Feature Importance–Driven Multimodal Learning for Medical Diagnosis Classification Using Clinical and Symptom Text Data


Indra Waspada(1*); Satriawan Rasyid Purnama(2); Alfonso Clement Sutantio(3); Alwey Hakim(4);

(1) Universitas Diponegoro
(2) Universitas Diponegoro
(3) Universitas Diponegoro
(4) Universitas Diponegoro
(*) Corresponding Author

  

Abstract


The integration of structured clinical measurements and unstructured textual symptom descriptions poses persistent challenges for automated medical diagnosis, particularly due to feature heterogeneity and class imbalance in real-world outpatient data. This study proposes a feature importance–driven multimodal machine learning framework for multi-class medical diagnosis classification that jointly models numerical clinical attributes and free-text symptom narratives within a unified pipeline. Beyond overall performance comparison, the proposed approach systematically examines the interaction between model architecture and feature importance through three controlled configurations: base, strong-feature, and weak-feature settings. Six supervised learning algorithms are evaluated using stratified five-fold cross-validation and imbalance-aware metrics. The results show that feature importance–driven modeling yields strongly model-dependent performance characteristics. Bagging-based tree ensembles benefit most from strong-feature selection, with the Extra Trees classifier achieving the best overall performance, reaching a macro-averaged F1-score of 0.821, compared to 0.811 in the base configuration and 0.642 when only weak features are retained. Conversely, margin-based classifiers rely on distributed feature representations. The kernel-based Support Vector Machine performs poorly under strong-feature selection (F1-score 0.450) but achieves a substantially higher F1-score of 0.795 and a macro-averaged recall of 0.808 under the weak-feature configuration. Linear SVM demonstrates stable behavior across configurations, maintaining a macro-averaged F1-score between 0.798 and 0.810, while attaining the highest overall recall of 0.819. These findings indicate that feature importance should be treated as a model-aware analytical tool for aligning feature selection strategies with the inductive bias of the learning algorithm, supporting robust and clinically meaningful diagnostic classification.


Keywords


Health Diagnosis Classification; Medical Text Mining; TF–IDF; Ensemble Learning; Clinical Data Preprocessing; Multiclass Classification; Imbalanced Data

  
  

Full Text:

PDF
  

Article Metrics

Abstract view: 97 times
PDF view: 12 times 		     

Digital Object Identifier

doi  https://doi.org/10.33096/ilkom.v18i2.3289.255-267 		  

Cite

How to cite item

References


P. Zhang, X. Huang, and M. Li, “Disease Prediction and Early Intervention System Based on Symptom Similarity Analysis,” IEEE Access, vol. 7, pp. 176484–176494, 2019.

J. Latif, C. Xiao, S. Tu, S. U. Rehman, A. Imran, and A. Bilal, “Implementation and Use of Disease Diagnosis Systems for Electronic Medical Records Based on Machine Learning: A Complete Review,” IEEE Access, vol. 8, pp. 150489–150513, 2020.

M. E. Hossain, A. Khan, M. A. Moni, and S. Uddin, “Use of Electronic Health Data for Disease Prediction: A Comprehensive Literature Review,” IEEE/ACM Transactions on Computational Biology and Bioinformatics, vol. 18, no. 2, pp. 745–758, 2021.

S. Priyanka, S. Keerthika, S. Santhiya, S. J. Malar, A. Malavika, and T. D. Babu, “Enhancing Disease Diagnosis with Machine Learning Based Symtom Prediction,” Proceedings - 2024 International Conference on Emerging Innovations and Advanced Computing, INNOCOMP 2024, pp. 555–562, 2024.

Y. Yu, M. Li, L. Liu, Y. Li, and J. Wang, “Clinical big data and deep learning: Applications, challenges, and future outlooks,” Big Data Mining and Analytics, vol. 2, no. 4, pp. 288–305, 2019.

N. Mumtazah, I. Waspada, K. N. Dinar Mutiara, and S. Adhy, “A Combination of Data Mining Methods for Disease Classification Using Patient-Perceived Symptoms from Medical Records,” Proceedings - International Conference on Informatics and Computational Sciences, pp. 426–431, 2024.

K. J. Soujanya, A. Kodipalli, S. Gosai, B. J. Sneha, and T. Rao, “Symptoms-based Classification of Disease Using Various ML Algorithms and Interpretation using LIME and SHAP KERNELS,” 2024 4th Asian Conference on Innovation in Technology, ASIANCON 2024, pp. 1–6, 2024.

D. Nishad, A. Mishra, and N. Goyal, “Symptom-Based Disease Prediction Using Machine Learning,” Proceedings of the 14th International Conference on Cloud Computing, Data Science and Engineering, Confluence 2024, pp. 416–420, 2024.

A. Jindal, R. Kamboj, S. Pathak, K. Dubey, and A. Vajpayee, “Disease Prediction Based on Symptoms and Drug Recommendation,” 2024 11th International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions), ICRITO 2024, pp. 1–6, 2024.

Md Russel Hossain, Shohoni Mahabub, Abdullah Al Masum, and Israt Jahan, “Natural Language Processing (NLP) in Analyzing Electronic Health Records for Better Decision Making,” Journal of Computer Science and Technology Studies, vol. 6, no. 5, pp. 216–228, Dec. 2024.

R. F. Oybek Kizi, T. P. Theodore Armand, and H. C. Kim, “A Review of Deep Learning Techniques for Leukemia Cancer Classification Based on Blood Smear Images,” Applied Biosciences, vol. 4, no. 1, 2025.

Y. H. Chang et al., “Using machine learning and natural language processing in triage for prediction of clinical disposition in the emergency department,” BMC Emergency Medicine, vol. 24, no. 1, 2024.

Y. Hao, M. Usama, J. Yang, M. S. Hossain, and A. Ghoneim, “Recurrent convolutional neural network based multimodal disease risk prediction,” Future Generation Computer Systems, vol. 92, pp. 76–83, 2019.

M. K. Siam, M. J. Hossain Faruk, B. He, J. Q. Cheng, and H. Gu, “Multimodal Models in Healthcare: Methods, Challenges, and Future Directions for Enhanced Clinical Decision Support,” Information (Switzerland), vol. 16, no. 11, 2025.

S. Shurrab, A. Guerra-Manzanares, A. Magid, B. Piechowski-Jozwiak, S. F. Atashzar, and F. E. Shamout, “Multimodal Machine Learning for Stroke Prognosis and Diagnosis: A Systematic Review,” IEEE Journal of Biomedical and Health Informatics, vol. 28, no. 11, pp. 6958–6973, 2024.

H. Han, M. Huang, Y. Zhang, and J. Liu, “Decision support system for medical diagnosis utilizing imbalanced clinical data,” Applied Sciences (Switzerland), vol. 8, no. 9, 2018.

I. Waspada, A. Wibowo, and N. S. Meraz, “Supervised Machine Learning Model for MicoRNA Expression Data in Cancer,” Jurnal Ilmu Komputer dan Informasi, vol. 10, no. 2, pp. 108–115, Jun. 2017.

B. Percha, “Modern Clinical Text Mining: A Guide and Review,” Annual Review of Biomedical Data Science, vol. 4, pp. 165–187, 2021.

I. D. Mienye and Y. Sun, “A Survey of Ensemble Learning: Concepts, Algorithms, Applications, and Prospects,” IEEE Access, vol. 10, no. September, pp. 99129–99149, 2022.

T. Naufal, R. Mahendra, and A. F. Wicaksono, “Sentences, entities, and keyphrases extraction from consumer health forums using multi-task learning,” Journal of Biomedical Semantics, vol. 16, no. 1, 2025.

R. N. Hanami, R. Mahendra, and A. F. Wicaksono, “Semantic classification of Indonesian consumer health questions,” Journal of Biomedical Semantics, vol. 16, no. 1, 2025.

A. Kline et al., “Multimodal machine learning in precision health: A scoping review,” npj Digital Medicine, vol. 5, no. 1, pp. 1–14, 2022.

F. Ali et al., “A smart healthcare monitoring system for heart disease prediction based on ensemble deep learning and feature fusion,” Information Fusion, vol. 63, no. April, pp. 208–222, 2020.

M. Salmi, D. Atif, D. Oliva, A. Abraham, and S. Ventura, Handling imbalanced medical datasets: review of a decade of research, vol. 57, no. 10. Springer Netherlands, 2024.

I. Kolyshkina and S. Simoff, “Interpretability of Machine Learning Solutions in Industrial Decision Engineering,” 2019, pp. 156–170.

I. Kolyshkina and S. Simoff, “Interpretability of Machine Learning Solutions in Public Healthcare: The CRISP-ML Approach,” Frontiers in Big Data, vol. 4, no. May, 2021.

S. Studer et al., “Towards CRISP-ML(Q): A Machine Learning Process Model with Quality Assurance Methodology,” Machine Learning and Knowledge Extraction, vol. 3, no. 2, pp. 392–413, 2021.

C. P. Chai, “Comparison of text preprocessing methods,” Natural Language Engineering, vol. 29, no. 3, pp. 509–553, 2023.

M. Yetisgen-Yildiz, M. L. Gunn, F. Xia, and T. H. Payne, “A text processing pipeline to extract recommendations from radiology reports,” Journal of Biomedical Informatics, vol. 46, no. 2, pp. 354–362, 2013.

A. Spooner et al., “Benchmarking ensemble machine learning algorithms for multi-class, multi-omics data integration in clinical outcome prediction,” Briefings in Bioinformatics, vol. 26, no. 2, 2025.


Refbacks

  • There are currently no refbacks.


Copyright (c) 2026 Indra Waspada, Satriawan Rasyid Purnama, Alfonso Clement Sutantio, Alwey Hakim

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.