Journal of Precision Biosciences
Precision Biosciences | Online ISSN 3064-9226
29
Citations
120.3k
Views
53
Articles
Volume 8 Number 1 2026
REVIEWS (Open Access)
Computational Intelligence and patient-derived models for predicting treatment response and toxicity in Rare Disease Management: A Review of Emerging Diagnostic and Predictive Paradigms
Hares Bin Syed Md. Rifat 1*
Journal of Precision Biosciences 8 (1) 1-8 https://doi.org/10.25163/biosciences.8110585
Submitted: 18 August 2026 Revised: 10 October 2026 Accepted: 17 October 2026 Published: 19 October 2026
Abstract
Rare diseases and rare cancers are individually uncommon yet collectively burdensome, and the data needed to model them are scarce. Computational intelligence, from random forests to graph neural networks, is often proposed as a remedy, but its evidence has accumulated mostly in oncology and chemical toxicology, where datasets and biological test systems are more mature. We asked how well machine-learning and deep-learning models, alongside patient-derived organoids (PDO) and xenografts (PDX), predict diagnosis, treatment response and toxicity, and what this might teach rare-disease medicine. We searched PubMed, Scopus, Web of Science and Embase, screened 501 de-duplicated records, and included 22 studies (2,814 patients) in a structured synthesis with exploratory random-effects pooling. Two reviewers screened independently, and bias was appraised with QUADAS-2 and the Newcastle–Ottawa Scale. Pooled sensitivity was 0.88 (95% CI 0.85–0.91), specificity 0.86 (0.83–0.89) and the area under the curve 0.92; risk stratification yielded a hazard ratio of 2.18 (1.76–2.70). Heterogeneity was moderate (I² = 57%), and small-study asymmetry was detected (Egger p < 0.05). In Tox21 benchmarks, graph-based models averaged an AUC of 0.90–0.91, whereas DeepTox (0.85) did no better than simpler random-forest and naive-Bayes models. PDO and PDX concordance with clinical response varied by tumour type, and several reported values repeated across tumours, so we interpret them cautiously. Most studies lacked external validation, and few addressed non-oncological rare diseases. The approach is promising but not yet proven reliable; progress will depend on external validation, common reporting standards and rare-disease-specific datasets.
Keywords: artificial intelligence; machine learning; graph neural networks; patient-derived organoids; patient-derived xenografts; toxicity prediction; rare diseases
References
Biau, G., & Scornet, E. (2016). A random forest guided tour. Test, 25(2), 197–227. https://doi.org/10.1007/s11749-016-0481-7
Capuzzi, S. J., Politi, R., Isayev, O., Farag, S., & Tropsha, A. (2016). QSAR modeling of Tox21 challenge stress response and nuclear receptor signaling toxicity assays. Frontiers in Environmental Science, 4, Article 3. https://doi.org/10.3389/fenvs.2016.00003
Cremer, J., Medrano Sandonas, L., Tkatchenko, A., Clevert, D.-A., & De Fabritiis, G. (2023). Equivariant graph neural networks for toxicity prediction. Chemical Research in Toxicology, 36(10), 1561–1573. https://doi.org/10.1021/acs.chemrestox.3c00032
Cybula, M., Wang, L., Drumond-Bock, A. L., Moxley, K. M., Benbrook, D. M., Gunderson-Jackson, C., Ruiz-Echevarria, M. J., Bhattacharya, R., Mukherjee, P., et al. (2021). Patient-derived xenografts of high-grade serous ovarian cancer subtype as a powerful tool in pre-clinical research. Cancers, 13(24), Article 6288. https://doi.org/10.3390/cancers13246288
Dankner, M., Romero, J. M., Magrill, J., Kalashnikov, N., Luo, M., Chen, O., Atallah, A., Lazaratos, A.-M., Busque, S., Ma, R., et al. (2025). Patient-derived xenografts (PDX) versus patient-derived organoids (PDO) as predictors of clinical response to anti-cancer therapies. Journal of Clinical Oncology, 43(16_suppl), e15169. https://doi.org/10.1200/JCO.2025.43.16_suppl.e15169
de Witte, C. J., Valle-Inclan, J. E., Hami, N., Lõhmussaar, K., Kopper, O., Vreuls, C. P. H., Jonges, G. N., van Diest, P., Nguyen, L., Clevers, H., et al. (2020). Patient-derived ovarian cancer organoids mimic clinical response and exhibit heterogeneous inter- and intrapatient drug responses. Cell Reports, 31(11), Article 107762. https://doi.org/10.1016/j.celrep.2020.107762
Demircioglu, A. (2019). Radiomics: AI based image analysis. Der Pathologe, 40(Suppl. 3), 271–276. https://doi.org/10.1007/s00292-019-00704-8
Drwal, M. N., Siramshetty, V. B., Banerjee, P., Goede, A., Preissner, R., & Dunkel, M. (2015). Molecular similarity-based predictions of the Tox21 screening outcome. Frontiers in Environmental Science, 3, Article 54. https://doi.org/10.3389/fenvs.2015.00054
Esteva, A., Robicquet, A., Ramsundar, B., Kuleshov, V., DePristo, M., Chou, K., Cui, C., Corrado, G., Thrun, S., & Dean, J. (2019). A guide to deep learning in healthcare. Nature Medicine, 25(1), 24–29. https://doi.org/10.1038/s41591-018-0316-z
Gao, J., Lan, J., Liao, H., Yang, F., Qiu, P., Jin, F., Wang, S., Shen, L., Chao, T., Zhang, C., et al. (2023). Promising preclinical patient-derived organoid (PDO) and xenograft (PDX) models in upper gastrointestinal cancers: Progress and challenges. BMC Cancer, 23, Article 1205. https://doi.org/10.1186/s12885-023-11434-9
Gao, Y., Zhou, R., Huang, J.-F., Hu, B., Cheng, J.-W., Huang, X.-W., Wang, P.-X., Peng, H.-X., Guo, W., Zhou, J., et al. (2021). Patient-derived xenograft models for intrahepatic cholangiocarcinoma and their application in guiding personalized medicine. Frontiers in Oncology, 11, Article 704042. https://doi.org/10.3389/fonc.2021.704042
Gargeya, R., & Leng, T. (2017). Automated identification of diabetic retinopathy using deep learning. Ophthalmology, 124(7), 962–969. https://doi.org/10.1016/j.ophtha.2017.02.008
Higgins, J. P. T., & Green, S. (Eds.). (2011). Cochrane handbook for systematic reviews of interventions (Version 5.1.0). The Cochrane Collaboration.
Johnson, J. M., & Khoshgoftaar, T. M. (2019). Survey on deep learning with class imbalance. Journal of Big Data, 6, Article 27. https://doi.org/10.1186/s40537-019-0192-5
Kermany, D. S., Goldbaum, M., Cai, W., Valentim, C. C. S., Liang, H., Baxter, S. L., … Zhang, K. (2018). Identifying medical diagnoses and treatable diseases by image-based deep learning. Cell, 172(5), 1122–1131.e9. https://doi.org/10.1016/j.cell.2018.02.010
Kim, J., & Minna, J. D. (2023). Moving toward precision medicine with lung cancer organoids. Cell Reports Medicine, 4(2), Article 100952. https://doi.org/10.1016/j.xcrm.2023.100952
Kohli, M. D., Summers, R. M., & Geis, J. R. (2017). Medical image data and datasets in the era of machine learning—Whitepaper from the 2016 C-MIMI meeting dataset session. Journal of Digital Imaging, 30(4), 392–399. https://doi.org/10.1007/s10278-017-9976-3
LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436–444. https://doi.org/10.1038/nature14539
Lipton, Z. C. (2018). The mythos of model interpretability. Queue, 16(3), 31–57. https://doi.org/10.1145/3236386.3241340
Lu, Y., Lei, X., Xu, Y., Li, Y., Wang, R., Wang, S., Wu, A., & Qin, C. (2026). Advancing cancer research: Cutting-edge insights from colorectal cancer patient-derived xenograft mouse models. Genes & Diseases, 13, Article 101634. https://doi.org/10.1016/j.gendis.2025.101634
Madabhushi, A., & Lee, G. (2016). Image analysis and machine learning in digital pathology: Challenges and opportunities. Medical Image Analysis, 33, 170–175. https://doi.org/10.1016/j.media.2016.06.037
Mayr, A., Klambauer, G., Unterthiner, T., & Hochreiter, S. (2016). DeepTox: Toxicity prediction using deep learning. Frontiers in Environmental Science, 3, Article 80. https://doi.org/10.3389/fenvs.2015.00080
Miotto, R., Wang, F., Wang, S., Jiang, X., & Dudley, J. T. (2018). Deep learning for healthcare: Review, opportunities and challenges. Briefings in Bioinformatics, 19(6), 1236–1246. https://doi.org/10.1093/bib/bbx044
Murdoch, T. B., & Detsky, A. S. (2013). The inevitable application of big data to health care. JAMA, 309(13), 1351–1352. https://doi.org/10.1001/jama.2013.393
Na, D., Chae, J., Cho, S.-Y., Kang, W., Lee, A., Min, S., Kang, J., Kim, M. J., Choi, J., Lee, W., et al. (2021). Predictive biomarkers for 5-fluorouracil and oxaliplatin-based chemotherapy in gastric cancers via profiling of patient-derived xenografts. Nature Communications, 12, Article 4840. https://doi.org/10.1038/s41467-021-25122-4
Obermeyer, Z., & Emanuel, E. J. (2016). Predicting the future—Big data, machine learning, and clinical medicine. The New England Journal of Medicine, 375(13), 1216–1219. https://doi.org/10.1056/NEJMp1606181
Rajkomar, A., Dean, J., & Kohane, I. (2019). Machine learning in medicine. The New England Journal of Medicine, 380(14), 1347–1358. https://doi.org/10.1056/NEJMra1814259
Romero, J. M., Magrill, J., Kalashnikov, N., Luo, Y. Z., Chen, O. J., Busque, S., Ma, R., Atallah, A., Lazaratos, A.-M., Mendelson, D., et al. (2025). Comparative analysis of patient-derived organoids and patient-derived xenografts as avatar models for predicting response to anti-cancer therapy [Preprint]. medRxiv. https://doi.org/10.1101/2025.08.10.25333051
Sauer, R., Becker, H., Hohenberger, W., Rödel, C., Wittekind, C., Fietkau, R., Martus, P., Tschmelitsch, J., Hager, E., Hess, C. F., et al. (2004). Preoperative versus postoperative chemoradiotherapy for rectal cancer. The New England Journal of Medicine, 351(17), 1731–1740. https://doi.org/10.1056/NEJMoa040694
Setio, A. A. A., Ciompi, F., Litjens, G., Gerke, P., Jacobs, C., van Riel, S. J., … van Ginneken, B. (2016). Pulmonary nodule detection in CT images: False positive reduction using multi-view convolutional networks. IEEE Transactions on Medical Imaging, 35(5), 1160–1169. https://doi.org/10.1109/TMI.2016.2536809
Shen, D., Wu, G., & Suk, H.-I. (2017). Deep learning in medical image analysis. Annual Review of Biomedical Engineering, 19, 221–248. https://doi.org/10.1146/annurev-bioeng-071516-044442
Strobl, C., Boulesteix, A.-L., Zeileis, A., & Hothorn, T. (2007). Bias in random forest variable importance measures: Illustrations, sources and a solution. BMC Bioinformatics, 8, Article 25. https://doi.org/10.1186/1471-2105-8-25
Su, C., Olsen, K. A., Bond, C. E., & Whitehall, V. L. J. (2023). The efficacy of using patient-derived organoids to predict treatment response in colorectal cancer. Cancers, 15(3), Article 805. https://doi.org/10.3390/cancers15030805
Teng, Z., Li, L., Xin, Z., Xiang, D., Huang, J., Zhou, H., Shi, F., Zhu, W., Cai, J., Peng, T., & Chen, X. (2024). A literature review of artificial intelligence (AI) for medical image segmentation: From AI and explainable AI to trustworthy AI. Quantitative Imaging in Medicine and Surgery, 14(12), 9620–9652. https://doi.org/10.21037/qims-24-723
Topol, E. J. (2019). Deep medicine: How artificial intelligence can make healthcare human again. Basic Books.
Ueda, D., Kakinuma, T., Fujita, S., Kamagata, K., Fushimi, Y., Ito, R., Matsui, Y., Nozaki, T., Nakaura, T., Fujima, N., Tatsugami, F., Yanagawa, M., Hirata, K., Yamada, A., Tsuboyama, T., Kawamura, M., Fujioka, T., & Naganawa, S. (2024). Fairness of artificial intelligence in healthcare: Review and recommendations. Japanese Journal of Radiology, 42(1), 3–15. https://doi.org/10.1007/s11604-023-01474-3
Van der Velden, B. H. M., Kuijf, H. J., Gilhuijs, K. G. A., & Viergever, M. A. (2022). Explainable artificial intelligence (XAI) in deep learning-based medical image analysis. Medical Image Analysis, 79, Article 102470. https://doi.org/10.1016/j.media.2022.102470
Vlachogiannis, G., Hedayat, S., Vatsiou, A., Jamin, Y., Fernández-Mateos, J., Khan, K., Lampis, A., Eason, K., Huntingford, I., Burke, R., et al. (2018). Patient-derived organoids model treatment response of metastatic gastrointestinal cancers. Science, 359(6378), 920–926. https://doi.org/10.1126/science.aao2774
Wang, Z., & Deisboeck, T. S. (2014). Computational modeling of cancer nanomedicine: Multi-scale modeling of drug transport and tumor response. Drug Discovery Today, 19(5), 650–658. https://doi.org/10.1016/j.drudis.2013.06.015
Wu, Z., Ramsundar, B., Feinberg, E. N., Gomes, J., Geniesse, C., Pappu, A. S., Leswing, K., & Pande, V. (2018). MoleculeNet: A benchmark for molecular machine learning. Chemical Science, 9(2), 513–530. https://doi.org/10.1039/C7SC02664A
Xie, J., Liu, W., Hu, W., Ouyang, M., & Huang, T. (2025). Graph neural network-based toxicity prediction by integrating molecular fingerprints and knowledge graph features. Toxics, 13(11), Article 953. https://doi.org/10.3390/toxics13110953
Xu, J., Pham, M. D., Corbo, V., Ponz-Sarvise, M., Oni, T., Öhlund, D., & Hwang, C.-I. (2025). Advancing pancreatic cancer research and therapeutics: The transformative role of organoid technology. Experimental & Molecular Medicine, 57, 50–58. https://doi.org/10.1038/s12276-024-01378-w
Yasaka, K., & Abe, O. (2018). Deep learning and artificial intelligence in radiology: Current applications and future directions. PLOS Medicine, 15(11), Article e1002707. https://doi.org/10.1371/journal.pmed.1002707
Yu, J., Qin, B., Moyer, A. M., Sinnwell, J. P., Thompson, K. J., Copland, J. A., Marlow, L. A., Miller, J. L., Yin, P., Gao, B., et al. (2017). Establishing and characterizing patient-derived xenografts using pre-chemotherapy percutaneous biopsy and post-chemotherapy surgical samples from a prospective neoadjuvant breast cancer study. Breast Cancer Research, 19, Article 130. https://doi.org/10.1186/s13058-017-0920-8
Zanella, E. R., Grassi, E., & Trusolino, L. (2022). Towards precision oncology with patient-derived xenografts. Nature Reviews Clinical Oncology, 19(11), 719–732. https://doi.org/10.1038/s41571-022-00682-6
Zhao, X., Zhang, S., Zhang, T., Cao, Y., & Liu, J. (2025). A small-scale data-driven and graph neural network-based toxicity prediction method of compounds. Computational Biology and Chemistry, 117, Article 108393. https://doi.org/10.1016/j.compbiolchem.2025.108393