Claim Missing Document
Check
Articles

Found 9 Documents
Search

Interpretable Machine Learning for Chronic Kidney Disease Diagnosis: A Gaussian Processes Approach Noviandy, Teuku Rizky; Idroes, Ghifari Maulana; Syukri, Maimun; Idroes, Rinaldi
Indonesian Journal of Case Reports Vol. 2 No. 1 (2024): June 2024
Publisher : Heca Sentra Analitika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.60084/ijcr.v2i1.204

Abstract

Chronic Kidney Disease (CKD) is a global health issue impacting over 800 million people, characterized by a gradual loss of kidney function leading to severe complications. Traditional diagnostic methods, relying on laboratory tests and clinical assessments, have limitations in sensitivity and are prone to human error, particularly in the early stages of CKD. Recent advances in machine learning (ML) offer promising tools for disease diagnosis, but a lack of interpretability often hinders their adoption in clinical practice. Gaussian Processes (GP) provide a flexible ML model capable of delivering predictions and uncertainty estimates, essential for high-stakes medical applications. However, the integration of GP with interpretable methods remains underexplored. We developed an interpretable CKD classification model to address this knowledge gap by combining GP with Shapley Additive Explanations (SHAP). We assessed the model's performance using three GP kernels (Radial Basis Function, Matern, and Rational Quadratic). The results show that the Rational Quadratic kernel outperforms the other kernels, achieving an accuracy of 98.75%, precision of 100%, sensitivity of 97.87%, specificity of 100%, and an F1-score of 98.51%. SHAP values indicate that haemoglobin and specific gravity are the most influential features. The results demonstrate that the Rational Quadratic kernel enhances predictive accuracy and provides robust uncertainty estimates and interpretable explanations. This combination of accuracy and interpretability supports clinicians in making informed decisions and improving patient management and outcomes in CKD. Our study connects advanced ML techniques with practical medical applications, leading to more effective and reliable ML-driven healthcare solutions.
Advanced Anemia Classification Using Comprehensive Hematological Profiles and Explainable Machine Learning Approaches Noviandy, Teuku Rizky; Idroes, Ghifari Maulana; Suhendra, Rivansyah; Bakri, Tedy Kurniawan; Idroes, Rinaldi
Infolitika Journal of Data Science Vol. 2 No. 2 (2024): November 2024
Publisher : Heca Sentra Analitika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.60084/ijds.v2i2.237

Abstract

Anemia is a common health issue with serious clinical effects, making timely and accurate diagnosis essential to prevent complications. This study explores the use of machine learning (ML) methods to classify anemia and its subtypes using detailed hematological data. Six ML models were tested: Gradient Boosting, Random Forest, Naive Bayes, Logistic Regression, Support Vector Machine, and K-Nearest Neighbors. The dataset was preprocessed using feature standardization and the Synthetic Minority Oversampling Technique (SMOTE) to address class imbalance. Gradient Boosting delivered the highest accuracy, sensitivity, and F1-score, establishing itself as the top-performing model. SHapley Additive exPlanations (SHAP) analysis was applied to enhance model interpretability, identifying key predictive features. This study highlights the potential of explainable ML to develop efficient, accurate, and scalable tools for anemia diagnosis, fostering improved healthcare outcomes globally.
Enhancing Early Detection of Alzheimer's Disease through MRI using Explainable Artificial Intelligence Noviandy, Teuku Rizky; Idroes, Ghifari Maulana; Purnawarman, Adi; Imran, Imran; Lestari, Nova Dian; Hastuti, Sri; Idroes, Rinaldi
Indonesian Journal of Case Reports Vol. 2 No. 2 (2024): December 2024
Publisher : Heca Sentra Analitika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.60084/ijcr.v2i2.255

Abstract

Alzheimer’s disease is a progressive brain disorder that causes memory loss and cognitive decline, affecting millions of people worldwide. Early detection is critical for slowing the disease's progression and improving patient outcomes. Magnetic Resonance Imaging (MRI) is widely used to identify brain changes associated with AD, but subtle abnormalities in the early stages are often difficult to detect using traditional methods. In this study, we used a deep learning approach with a model called ResNet-50 to analyze MRI scans and classify patients into four categories: Non-Demented, Very Mild Demented, Mild Demented, and Moderate Demented. The model was trained using MRI images, achieving an accuracy of 95.63%, with strong sensitivity, precision, and specificity. To make the model’s predictions understandable for healthcare professionals, we applied a technique called Grad-CAM, which highlights areas of the brain that influenced the model’s decisions. These visual explanations help clinicians see and trust the reasoning behind the AI's results. While the model performed well overall, misclassifications between adjacent disease stages were observed, likely due to class imbalance and subtle brain changes. This study demonstrates that explainable AI tools can improve early detection of Alzheimer’s disease, supporting clinicians in making accurate and timely diagnoses. Future work will focus on expanding the dataset and combining MRI with other clinical information to enhance the tool's reliability in real-world settings.
Hybrid Handwash with Silver Nanoparticles from Calotropis gigantea Leaves and Patchouli Oil: Development and Properties Salsabila, Indah; Khairan, Khairan; Kemala, Pati; Idroes, Ghifari Maulana; Isnaini, Nadia; Maulydia, Nur Balqis; El-Shazly, Mohamed; Idroes, Rinaldi
Malacca Pharmaceutics Vol. 2 No. 2 (2024): September 2024
Publisher : Heca Sentra Analitika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.60084/mp.v2i2.206

Abstract

When washing hands, handwashing is one way to prevent diseases caused by bacteria such as Staphylococcus aureus and Escherichia coli, the most common bacteria that can cause infections. The production of handwash utilizing silver nanoparticles as an active antibacterial agent remains a relatively infrequent practice. The synthesis of silver nanoparticles from the leaves of Calotropis gigantea, which grows in the geothermal area of Ie Seu-um Aceh Besar, has been carried out using the green synthesis method and hybrid green synthesis with patchouli oil. Handwash with active ingredients such as silver nanoparticles was successfully formulated, evaluated, and tested against S. aureus and E. coli. The organoleptic characteristics, pH, viscosity, foam height measurements, density, irritation, and antibacterial activity against S. aureus and E. coli were evaluated. The results showed that the organoleptic properties of the handwash with silver nanoparticles were not changed during a 30-day storage period, with pH values in the range of 9.7-10.3, and did not cause irritation upon using silver nanoparticle handwash. The best formula for handwashing with silver nanoparticles in inhibiting the growth of S. aureus and E. coli bacteria was F2, with inhibition zones of 12.9 ± 2.85 mm and 10.95 ± 0.8 mm, respectively. The formulated handwash with silver nanoparticles met the requirements of good liquid soap according to the Indonesian National Standard (SNI) with potent antibacterial activity.
Application of Ensemble Machine Learning Methods for QSAR Classification of Leukotriene A4 Hydrolase Inhibitors in Drug Discovery Noviandy, Teuku Rizky; Idroes, Ghifari Maulana; Mohd Fauzi, Fazlin; Idroes, Rinaldi
Malacca Pharmaceutics Vol. 2 No. 2 (2024): September 2024
Publisher : Heca Sentra Analitika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.60084/mp.v2i2.217

Abstract

Inflammatory diseases such as asthma, rheumatoid arthritis, and cardiovascular conditions are driven by overproduction of leukotriene B4 (LTB4), a potent inflammatory mediator. Leukotriene A4 hydrolase (LTA4H) plays a critical role in converting leukotriene A4 into LTB4, making it a prime target for drug discovery. Despite ongoing efforts, developing effective LTA4H inhibitors has been challenging due to the complex binding properties of the enzyme and the structural diversity of potential inhibitors. Traditional drug discovery methods, like high-throughput screening (HTS), are often time-consuming and inefficient, prompting the need for more advanced approaches. Quantitative Structure-Activity Relationship (QSAR) modeling, enhanced by ensemble machine learning techniques, provides a promising solution by enabling accurate prediction of compound bioactivity based on molecular descriptors. In this study, six ensemble machine learning methods—AdaBoost, Extra Trees, Gradient Boosting, LightGBM, Random Forest, and XGBoost—were employed to classify LTA4H inhibitors. The dataset, comprising 636 compounds labeled as active or inactive based on pIC50 values, was processed to extract 450 molecular descriptors after feature engineering. The results show that the LightGBM model achieved the highest classification accuracy (83.59%) and Area Under the Curve (AUC) value (0.901), outperforming other models. XGBoost and Random Forest also demonstrated strong performance, with AUC values of 0.890 and 0.895, respectively. The high sensitivity (95.24%) of the XGBoost model highlights its ability to accurately identify active compounds, though it exhibited slightly lower specificity (61.36%), indicating a higher false-positive rate. These findings suggest that ensemble machine learning models, particularly LightGBM, are highly effective in predicting bioactivity, offering valuable tools for early-stage drug discovery. The results indicate that ensemble methods significantly enhance QSAR model accuracy, making them viable for identifying promising LTA4H inhibitors, potentially accelerating the development of anti-inflammatory therapies.
QSAR Modeling for Predicting Beta-Secretase 1 Inhibitory Activity in Alzheimer's Disease with Support Vector Regression Noviandy, Teuku Rizky; Idroes, Ghifari Maulana; Tallei, Trina Ekawati; Handayani, Dian; Idroes, Rinaldi
Malacca Pharmaceutics Vol. 2 No. 2 (2024): September 2024
Publisher : Heca Sentra Analitika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.60084/mp.v2i2.226

Abstract

Alzheimer's disease (AD) is a neurodegenerative disorder characterized by cognitive decline, with the accumulation of β-amyloid (Aβ) plaques playing a key role in its progression. Beta-Secretase 1 (BACE1) is a crucial enzyme in Aβ production, making it a prime therapeutic target for AD treatment. However, designing effective BACE1 inhibitors has been challenging due to poor selectivity and limited blood-brain barrier permeability. To address these challenges, we employed a machine learning approach using Support Vector Regression (SVR) in a Quantitative Structure-Activity Relationship (QSAR) model to predict the inhibitory activity of potential BACE1 inhibitors. Our model, trained on a dataset of 7,298 compounds from the ChEMBL database, accurately predicted pIC50 values using molecular descriptors, achieving an R² of 0.690 on the testing set. The model's performance demonstrates its utility in prioritizing drug candidates, potentially accelerating drug discovery. This study highlights the effectiveness of computational approaches in optimizing drug discovery and suggests that further refinement could enhance the model’s predictive power for AD therapeutics.
Long-Term Impact of Dirty and Clean Energy on Indonesia’s Economic Growth: Before and During the COVID-19 Pandemic Ringga, Edi Saputra; Hafizah, Iffah; Idroes, Ghifari Maulana; Amalina, Faizah; Kadri, Mirzatul; Idroes, Ghalieb Mutig; Noviandy, Teuku Rizky; Hardi, Irsan
Grimsa Journal of Business and Economics Studies Vol. 2 No. 1 (2025): January 2025
Publisher : Graha Primera Saintifika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61975/gjbes.v2i1.49

Abstract

Dirty (non-renewable) energy, considered environmentally harmful due to greenhouse gas emissions, is contrasted with clean (renewable) energy, which is believed to have positive ecological impacts that can boost economic growth in the long term. This study analyzes the long-term effects of electricity generation from both dirty and clean energy sources on economic growth in Indonesia, using data from two periods: before the COVID-19 pandemic (2000–2019) and the full period including the COVID-19 pandemic (2000–2022). Empirical findings from Fully Modified Ordinary Least Squares (FMOLS) and Dynamic Ordinary Least Squares (DOLS) methods reveal that dirty energy significantly impacts long-term economic growth in both periods, while clean energy does not have a substantial effect. A robustness check conducted using the Canonical Cointegrating Regression (CCR) method confirms that dirty energy continues to play a crucial role in Indonesia's long-term economic growth. A key finding is that the positive impact of dirty energy generation on economic growth was stronger in the full period including the COVID-19 pandemic compared to before. This suggests that dirty energy contributed more to economic growth during the pandemic. The study recommends a balanced approach to economic growth by prioritizing the transition to clean energy while recognizing the importance of dirty energy in Indonesia's economy. This transition should be gradual, using the current role of dirty energy to support economic development while investing in clean energy alternatives for sustainable growth.
Predicting AXL Tyrosine Kinase Inhibitor Potency Using Machine Learning with Interpretable Insights for Cancer Drug Discovery Noviandy, Teuku Rizky; Idroes, Ghifari Maulana; Harnelly, Essy; Sari, Irma; Fauzi, Fazlin Mohd; Idroes, Rinaldi
Heca Journal of Applied Sciences Vol. 3 No. 1 (2025): March 2025
Publisher : Heca Sentra Analitika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.60084/hjas.v3i1.270

Abstract

AXL tyrosine kinase plays a critical role in cancer progression, metastasis, and therapy resistance, making it a promising target for therapeutic intervention. However, traditional drug discovery methods for developing AXL inhibitors are resource-intensive, time-consuming, and often fail to provide detailed insights into molecular determinants of potency. To address this gap, we applied machine learning techniques, including Random Forest, Gradient Boosting, Support Vector Regression, and Decision Tree models, to predict the potency (pIC50) of AXL inhibitors using a dataset of 972 compounds with 550 molecular descriptors. Our results demonstrate that the Random Forest model outperformed others with an R² of 0.703, MAE of 0.553, RMSE of 0.720, and PCC of 0.841, showcasing strong predictive accuracy. SHAP analysis identified critical molecular features, such as RNCG and TopoPSA(NO), as key contributors to inhibitor potency, providing interpretable insights into structure-activity relationships. These findings highlight the potential of machine learning to accelerate the identification and optimization of AXL inhibitors, bridging the gap between computational predictions and rational drug design and paving the way for effective cancer therapeutics.
Inductive Biases in Feature Reduction for QSAR: SHAP vs. Autoencoders Noviandy, Teuku Rizky; Idroes, Ghifari Maulana; Lala, Andi; Helwani, Zuchra; Idroes, Rinaldi
Infolitika Journal of Data Science Vol. 3 No. 1 (2025): May 2025
Publisher : Heca Sentra Analitika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.60084/ijds.v3i1.306

Abstract

Machine learning models in drug discovery often depend on high-dimensional molecular descriptors, many of which may be redundant or irrelevant. Reducing these descriptors is essential for improving model performance, interpretability, and computational efficiency. This study compares two widely used reduction strategies: SHAP-based feature selection and autoencoder-based compression, within the context of Quantitative Structure-Activity Relationship (QSAR) classification. LightGBM is used as a consistent modeling framework to evaluate models trained on all descriptors, the top 50 and 100 SHAP-ranked descriptors, and a 64-dimensional autoencoder embedding. The results show that SHAP-based selection produces interpretable and stable models with minimal performance loss, particularly when using the top 100 descriptors. In contrast, the autoencoder achieves the highest test performance by capturing nonlinear patterns in a compact, low-dimensional representation, although this comes at the cost of interpretability and consistency across data splits. These findings reflect the differing inductive biases of each method. SHAP prioritizes sparsity and attribution, while autoencoders focus on reconstruction and continuity. The analysis emphasizes that descriptor reduction strategies are not interchangeable. SHAP-based selection is suitable for applications where interpretability and reliability are essential, such as in hypothesis-driven or regulatory settings. Autoencoders are more appropriate for performance-driven tasks, including virtual screening. The choice of reduction strategy should be guided not only by performance metrics but also by the specific modeling requirements and assumptions relevant to cheminformatics workflows.