John Jaime Sprockel

Dr. John Jaime Sprockel


Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
3 January 2022 in Heart & Lung
Verified
Journal Article
Closed access
JSJohn Jaime Sprockel
John Jaime Sprockel
JRJuan Manuel Rincon
Juan Manuel Rincon
MLManuela Alejandra Rondón López
Manuela Alejandra Rondón López
MZMarisol Bejarano Zuleta
Marisol Bejarano Zuleta
NCNathaly Castellanos
Nathaly Castellanos
JFJuan José Diaztagle Fernández
Juan José Diaztagle Fernández

7 October 2023 in Medicina Intensiva (English Edition)
Verified
Journal Article
Closed access
JSJohn Jaime Sprockel
John Jaime Sprockel
VZVictoria Eugenia Coral Zuñiga
Victoria Eugenia Coral Zuñiga
EGEliana Angarita Gonzalez
Eliana Angarita Gonzalez
SRSebastián Camilo Tabares Rodríguez
Sebastián Camilo Tabares Rodríguez
MAMaría Paula Carrillo Ayerbe
María Paula Carrillo Ayerbe
JFJuan José Diaztagle Fernández
Juan José Diaztagle Fernández

7 July 2025 in Journal of Imaging
Verified
Journal Article
Open access
PDF file
RPRafael Parra-Medina
Rafael Parra-Medina
CZCarlos Zambrano-Betancourt
Carlos Zambrano-Betancourt
SPSergio Peña-Rojas
Sergio Peña-Rojas
LQLina Quintero-Ortiz
Lina Quintero-Ortiz
MBMaría Victoria Caro Barbosa
María Victoria Caro Barbosa
AMAndres Mosquera
Andres Mosquera
Traditionally, Helicobacter pylori (HP) gastritis has been diagnosed by pathologists through the examination of gastric biopsies using optical microscopy with standard hematoxylin and eosin (H&E) staining. However, with the adoption of digital pathology, the identification of HP faces certain limitations, particularly due to insufficient resolution in some scanned images. Moreover, interobserver variability has been well documented in the traditional diagnostic approach, which may further complicate consistent interpretation. In this context, deep convolutional neural network (DCNN) models are showing promising results in the automated detection of this infection in whole-slide images (WSIs). The aim of the present article is to detect the presence of HP infection from our own institutional dataset of histopathological gastric biopsy samples using different pretrained and recognized DCNN and AutoML approaches. The dataset comprises 100 H&E-stained WSIs of gastric biopsies. HP infection was confirmed previously using immunohistochemical confirmation. A total of 45,795 patches were selected for model development. InceptionV3, Resnet50, and VGG16 achieved AUC (area under the curve) values of 1. However, InceptionV3 showed superior metrics such as accuracy (97%), recall (100%), F1 score (97%), and MCC (93%). BoostedNet and AutoKeras achieved accuracy, precision, recall, specificity, and F1 scores less than 85%. The InceptionV3 model was used for external validation, and the predictions across all patches yielded a global accuracy of 78%. In conclusion, DCNN models showed stronger potential for diagnosing HP in gastric biopsies compared with the auto ML approach. However, due to variability across pathology applications, no single model is universally optimal. A problem-specific approach is essential. With growing WSI adoption, DL can improve diagnostic accuracy, reduce variability, and streamline pathology workflows using automation.

1 July 2014 in Revista Colombiana de Cardiología
Verified
Journal Article
Open access
JSJohn Jaime Sprockel
John Jaime Sprockel
JDJuan J. Diaztagle
Juan J. Diaztagle
WAWilson Alzate
Wilson Alzate
EGEnrique González
Enrique González
ResumenIntroducciónEl infarto agudo de miocardio representa la primera causa de muerte no trasmisible en el mundo. Una de las herramientas que sirven como soporte a las decisiones en su diagnóstico son las redes neuronales, de las cuales se ha demostrado un buen nivel de precisión.MétodosSe realizó el entrenamiento y la prueba de varias redes neuronales, con diferentes arquitecturas para el diagnóstico del infarto, a partir de los datos de la escala de clasificación de la probabilidad de angina de Braunwald en un grupo de pacientes que ingresaron por dolor torácico al servicio de urgencias del Hospital San José de Bogotá.ResultadosSe generaron 40 redes que fueron probadas en 5 experimentos de los cuales se obtuvo mayor precisión diagnóstica con el modelo de 5 entradas electrocardiográficas más troponina, aunque el mejor valor predictivo negativo se alcanzó en el modelo con 10 variables clínicas, electrocardiográficas y troponina. Varias de las redes diseñadas tuvieron una sensibilidad y una especificidad del 100%. Se requiere un estudio de validación para comprobar estos hallazgos.ConclusionesCon los resultados encontrados para las redes neuronales en la literatura y en este estudio se puede considerar el uso de esta estrategia de inteligencia computacional en la práctica.AbstractIntroductionMyocardial infarction represents the leading cause of death by a noncommunicable disease worldwide; one of the tools that serve as decision support for establishing a diagnosis are neural networks. They have been shown to have a good level of accuracy.MethodsTraining and testing of several neural networks was performed with different architectures for the diagnosis of the myocardial infarction in a group of patients admitted with chest pain emergency room in the Hospital de San José, Bogotá. This was carried out according to data from the incidence scale of Braunwald's classification of unstable angina.ResultsForty networks were generated and tested in five experiments obtaining an accurate diagnostic with the electrocardiographic pattern of five entries and troponin. The negative predictive value was 100% in the model with ten clinical variables, electrocardiogram and troponin. Some of the designed networks had a sensitivity and specificity of 100%. A validation study to verify these findings is required.ConclusionsWith the results found for neural networks in the literature and in the present study, we should consider the practical use of this computational intelligence strategy in daily practice

1 March 2015 in Critical Pathways in Cardiology: A Journal of Evidence-Based Medicine
Verified
Journal Article
Closed access
JSJohn Jaime Sprockel
John Jaime Sprockel
LDLina Paola Md Tovar Diaz
Lina Paola Md Tovar Diaz
OOOlga Paola Md Omaña Orduz
Olga Paola Md Omaña Orduz
MSMiguel Angel Md Saavedra
Miguel Angel Md Saavedra
WSWalter Gabriel Md Chaves Santiago
Walter Gabriel Md Chaves Santiago
JFJuan José Md Diaztagle Fernández
Juan José Md Diaztagle Fernández
Introduction: Door-to-electrocardiogram (D2E) time is recognized as one of the quality parameters in the attention of acute coronary syndromes. Electrocardiogram realization within periods below 10 minutes increases the possibility to achieve quick and effective reperfusion, which has an impact on outcomes. Objective: To describe the results of a strategy whose goal is to improve the fulfillment of the D2E deadline below 10 minutes in adults who attend the emergency service due to chest pain with clinical suspicion of acute coronary syndromes. Methods: Before-and-after study that assesses D2E time upon the implementation of actions for the reorganization of the process of attention of the patients with chest pain within the context of the implementation of a critical pathway. Results: A total of 373 patients were assessed, 204 in the before stage and 169 in the after stage. The median D2E time was 16 minutes in the before stage, in 41% of the cases it was below 10 minutes; upon the implementation of the change in the process of attention of chest pain the median was 5 minutes, with 63% of the cases below 10 minutes, exhibiting a statistically significant difference. Conclusions: The actions taken led to a lower median of D2E time and a higher percentage of patients with times below 10 minutes. However, further interventions are required to assure a higher number of patients with D2E times below 10 minutes.