Eka Widrian Suradji
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Eka Widrian Suradji has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Amanda Dianky
LIF Indonesia, DKI Jakarta, Indonesia
2 shared publications - Amos W. H. Lim
Actxa Pte Ltd, Singapore, Singapore
2 shared publications - Entong Zhou
Actxa Pte Ltd, Singapore, Singapore
2 shared publications - Ernest Gamaliel Masayoshi Takashi
Integrated Research Laboratory, Krida Wacana Christian University, DKI Jakarta, Indonesia
2 shared publications - Fredicia Fredicia
Computer Science Department, Faculty of Engineering and Computer Science, Krida Wacana Christian University, DKI Jakarta, Indonesia
2 shared publications - Li-Feng Zhang
School of Biological Sciences, Nanyang Technological University, 60 Nanyang Drive, Singapore 637551
2 shared publications
Latest Publications
- Open Access
- 28 October 2026
- Published by Universitas Airlangga in Journal of Information Systems Engineering and Business Intelligence
- Vol. 12 (3) , 566-579
Explainable AI-Driven Deep Learning Model for Transparent and Accurate Pneumonia Detection Using Chest X-Rays
Background: Pneumonia remains a national health concern with high morbidity and mortality among vulnerable populations. Chest X-ray is the most widely used diagnostic modality due to its accessibility and low cost. However, its interpretation heavily relies on radiologist expertise and often exhibits substantial interobserver variability, potentially leading to inconsistent diagnoses. Although deep learning models have shown remarkable accuracy in medical image analysis, their adoption in clinical practice is limited by the lack of transparency. XAI has therefore emerged as a promising approach to enhance interpretability and clinical trust. Objective: This study aims to develop a ResNet-50-based explainable deep learning framework for pneumonia detection in CXR by integrating XAI techniques in the form of Grad-CAM and LIME Methods: A CNN model with a ResNet-50 backbone was trained and tested using a CXR dataset from clinical sources at partner hospitals in Indonesia. Grad-CAM enhances transparency by highlighting relevant lung areas, and LIME offers local feature based explanations by identifying the most important image regions for model decisions. Performance was evaluated using metrics such as accuracy, precision, recall, F1-score, IoU, Dice Score, mean Average Precision (mAP@0.5), and the agreement level with radiologists measured by Cohen’s Kappa test. Results: The model achieved an accuracy of 93.2%, precision of 92.5%, recall of 94.1%, F1-score of 93.3%, IoU of 78.4%, Dice score of 87.9%, and mAP@0.5 of 89.7%, with an average inference time of 120 ms per image. Grad-CAM and SHAP visualizations showed up to 91% of the area matched the radiologist’s assessment, indicating nearly perfect agreement, with a Kappa value of 0.90. Conclusion: Combining ResNet-50 with Grad-CAM creates a pneumonia detection model that is accurate, easy to understand, and matches doctors' opinions. This approach could help doctors trust artificial intelligence more and encourage wider use of technology in healthcare, especially in resource limited settings. Keywords: Pneumonia detection; Chest X-ray; Deep learning; Explainable AI; ResNet-50; Grad-CAM; Medical image analysis
- 28 October 2026
- Published by Universitas Airlangga in Journal of Information Systems Engineering and Business Intelligence
- Vol. 12 (3) , 566-579
Open AccessExplainable AI-Driven Deep Learning Model for Transparent and Accurate Pneumonia Detection Using Chest X-Rays
Background: Pneumonia remains a national health concern with high morbidity and mortality among vulnerable populations. Chest X-ray is the most widely used diagnostic modality due to its accessibility and low cost. However, its interpretation heavily relies on radiologist expertise and often exhibits substantial interobserver variability, potentially leading to inconsistent diagnoses. Although deep learning models have shown remarkable accuracy in medical image analysis, their adoption in clinical practice is limited by the lack of transparency. XAI has therefore emerged as a promising approach to enhance interpretability and clinical trust. Objective: This study aims to develop a ResNet-50-based explainable deep learning framework for pneumonia detection in CXR by integrating XAI techniques in the form of Grad-CAM and LIME Methods: A CNN model with a ResNet-50 backbone was trained and tested using a CXR dataset from clinical sources at partner hospitals in Indonesia. Grad-CAM enhances transparency by highlighting relevant lung areas, and LIME offers local feature based explanations by identifying the most important image regions for model decisions. Performance was evaluated using metrics such as accuracy, precision, recall, F1-score, IoU, Dice Score, mean Average Precision (mAP@0.5), and the agreement level with radiologists measured by Cohen’s Kappa test. Results: The model achieved an accuracy of 93.2%, precision of 92.5%, recall of 94.1%, F1-score of 93.3%, IoU of 78.4%, Dice score of 87.9%, and mAP@0.5 of 89.7%, with an average inference time of 120 ms per image. Grad-CAM and SHAP visualizations showed up to 91% of the area matched the radiologist’s assessment, indicating nearly perfect agreement, with a Kappa value of 0.90. Conclusion: Combining ResNet-50 with Grad-CAM creates a pneumonia detection model that is accurate, easy to understand, and matches doctors' opinions. This approach could help doctors trust artificial intelligence more and encourage wider use of technology in healthcare, especially in resource limited settings. Keywords: Pneumonia detection; Chest X-ray; Deep learning; Explainable AI; ResNet-50; Grad-CAM; Medical image analysis
- Open Access
- 8 January 2026
- Published by JMIR Publications Inc. in JMIR Research Protocols
- Vol. 15, e76558
Assessment of Blood Glucose Measurement Using New Noninvasive Technology: Protocol and Methodology
Background: Diabetes mellitus (DM) is a major noncommunicable disease with a significant increase in prevalence, especially in low- and middle-income countries. The latest International Diabetes Federation Diabetes Atlas (2025) reports that 11.1% of the adult population (20 to 79 years old) is living with diabetes, with over 4 in 10 unaware of their condition. Early diagnosis and treatment of diabetes reduce the risk and slow the progression of debilitating complications, such as amputation, vision loss, renal failure, cardiovascular disease, dementia, some cancers, and infections like tuberculosis and severe COVID-19. Current screening methods for diabetes are invasive and costly. This has limited their utilization, especially in high-density populations and low- and middle-income countries such as Indonesia. Blood Glucose Evaluation and Monitoring (BGEM) is a machine learning algorithm developed by Actxa to analyze photoplethysmography data from wearable devices for diabetic risk assessment. Its noninvasive and user-friendly nature makes it a strong candidate for fulfilling the need for a diabetes screening or monitoring tool. Objective: The aim of this study is to collect a large and more diverse dataset for the training of BGEM machine learning models. This dataset is intended to improve the model’s generalizability and to evaluate its performance across different age groups, racial groups, and skin types, with the goal of enhancing accuracy and robustness for diabetes risk assessment and glucose monitoring. Methods: Adult participants aged 18 years and above, with either a diabetic or a nondiabetic history, who reside in Greater Jakarta Area, Indonesia, were approached for recruitment. Blood glucose was assessed using laboratory blood analysis from capillary or plasma samples after fasting and at 1, 2, and 3 hours after a meal. BGEM data were also collected at each of these time points. Anthropological measurements with a standardized questionnaire on physical activity, demographic information, respondent’s diabetic status, and current medications taken were also collected. Results: Between June and October 2024, 885 participants were enrolled. Eight photoplethysmography recordings per participant were collected across 4 meal time points using 2 wearable devices in addition to the collection of clinical measurements, blood sampling, and related questionnaires. Conclusions: This protocol paper outlines the methodology designed for assessing and interpreting participants’ blood sugar profiles, especially on demographic variability, in order to evaluate BGEM, a photoplethysmography-based artificial intelligence model designed to estimate blood glucose levels and diabetic risk. The clinical trial was conducted on Indonesian participants with and without diabetes while considering various influencing factors. This dataset is designed to enable assessment of the model’s performance across diverse racial, risk factors, and skin-type groups, with the aim of making the model more valid and reliable.
- 8 January 2026
- Published by JMIR Publications Inc. in JMIR Research Protocols
- Vol. 15, e76558
Open AccessAssessment of Blood Glucose Measurement Using New Noninvasive Technology: Protocol and Methodology
Background: Diabetes mellitus (DM) is a major noncommunicable disease with a significant increase in prevalence, especially in low- and middle-income countries. The latest International Diabetes Federation Diabetes Atlas (2025) reports that 11.1% of the adult population (20 to 79 years old) is living with diabetes, with over 4 in 10 unaware of their condition. Early diagnosis and treatment of diabetes reduce the risk and slow the progression of debilitating complications, such as amputation, vision loss, renal failure, cardiovascular disease, dementia, some cancers, and infections like tuberculosis and severe COVID-19. Current screening methods for diabetes are invasive and costly. This has limited their utilization, especially in high-density populations and low- and middle-income countries such as Indonesia. Blood Glucose Evaluation and Monitoring (BGEM) is a machine learning algorithm developed by Actxa to analyze photoplethysmography data from wearable devices for diabetic risk assessment. Its noninvasive and user-friendly nature makes it a strong candidate for fulfilling the need for a diabetes screening or monitoring tool. Objective: The aim of this study is to collect a large and more diverse dataset for the training of BGEM machine learning models. This dataset is intended to improve the model’s generalizability and to evaluate its performance across different age groups, racial groups, and skin types, with the goal of enhancing accuracy and robustness for diabetes risk assessment and glucose monitoring. Methods: Adult participants aged 18 years and above, with either a diabetic or a nondiabetic history, who reside in Greater Jakarta Area, Indonesia, were approached for recruitment. Blood glucose was assessed using laboratory blood analysis from capillary or plasma samples after fasting and at 1, 2, and 3 hours after a meal. BGEM data were also collected at each of these time points. Anthropological measurements with a standardized questionnaire on physical activity, demographic information, respondent’s diabetic status, and current medications taken were also collected. Results: Between June and October 2024, 885 participants were enrolled. Eight photoplethysmography recordings per participant were collected across 4 meal time points using 2 wearable devices in addition to the collection of clinical measurements, blood sampling, and related questionnaires. Conclusions: This protocol paper outlines the methodology designed for assessing and interpreting participants’ blood sugar profiles, especially on demographic variability, in order to evaluate BGEM, a photoplethysmography-based artificial intelligence model designed to estimate blood glucose levels and diabetic risk. The clinical trial was conducted on Indonesian participants with and without diabetes while considering various influencing factors. This dataset is designed to enable assessment of the model’s performance across diverse racial, risk factors, and skin-type groups, with the aim of making the model more valid and reliable.
- Open Access
- 26 April 2025
- Published by JMIR Publications Inc. in JMIR Preprints
Assessment of Blood Glucose measurement using New Non-Invasive Technology: Protocol & Methodology (Preprint)
BACKGROUND Diabetes Mellitus is a major non-communicable disease with significant increase in prevalence, especially in low and middle-income countries. The latest IDF Diabetes Atlas (2025) reports that 11,1%, or about 1 in 9, of the adult population (20-79 years old) is living with diabetes, with over 4 in 10 unaware that they have the condition. This Prevalence is expected to increase to 1 in 8 adults by the year 2050. Early diagnosis and treatment of Diabetes reduces the risk and slows the progression of debilitating complications such as amputation, vision loss, and renal failure, cardiovascular disease, dementia, some cancers, and infections such as tuberculosis and severe COVID-19. Current screening methods for diabetes are invasive and costly. This has limited its more widespread utilisation especially in a high-density population, middle-low income country such as Indonesia. Blood Glucose Evaluation and Monitoring (BGEM) is a machine learning (ML) algorithm developed by Actxa to analyze Photoplethysmography (PPG) data from wearable devices for diabetic risk assessment. Its non-invasive and user-friendly nature makes it a strong candidate for fulfilling the need for a diabetes screening tool. OBJECTIVE The Aim of this study is to enhance BGEM’s performance on a large and diverse data set with an emphasis on the detailed blood sugar fluctuation, also known as glycaemic variability, under semi-controlled conditions in an Indonesian population. METHODS Adult subjects aged 18 years old and above, either with a diabetic or non-diabetic history that resides in Greater Jakarta Area, Indonesia were recruited. The study will explore BGEM blood glucose prediction capabilities compared to laboratory blood analysis from capillary or plasma samples at after fasting, 1 hour, 2 hour and 3 hours after meal. In addition to PPG and blood data collection, anthropological measurement, a standardize questionnaire on activity, demographic information and diabetic status were also conducted to provide a more complete dataset. RESULTS A total of 885 subjects were included into the study from June to October 2024, 473 were diabetic subjects and 412 were non-diabetic subjects. The blood sugar profiles of the subjects will be studied and analysed. BGEM’s performance will be assessed on this Indonesian dataset on glycaemic variability. CONCLUSIONS This protocol paper outlines the methodology designed for subject’s blood sugar profiles especially on glycaemic variability in order to evaluate BGEM, a PPG-based AI model designed to estimate blood glucose levels and diabetic risk. The clinical trial was conducted on both diabetic (DM) and non-diabetic (non-DM) Indonesian subjects, while considering various influencing factors. The results will provide objective evidence on the validity and use of a non-invasive technique for the measurement of blood sugar levels using wearables. CLINICALTRIAL Clinical trial registration NCT06642467 Institutional Review Board of Ukrida faculty of medicine & health sciences ethical committee 1779/SLKE/IM/UKKW /FKIK/KEPK /VII/2024
- 26 April 2025
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessAssessment of Blood Glucose measurement using New Non-Invasive Technology: Protocol & Methodology (Preprint)
BACKGROUND Diabetes Mellitus is a major non-communicable disease with significant increase in prevalence, especially in low and middle-income countries. The latest IDF Diabetes Atlas (2025) reports that 11,1%, or about 1 in 9, of the adult population (20-79 years old) is living with diabetes, with over 4 in 10 unaware that they have the condition. This Prevalence is expected to increase to 1 in 8 adults by the year 2050. Early diagnosis and treatment of Diabetes reduces the risk and slows the progression of debilitating complications such as amputation, vision loss, and renal failure, cardiovascular disease, dementia, some cancers, and infections such as tuberculosis and severe COVID-19. Current screening methods for diabetes are invasive and costly. This has limited its more widespread utilisation especially in a high-density population, middle-low income country such as Indonesia. Blood Glucose Evaluation and Monitoring (BGEM) is a machine learning (ML) algorithm developed by Actxa to analyze Photoplethysmography (PPG) data from wearable devices for diabetic risk assessment. Its non-invasive and user-friendly nature makes it a strong candidate for fulfilling the need for a diabetes screening tool. OBJECTIVE The Aim of this study is to enhance BGEM’s performance on a large and diverse data set with an emphasis on the detailed blood sugar fluctuation, also known as glycaemic variability, under semi-controlled conditions in an Indonesian population. METHODS Adult subjects aged 18 years old and above, either with a diabetic or non-diabetic history that resides in Greater Jakarta Area, Indonesia were recruited. The study will explore BGEM blood glucose prediction capabilities compared to laboratory blood analysis from capillary or plasma samples at after fasting, 1 hour, 2 hour and 3 hours after meal. In addition to PPG and blood data collection, anthropological measurement, a standardize questionnaire on activity, demographic information and diabetic status were also conducted to provide a more complete dataset. RESULTS A total of 885 subjects were included into the study from June to October 2024, 473 were diabetic subjects and 412 were non-diabetic subjects. The blood sugar profiles of the subjects will be studied and analysed. BGEM’s performance will be assessed on this Indonesian dataset on glycaemic variability. CONCLUSIONS This protocol paper outlines the methodology designed for subject’s blood sugar profiles especially on glycaemic variability in order to evaluate BGEM, a PPG-based AI model designed to estimate blood glucose levels and diabetic risk. The clinical trial was conducted on both diabetic (DM) and non-diabetic (non-DM) Indonesian subjects, while considering various influencing factors. The results will provide objective evidence on the validity and use of a non-invasive technique for the measurement of blood sugar levels using wearables. CLINICALTRIAL Clinical trial registration NCT06642467 Institutional Review Board of Ukrida faculty of medicine & health sciences ethical committee 1779/SLKE/IM/UKKW /FKIK/KEPK /VII/2024