Menjelajahi Tantangan dan Kemajuan Dalam Deep Learning Untuk Readmisi Pasien: Tinjauan Literatur Sistematis
DOI:
https://doi.org/10.52436/1.jpti.681Keywords:
Deep Learning, Explainable AI, Federated Learning, LSTM, Prediksi Kesehatan, Readmisi PasienAbstract
Prediksi readmisi pasien telah menjadi tantangan utama dalam meningkatkan kualitas layanan kesehatan. Penelitian ini menyajikan tinjauan sistematis terhadap algoritma deep learning, dengan menganalisis 30 artikel dari database utama seperti Scopus, IEEE Xplore, dan ScienceDirect. Proses pencarian literatur dilakukan menggunakan kombinasi kata kunci seperti 'deep learning', 'readmisi pasien', dan 'prediksi kesehatan' serta mengikuti kerangka PRISMA untuk menyaring studi yang relevan berdasarkan kriteria inklusi dan eksklusi. Hasil penelitian menunjukkan bahwa algoritma Long Short-Term Memory (LSTM) mendominasi dalam menangkap pola temporal dari data Electronic Health Record (EHR), dengan kinerja mencapai Area Under the Curve (AUC) hingga 88,4%. Selain itu, Convolutional Neural Networks (CNN) terbukti efektif untuk menganalisis teks tidak terstruktur, sementara model Transformer menunjukkan potensi dalam menangani dataset berskala besar. Tantangan utama yang ditemukan meliputi ketidakseimbangan data dan heterogenitas data medis, yang dapat mempengaruhi akurasi prediksi. Solusi inovatif seperti federated learning dan Explainable AI (XAI) diusulkan untuk meningkatkan interpretabilitas dan efisiensi algoritma dalam konteks klinis. Penelitian ini memberikan wawasan berharga mengenai potensi dan keterbatasan deep learning dalam prediksi readmisi pasien serta menawarkan rekomendasi strategis untuk pengembangan teknologi kesehatan yang lebih baik.
Downloads
References
“Medicare Drug Price Negotiation | CMS.” Accessed: Jan. 22, 2025. [Online]. Available: https://www.cms.gov/inflation-reduction-act-and-medicare/medicare-drug-price-negotiation
“Profil Kesehatan Indonesia 2023.” Accessed: Jan. 22, 2025. [Online]. Available: https://www.kemkes.go.id/id/profil-kesehatan-indonesia-2023
Z. Wu et al., “Medical long-tailed learning for imbalanced data: Bibliometric analysis,” Comput. Methods Programs Biomed., vol. 247, p. 108106, Apr. 2024, doi: 10.1016/j.cmpb.2024.108106.
X. Liu, Y. Chen, J. Bae, H. Li, J. Johnston, and T. Sanger, “Predicting Heart Failure Readmission from Clinical Notes Using Deep Learning,” in 2019 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), Nov. 2019, pp. 2642–2648. doi: 10.1109/BIBM47256.2019.8983095.
J. Xie, B. Zhang, J. Ma, D. Zeng, and J. Lo-Ciganic, “Readmission Prediction for Patients with Heterogeneous Medical History: A Trajectory-Based Deep Learning Approach,” ACM Trans Manage Inf Syst, vol. 13, no. 2, p. 14:1-14:27, Oktober 2021, doi: 10.1145/3468780.
H.-Y. Chen, H.-M. Wang, C.-H. Lin, R. Yang, and C.-C. Lee, “Lung Cancer Prediction Using Electronic Claims Records: A Transformer-Based Approach,” IEEE J. Biomed. Health Inform., vol. 27, no. 12, pp. 6062–6073, Dec. 2023, doi: 10.1109/JBHI.2023.3324191.
G. Huang, Y. Li, S. Jameel, Y. Long, and G. Papanastasiou, “From explainable to interpretable deep learning for natural language processing in healthcare: How far from reality?,” Comput. Struct. Biotechnol. J., vol. 24, pp. 362–373, Dec. 2024, doi: 10.1016/j.csbj.2024.05.004.
Y. Shahzad, H. Javed, H. Farman, J. Ahmad, B. Jan, and A. A. Nassani, “Optimized Predictive Framework for Healthcare Through Deep Learning,” Comput. Mater. Contin., vol. 67, no. 2, pp. 2463–2480, 2021, doi: 10.32604/cmc.2021.014904.
T. Khanna and S. Mathur, “An Enhanced Analysis of Cloud-Based Deep Learning Model in Smart Healthcare Management,” 2024 2nd Int. Conf. Disruptive Technol. ICDT, pp. 705–710, Mar. 2024, doi: 10.1109/ICDT61202.2024.10489824.
M. J. Page et al., “The PRISMA 2020 statement: an updated guideline for reporting systematic reviews,” BMJ, vol. 372, p. n71, Mar. 2021, doi: 10.1136/bmj.n71.
J. F. Silva and S. Matos, “Modelling patient trajectories using multimodal information,” J. Biomed. Inform., vol. 134, p. 104195, Oct. 2022, doi: 10.1016/j.jbi.2022.104195.
B. Davazdahemami, P. Peng, and D. Delen, “A deep learning approach for predicting early bounce-backs to the emergency departments,” Healthc. Anal., vol. 2, p. 100018, Nov. 2022, doi: 10.1016/j.health.2022.100018.
Z. Xu, Q. Zhang, and P. S. F. Yip, “Predicting post-discharge self-harm incidents using disease comorbidity networks: A retrospective machine learning study,” J. Affect. Disord., vol. 277, pp. 402–409, Dec. 2020, doi: 10.1016/j.jad.2020.08.044.
C. Qian, P. Leelaprachakul, M. Landers, C. Low, A. K. Dey, and A. Doryab, “Prediction of Hospital Readmission from Longitudinal Mobile Data Streams,” Sensors, vol. 21, no. 22, p. 7510, Nov. 2021, doi: 10.3390/s21227510.
Z. Wang et al., “Using Deep Learning to Identify High-Risk Patients with Heart Failure withReduced Ejection Fraction,” J. Health Econ. Outcomes Res., vol. 8, no. 2, pp. 6–13, Jul. 2021, doi: 10.36469/jheor.2021.25753.
J. Q. Sheng, P. J.-H. Hu, X. Liu, T.-S. Huang, and Y. H. Chen, “Predictive Analytics for Care and Management of Patients With Acute Diseases: Deep Learning–Based Method to Predict Crucial Complication Phenotypes,” J. Med. Internet Res., vol. 23, no. 2, p. e18372, Feb. 2021, doi: 10.2196/18372.
S. J. Im, Y. Xu, and J. Watson, “Semantic-based Attention model for Hospital Readmission Prediction,” in 2022 IEEE International Conference on Big Data (Big Data), Dec. 2022, pp. 1836–1841. doi: 10.1109/BigData55660.2022.10020315.
W. Liu et al., “Predicting 30-day hospital readmissions using artificial neural networks with medical code embedding,” PLOS ONE, vol. 15, no. 4, p. e0221606, Apr. 2020, doi: 10.1371/journal.pone.0221606.
C.-C. Chiu, C.-M. Wu, T.-N. Chien, L.-J. Kao, and C. Li, “Predicting ICU Readmission from Electronic Health Records via BERTopic with Long Short Term Memory Network Approach,” J. Clin. Med., vol. 13, no. 18, Art. no. 18, Jan. 2024, doi: 10.3390/jcm13185503.
H.-Y. Chen, H.-M. Wang, C.-H. Lin, R. Yang, and C.-C. Lee, “Lung Cancer Prediction Using Electronic Claims Records: A Transformer-Based Approach,” IEEE J. Biomed. Health Inform., vol. 27, no. 12, pp. 6062–6073, Dec. 2023, doi: 10.1109/JBHI.2023.3324191.
T. B. Sivakumar, A. Malakar, L. S, G. Shailaja, E. Kalaivani, and D. Babu K, “Enhanced Diabetes Prediction Using Deep Autoencoder Framework and Electronic Health Records,” 2024 Second Int. Conf. Adv. Inf. Technol. ICAIT, pp. 1–5, Jul. 2024, doi: 10.1109/ICAIT61638.2024.10690358.
J. Q. Sheng, P. J.-H. Hu, X. Liu, T.-S. Huang, and Y. H. Chen, “Predictive Analytics for Care and Management of Patients With Acute Diseases: Deep Learning–Based Method to Predict Crucial Complication Phenotypes,” J. Med. Internet Res., vol. 23, no. 2, p. e18372, Feb. 2021, doi: 10.2196/18372.
S. Ali, S. El-Sappagh, F. Ali, M. Imran, and T. Abuhmed, “Multitask Deep Learning for Cost-Effective Prediction of Patient’s Length of Stay and Readmission State Using Multimodal Physical Activity Sensory Data,” IEEE J. Biomed. Health Inform., vol. 26, no. 12, pp. 5793–5804, Dec. 2022, doi: 10.1109/JBHI.2022.3202178.
Y. Zhang et al., “Development of a prediction model for the risk of 30-day unplanned readmission in older patients with heart failure: A multicenter retrospective study,” Nutr. Metab. Cardiovasc. Dis., vol. 33, no. 10, pp. 1878–1887, Oct. 2023, doi: 10.1016/j.numecd.2023.05.034.
Z. Zhou, C. Fu, and R. Weibel, “SpaGAN: A spatially-aware generative adversarial network for building generalization in image maps,” Int. J. Appl. Earth Obs. Geoinformation, vol. 135, p. 104236, Dec. 2024, doi: 10.1016/j.jag.2024.104236.
Al-Azhar University et al., “Enhanced Predictive Modelling for 30-Day Readmission Diabetes Patients Based on Data Normalization Analysis,” Int. J. Intell. Eng. Syst., vol. 14, no. 4, pp. 204–216, Aug. 2021, doi: 10.22266/ijies2021.0831.19.
X. Liu, Y. Chen, J. Bae, H. Li, J. Johnston, and T. Sanger, “Predicting Heart Failure Readmission from Clinical Notes Using Deep Learning,” in 2019 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), San Diego, CA, USA: IEEE, Nov. 2019, pp. 2642–2648. doi: 10.1109/BIBM47256.2019.8983095.
O. T. Odeyomi, H. Karnati, and A. Smith, “Preserving Medical Data with Renyi Differential Privacy,” 2024 IEEE World AI IoT Congr. AIIoT, pp. 244–251, May 2024, doi: 10.1109/AIIoT61789.2024.10578985.
M.-K. Pham et al., “Forecasting Patient Early Readmission from Irish Hospital Discharge Records Using Conventional Machine Learning Models,” Diagnostics, vol. 14, no. 21, Art. no. 21, Jan. 2024, doi: 10.3390/diagnostics14212405.
A. Soliman, B. Agvall, K. Etminani, O. Hamed, and M. Lingman, “The Price of Explainability in Machine Learning Models for 100-Day Readmission Prediction in Heart Failure: Retrospective, Comparative, Machine Learning Study,” J. Med. Internet Res., vol. 25, no. 1, p. e46934, Oct. 2023, doi: 10.2196/46934.
