David F. Estupiñan-Pepinosa
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
David F. Estupiñan-Pepinosa has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
Cesar A. Buitrago
Department of Neurology, Epilepsy Clinic, Fundación Santa Fe de Bogotá, Bogotá , Colombia
2 shared publicationsJheremy S. Reyes
Cancer and Molecular Medicine Research Group (CAMMO), Bogotá, Colombia
2 shared publicationsJuan P. Quintero-Ruiz
Universidad de los Andes, Bogota, Colombia
2 shared publicationsJuan S. Aguirre-Patiño
Department of Neurology, Epilepsy Clinic, Fundación Santa Fe de Bogotá, Bogotá , Colombia
2 shared publicationsLuis C. Mayor-Romero
Department of Neurology, Epilepsy Clinic, Fundación Santa Fe de Bogotá, Bogotá , Colombia
2 shared publicationsMaria F. Cordoba-Gallego
Universidad de los Andes, Bogota, Colombia
2 shared publications
Latest Publications
- Top Cited Papers
- 27 March 2026
- Published by Springer Nature in Neuroradiology
- Vol. 68 (5) , 1235-1250
Artificial intelligence and radiomics for pediatric brain tumor classification and molecular characterization: a systematic review
Background Artificial intelligence (AI) and radiomics are increasingly applied in pediatric neuroradiology to enhance diagnostic precision. However, their clinical implementation remains limited due to methodological variability and lack of standardization. Objective To systematically evaluate the diagnostic applications, performance, and methodological quality of artificial intelligence models, including both radiomics/machine learning and deep learning approaches, in pediatric brain tumor imaging. Methods A systematic review was conducted in accordance with PRISMA 2020 guidelines, searching PubMed, Scopus, and Web of Science (2010–2025). Eligible studies included patients aged 0–18 years with brain tumors, applied AI to neuroimaging for diagnostic classification, molecular characterization, or integral image processing tasks, and reported performance metrics. Methodological quality was assessed using the Newcastle–Ottawa Scale (NOS) and the Checklist for Artificial Intelligence in Medical Imaging (CLAIM). Results From 638 records, 24 studies were included. Most studies used MRI (96%) and machine learning models based on radiomics (88%), with a smaller proportion employing deep learning (29%). The primary diagnostic tasks were tumor classification (50%) and molecular subtype prediction (33%). Reported AUCs for diagnostic tasks ranged from 0.73 to 0.98 (median: 0.91). Based on the NOS, 19 studies (79%) were rated as low risk of bias (scores 8–9), though only 3 studies (12.5%) performed external validation on independent cohorts. Conclusion AI and radiomics demonstrate high diagnostic accuracy for pediatric brain tumor characterization. Nonetheless, the lack of prospective design and critically low rate of external validation limits generalizability. Standardized, multicenter studies are needed to support broader clinical adoption.
- 27 March 2026
- Published by Springer Nature in Neuroradiology
- Vol. 68 (5) , 1235-1250
Top Cited PapersArtificial intelligence and radiomics for pediatric brain tumor classification and molecular characterization: a systematic review
Background Artificial intelligence (AI) and radiomics are increasingly applied in pediatric neuroradiology to enhance diagnostic precision. However, their clinical implementation remains limited due to methodological variability and lack of standardization. Objective To systematically evaluate the diagnostic applications, performance, and methodological quality of artificial intelligence models, including both radiomics/machine learning and deep learning approaches, in pediatric brain tumor imaging. Methods A systematic review was conducted in accordance with PRISMA 2020 guidelines, searching PubMed, Scopus, and Web of Science (2010–2025). Eligible studies included patients aged 0–18 years with brain tumors, applied AI to neuroimaging for diagnostic classification, molecular characterization, or integral image processing tasks, and reported performance metrics. Methodological quality was assessed using the Newcastle–Ottawa Scale (NOS) and the Checklist for Artificial Intelligence in Medical Imaging (CLAIM). Results From 638 records, 24 studies were included. Most studies used MRI (96%) and machine learning models based on radiomics (88%), with a smaller proportion employing deep learning (29%). The primary diagnostic tasks were tumor classification (50%) and molecular subtype prediction (33%). Reported AUCs for diagnostic tasks ranged from 0.73 to 0.98 (median: 0.91). Based on the NOS, 19 studies (79%) were rated as low risk of bias (scores 8–9), though only 3 studies (12.5%) performed external validation on independent cohorts. Conclusion AI and radiomics demonstrate high diagnostic accuracy for pediatric brain tumor characterization. Nonetheless, the lack of prospective design and critically low rate of external validation limits generalizability. Standardized, multicenter studies are needed to support broader clinical adoption.
- 8 January 2026
- Published by Springer Nature in Neurosurgical Review
- Vol. 49 (1) , 114
Barriers to care in epilepsy surgery clinics in Latin America: a systematic review of social–economic impact
Epilepsy surgery remains underutilized in Latin America despite its proven effectiveness for drug-resistant epilepsy. Structural and socioeconomic barriers may contribute to limited access and delayed intervention. To systematically evaluate the clinical characteristics, surgical outcomes, and socioeconomic barriers to accessibility associated with epilepsy surgery in Latin America. A systematic review was conducted following PRISMA guidelines. Searches were performed in PubMed, Scopus, ScienceDirect, Web of Science, and SciELO. Studies were included if they reported original data on epilepsy surgery in Latin American populations. Data on demographics, epilepsy type, and surgical outcomes were extracted and analyzed descriptively. Barriers such as geographic centralization, economic constraints, lack of specialized centers, and limited diagnostic infrastructure were also identified and examined. Of 103 initial records, 10 studies met all inclusion criteria. Most were retrospective observational studies from Colombia, Brazil, Mexico, and Chile. The mean age at surgery was 30.3 years, with an average diagnostic-to-surgery delay of 17.1 years. Mesial temporal lobe epilepsy was the most common subtype. Seizure freedom (Engel Class I) was achieved in 43.7% to 85% of cases. However, only 3.8% of eligible patients underwent surgery in some cohorts. Barriers included geographic centralization, economic constraints, lack of specialized centers, limited diagnostic infrastructure, cultural stigma, and under-referral from physicians. Quality-of-life improvements and psychosocial reintegration were observed postoperatively, yet disparities in access persisted. Despite favorable surgical outcomes, epilepsy surgery in Latin America remains significantly delayed and centralized. Health system limitations and socioeconomic inequities continue to restrict timely and equitable access. Regional policies must prioritize early referral pathways, surgical infrastructure, and financial protection to reduce the epilepsy treatment gap.
- 8 January 2026
- Published by Springer Nature in Neurosurgical Review
- Vol. 49 (1) , 114
Barriers to care in epilepsy surgery clinics in Latin America: a systematic review of social–economic impact
Epilepsy surgery remains underutilized in Latin America despite its proven effectiveness for drug-resistant epilepsy. Structural and socioeconomic barriers may contribute to limited access and delayed intervention. To systematically evaluate the clinical characteristics, surgical outcomes, and socioeconomic barriers to accessibility associated with epilepsy surgery in Latin America. A systematic review was conducted following PRISMA guidelines. Searches were performed in PubMed, Scopus, ScienceDirect, Web of Science, and SciELO. Studies were included if they reported original data on epilepsy surgery in Latin American populations. Data on demographics, epilepsy type, and surgical outcomes were extracted and analyzed descriptively. Barriers such as geographic centralization, economic constraints, lack of specialized centers, and limited diagnostic infrastructure were also identified and examined. Of 103 initial records, 10 studies met all inclusion criteria. Most were retrospective observational studies from Colombia, Brazil, Mexico, and Chile. The mean age at surgery was 30.3 years, with an average diagnostic-to-surgery delay of 17.1 years. Mesial temporal lobe epilepsy was the most common subtype. Seizure freedom (Engel Class I) was achieved in 43.7% to 85% of cases. However, only 3.8% of eligible patients underwent surgery in some cohorts. Barriers included geographic centralization, economic constraints, lack of specialized centers, limited diagnostic infrastructure, cultural stigma, and under-referral from physicians. Quality-of-life improvements and psychosocial reintegration were observed postoperatively, yet disparities in access persisted. Despite favorable surgical outcomes, epilepsy surgery in Latin America remains significantly delayed and centralized. Health system limitations and socioeconomic inequities continue to restrict timely and equitable access. Regional policies must prioritize early referral pathways, surgical infrastructure, and financial protection to reduce the epilepsy treatment gap.
- 27 October 2025
- Published by Springer Nature in Neurosurgical Review
- Vol. 48 (1) , 1-41
Determinants of diagnostic accuracy and therapeutic outcomes of SEEG in epilepsy: a systematic review
Stereoelectroencephalography (SEEG) is a cornerstone in the presurgical evaluation of drug-resistant focal epilepsy. Despite its growing adoption, variability in outcomes and complication rates suggests the influence of multiple technical, institutional, and contextual factors. A systematic review was conducted in accordance with PRISMA 2020 guidelines and registered in PROSPERO (CRD420251065875). Six databases were searched up to July 2024. Eligible studies included original research in English or Spanish reporting on SEEG procedures in patients with drug-resistant epilepsy, with outcomes related to diagnostic accuracy, complications, and therapeutic interventions. Data were extracted and synthesized narratively across five thematic domains. Fifty studies involving 6,054 patients were included. Most were retrospective and conducted in high-income countries. Epileptogenic zone (EZ) identification rates ranged from 11.6% to 100%, with over 30 studies reporting rates ≥ 90%. A total of 465 SEEG-related complications were reported, predominantly intracranial hemorrhages. Lower complication rates were observed in high-volume centers using robotic or frame-based systems. Post-SEEG interventions, primarily surgical resections, led to favorable outcomes, with Engel Class I achieved in 551 patients. Institutional experience and access to advanced technologies emerged as key determinants of safety and efficacy. SEEG is a highly effective diagnostic and therapeutic modality in epilepsy surgery. However, its performance is strongly influenced by surgical expertise, procedural planning, and institutional context. Standardizing protocols, expanding training, and improving access in underserved regions are essential to optimize outcomes and ensure equitable care.
- 27 October 2025
- Published by Springer Nature in Neurosurgical Review
- Vol. 48 (1) , 1-41
Determinants of diagnostic accuracy and therapeutic outcomes of SEEG in epilepsy: a systematic review
Stereoelectroencephalography (SEEG) is a cornerstone in the presurgical evaluation of drug-resistant focal epilepsy. Despite its growing adoption, variability in outcomes and complication rates suggests the influence of multiple technical, institutional, and contextual factors. A systematic review was conducted in accordance with PRISMA 2020 guidelines and registered in PROSPERO (CRD420251065875). Six databases were searched up to July 2024. Eligible studies included original research in English or Spanish reporting on SEEG procedures in patients with drug-resistant epilepsy, with outcomes related to diagnostic accuracy, complications, and therapeutic interventions. Data were extracted and synthesized narratively across five thematic domains. Fifty studies involving 6,054 patients were included. Most were retrospective and conducted in high-income countries. Epileptogenic zone (EZ) identification rates ranged from 11.6% to 100%, with over 30 studies reporting rates ≥ 90%. A total of 465 SEEG-related complications were reported, predominantly intracranial hemorrhages. Lower complication rates were observed in high-volume centers using robotic or frame-based systems. Post-SEEG interventions, primarily surgical resections, led to favorable outcomes, with Engel Class I achieved in 551 patients. Institutional experience and access to advanced technologies emerged as key determinants of safety and efficacy. SEEG is a highly effective diagnostic and therapeutic modality in epilepsy surgery. However, its performance is strongly influenced by surgical expertise, procedural planning, and institutional context. Standardizing protocols, expanding training, and improving access in underserved regions are essential to optimize outcomes and ensure equitable care.