mid- to long-term follow-up where their incremental contribution appears to be limited. Our results may have important implications in resource-constrained settings for supporting personalized post-stroke management and rehabilitation.
Related
- Hyperlactataemia and Hypocalcaemia as Predictors of Mortality in Adult Polytrauma Patients: A Prospective Observational Study
- Multiparametric MRI habitat radiomics and longitudinal dynamic clinical parameters predict TACE refractoriness in HCC
- Incidence and predictors of early neonatal mortality among neonates admitted to neonatal intensive care units in public general hospitals in Northwest Ethiopia: a multicenter prospective cohort study.
- Trajectories and predictors of psychological distress during the first 6 months of weight loss among adults with obesity: a prospective longitudinal cohort study
- Multi-sequence magnetic resonance imaging radiomics integrated with clinical features predicts pelvic lymph node metastasis in cervical cancer: a retrospective-prospective cohort study
BibTeX
@misc{babu2026clinical,
title = {{Clinical and Radiomics Predictors of Post-stroke Longitudinal Mortality: A Prospective Cohort Study from a Tertiary Care Hospital in India}},
author = {M. Babu and S. Basak and K. Sardar and M. Hassan and I. M. Haji and R. Shirin and A. Gangadhar and A. Gogoi and D. Biswas and D. Chakraborty and S. Bhaduri and A. Datta},
howpublished = {medRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.24.26363784},
url = {https://www.medrxiv.org/content/10.64898/2026.09.24.26363784v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - Clinical and Radiomics Predictors of Post-stroke Longitudinal Mortality: A Prospective Cohort Study from a Tertiary Care Hospital in India
AU - M. Babu
AU - S. Basak
AU - K. Sardar
AU - M. Hassan
AU - I. M. Haji
AU - R. Shirin
AU - A. Gangadhar
AU - A. Gogoi
AU - D. Biswas
AU - D. Chakraborty
AU - S. Bhaduri
AU - A. Datta
PY - 2026
DA - 2026/09/24
PB - medRxiv
DO - 10.64898/2026.09.24.26363784
UR - https://www.medrxiv.org/content/10.64898/2026.09.24.26363784v1
AB - BackgroundStroke imposes substantial mortality and socioeconomic burden in India, particularly among younger adults. However, prospective evidence on the prognostic value of baseline clinical and radiomics features for mortality prediction remains limited. ObjectiveTo assess mortality at 28, 90, 180, and 365 days after stroke; characterize survival patterns across stroke subtypes and vascular territories; and identify baseline demographic, clinical, and radiomics predictors of mortality. MethodsThis prospective cohort study recruited consecutive patients with stroke admitted to a tertiary care hospital in Mangalore, India. Demographic, clinical, laboratory, and radiomics features were collected at admission, and mortality was assessed at 28, 90, 180, and 365 days. Kaplan-Meier analysis was used to compare survival across stroke subtypes and vascular territories, while Cox proportional hazards regression was used to identify independent baseline predictors of mortality. ResultsAmong 63 confirmed stroke cases, 38 (60%) had ischemic stroke (IS) and 25 (40%) had haemorrhagic stroke (HS). Within the middle cerebral artery (MCA) territory, HS patients demonstrated better survival than IS patients due to a greater burden of adverse baseline characteristics such as previous stroke, atrial fibrillation, and higher lesion volume in the IS-MCA subgroup. The combined clinical-radiomics model demonstrated superior prognostic performance than individual models, with higher concordance indices and consistently lower Akaike Information Criterion values. In the combined model, stroke severity (aHR = 2.35, 3.0, 2.93, 2.41) and DWI texture heterogeneity of lesion (aHR = 2.35, 2.11, 2.24, 2.10) were the strongest predictors of mortality across all time points. The CT attenuation heterogeneity (aHR = 1.81, 28 days; 1.76, 90 days; 1.80, 180 days) of lesion and age (aHR = 1.48, 365 days) were also significant predictors. ConclusionThe radiomics features provide critical complementary information to clinical parameters for predicting 28-day mortality, unlike during mid- to long-term follow-up where their incremental contribution appears to be limited. Our results may have important implications in resource-constrained settings for supporting personalized post-stroke management and rehabilitation.
ER -