COMPREHENSIVE REVIEW ON THERAPEUTIC APPLICATIONS OF AI IN LEUKAEMIA: A MULTI-OMICS APPROACH

COMPREHENSIVE REVIEW ON THERAPEUTIC APPLICATIONS OF AI IN LEUKAEMIA: A MULTI-OMICS APPROACH

Yashwanth Krishna, Jayalakshmi Venugopal and Arya Sathyan *

Department of Pharmacy Practice, Approved by PCI & amp, Affiliated to The Tamil Nadu Dr. M.G.R Medical University, Coimbatore, Tamil Nadu, India.

ABSTRACT: It is leukaemia, where immature white blood cells keep growing at a very fast pace and disrupt normal blood production. While there are many advances in treatment, genetics diversity, drug resistant and technological limits remain. Likewise, such AI combined with multi dimension approaches (genetics, transcriptomics, proteomics, metabolism, and epigenetics) has altered leukaemia research. Divining the diagnosis, risk assessment and precise plan for effective treatment from vast amounts of data allowed by AI is possible. In addition, it shortens the time of diagnosis, predicts responses to therapy, and explains how it fails. By integrating AI into mitigation of CML, tyrosine kinase inhibitor is first identified and targeted therapy is guided by other key biomarkers. Same is the case for AML which is mitigated by CK inhibitors and FLT3 inhibitors. Interruption and identification of various pathways by metabolomics and proteomics provide new therapeutic targets. More and more clinical studies show that AI assisted multi-omics strategies add value in making personalized care, reducing relapse, and increasing survival. Since challenges such as data integration, algorithm transparency, computational needs and ethics require collaboration among researchers, clinicians and policymakers, instant familiarity with the technology is not negligible. With the increase in AI, it will take precision medicine to the next step and change the treatment of leukaemia.

Keywords: Artificial intelligence, Multi-omics, Leukaemia, Personalized medicine, Biomarker discovery

INTRODUCTION: Leukaemia is a class of haematological neoplasm that involves the abnormal formation of immature white blood cells and the interference with normal production of blood components by the bone marrow ^{1, 2}. It can be classified into Acute Lymphoblastic Leukaemia (ALL) and Acute Myeloid Leukaemia [AML]) and Chronic Lymphocytic Leukaemia [CLL] and Chronic Myeloid Leukaemia [CML]), with acute types progressing rapidly and chronic types often remaining asymptomatic for extended periods ^{3, 4}.

Challenges to the treatment of leukaemia including disease genetic heterogeneity, drug resistance, limitation of bone marrow transplantation, side effects of chemotherapy, lack of predictive power for response to chemotherapy ^{5, 6}. It continues to be a global health menace with an estimated 450,000 new cases a year or about 3 per cent of all cancers around the world. In particular, it is a major cause of cancer related morbidity and mortality and is particularly common in children and in the elderly.

Leukaemia is a critical hematologic malignancy with relative slow progress of their treatment in the context of cancer ⁷. The following therapy could be revolutionized by the integration of artificial intelligence (AI) with multi-omics technologies including genomics, transcriptomics, proteomics and metabolomics. Omics data is immense and AI analyses can process it to discover novel biomarkers, predict response to treatment and identify resistance mechanisms, towards developing precise, personalized treatment strategies ⁸. A multi-omics approach, combining genetic mutations, protein expression patterns and metabolic signatures allows integration and a holistic picture of the patient’s disease. AI driven models’ base therapies on patient specific patterns, optimizing outcomes while limiting adverse effects ⁹. The major goal of the study was to analyse how AI and multi-omics integration have changed leukaemia therapy in the direction of precise and data driven, personalized treatment, in order to improve patient prognosis ¹⁰. AI has an important role in leukaemia treatment by integrating complex datasets to optimize therapeutic decision making. With AI's evolution, the use in personalized treatment options for treatment of leukaemia patients is going to play an extremely important role in the present situation when it comes to limiting use of current treatment options ¹¹. Over the years, the advancements in treatment technologies have enabled better mortality rate and leukaemia prognosis, which is evident from the line graph represented based on consolidated data from the years 2000- 2023 Fig. 1 ^12,13.

FIG. 1: (ADVANCEMENT IN TREATMENT OF LEUKAEMIA OVER YEARS VS THE MORTALITIY RATE OF LEUKAEMIA TREATMENT OUT COMES)

Multi Omics & Their Role in Leukemia: Multi omics combines different types of biomaterials to gain complete picture of leukaemia. Genomics, transcriptomics, proteomics, metabolomics, and epigenomics are included Table 1. Key deal breaking genetic changes are located in AML patients due to the existence of FLT3 and NPM1 mutations or the presence of BCR-ABL1 translocation in CML patients. Diagnosis and grouping of leukaemia subtypes are as the findings can guide the doctors on the disease progression and also to select the most effective treatments ¹⁴. RNA expression pattern is studied by transcriptomics, which allows markers to detect the disease, to visualise treatment outcomes, and to predict the likelihood of relapse. Transcriptomics different leukaemia subtypes apart and also can track change in gene expression in response to treatment ¹⁵. In turn, the genomic and transcriptomic insights allow doctors to spot leukaemia earlier before symptoms begin. That leads to prompt action and tailored treatments. Uncovering protein networks and metabolic pathways that do not work right in leukaemia cells has an influence of proteomics and metabolomics. Hence both proteomics and metabolomics enable the identification of leukaemia specific markers and identify key properties of the metabolism required by leukaemia cells. That is important to distinguish leukaemia from other blood cancers. For instance, leukaemia cells often use glucose differently, using many metabolic pathways more than normal. New ways of treating the disease are thus opened up ^{16, 17}.

By studying single cells of leukaemia, single cell multi omics tech gives us even closer look and also shows differences in the disease along with finding leukaemia stem cells that can cause the disease to come back. The following findings are valuable in predicting the risk of relapse and to allow a more targeted treatment by attacking the factors that are responsible for the disease at the cellular level ^{18, 19}. Multi­ omics suggests ways in which leukaemia clones evolve, allowing doctors to predict how the disease will progress. Tracking changes in genes, epigenetics and gene expression over time help doctors predict how the disease will evolve, whether it's going to recur, and how the patient will do. It leads them to find high risk patients that may need stronger treatments or closer watch ^{20, 21}.

Transcriptomics and proteomics look for high risk signs: too much or too little of cancer-causing proteins or genes that make drugs less effective. It gives doctors a way to sort patients into risk groups more and to create treatment plans specific to a patient's own very molecular makeup ²². With regard to the diagnostic application, multiomics can help identify the specific genetic and epigenetic changes characterizing subtypes of leukaemia, for example, BCR-ABL1 in CML, or other mutations, for example, FLT3, NPM1 and IDH1/2 in AML. These mutations are not only for the classification of subtypes but also as the early prognostic marker and the relapse risk predictor for early disease stages ^{23, 24}. This generation of transcriptomics data permits predicting overexpressed genes and monitoring subtle changes in expression which could be the reflecting molecules for the treatment of the leukaemia, contributing to early diagnosis of the disease or recovery from recurrence before any symptom appearance ^{25, 26}. In contrast to proteomics and metabolomics, these signatures from product of failed protein networks and metabolic pathways carry disease specific signatures of leukaemia but not of other diseases or disorder in the patient’s blood ²⁷. This is multi omics in treatments, it identifies specific molecular targets that are unique to patients’ leukaemia subtypes for development of targeted therapies. For example, like BCR-ABL1 positive CML, tyrosine kinase inhibitors may be used, and FLT3 inhibitors could be appropriate for patients with FLT3 mutations in AML ²⁸.

Additionally, metabolomics and proteomics identify metabolic pathways that have been remodelled and become the niche where leukaemia cells depend, etc. These pathways may in fact be targeted for therapeutic use. Thus, according to Epigenomic data, it gives information of the mechanisms of drug resistance and Clinicians could develop new methods against it thus by designing drugs that target the specific mechanisms of drug resistance ^{29, 30}. This will be used to combine artificial intelligence with multiple-omics data to help analyse this type of large dataset and improve treatment decision and discover new leukaemia subtypes or more identifying drug targets ^{31, 32}. Overall, merging of multicompositional data turns over the diagnosis, prognosis and treatment of leukaemia, giving a complete and detailed point of view of the diseases at the molecular level. This gives healthcare professionals better tools for diagnosis, more accurate personalised treatment approaches, and the possible to predict relapse. And so patient outcomes improved as the side effects and relapse risks are lowered.

TABLE 1: TYPES OF MULTI OMICS

Applications of Cancer Diagnosis and Prognosis with AI: The applications of artificial intelligence (AI) to oncology are now leading transformative progress toward diagnosing, predicting, and treating cancers. In the last four years clinical practice has changed in profound ways through the integration of machine learning (ML), deep learning (DL), and other AI driven tools ^{41, 42}. Convolutional neural networks (CNNs) are as good as 95% accurate at detecting early cancers from mammograms and blood based liquid biopsy AI systems have detected cancer markers with great accuracy of greater than 90% ⁴³. AI-powered systems are also used in imaging and pathology, improving accuracy with a 30% reduction in false positives in lung CT scans and help pathologists predict molecular profiles of tumour tissue, guiding personalized treatment strategy. Predictors of risk beyond the traditional metrics are being assessed using machine learning models incorporating multiple datasets (clinical and genomic), such as in prostate and breast cancer ^{44, 45}. Researches are conducted for better treatment planning in leukaemia care in which Al also uses multi-omics and imaging data to guide radiation therapy treatment planning and to accelerate drug discovery pipelines, getting new therapies to patients faster. As Al brings these advancements, it’s creating the next frontier of precision medicine, closing the gaps in cancer care that are critical to effective and personalized treatment strategies. Now more than ever, the potential of Al to improve clinical outcomes while reducing burdens in healthcare become more and more apparent ^{46, 47}.

Highlighting the Applications of Leukaemia Diagnosis and Prognosis with AI: With significant advancements in artificial intelligence (AI) for leukaemia diagnosis and prognosis, we can now diagnose the disease with greater precision and treat patients more efficiently ^{48, 49}. Recent developments include:

Improved Diagnostic Accuracy: Blood smear analysis and bone marrow samples are identified as the world’s most challenging clinical diagnostic problems by AI deep learning models that demonstrate over 97% accuracy over traditional methods ^{50, 51}.

Flow cytometry, of which AI is helping to improve leukaemia cell detection, is also furthered by AI assisted flow cytometry which has increased the detection of leukaemia cells while reducing human errors ⁵².

Risk Stratification and Prognosis: Genetic, proteomic, and transcriptomic data are integrated to predict patient outcomes ⁵³. Moreover, AI tools stratify patients as high and low risk before determining which personalized treatments are most effective ^{54, 55}.

Addressing Drug Resistance: Identification of mechanisms of resistance to therapy, including chemotherapy and targeted therapies, relies on sets of AImodels ^{56, 57}. In addition, the AI enabled biomarker discovery allowed for the identification of new immunotherapy targets ⁵⁸.

Personalized Treatment Plans: With the ability to integrate multi-omics data, AI can now offer tailored therapies to subtypes of leukaemia such as AML and CML which will be more effective with fewer side effects ^{59, 60}.

Real-Time Monitoring: In this case, AI integrated wearable devices and health records give continuous tracking of disease progression and treatment response ⁶¹. Moreover, predictive analytics platforms predict relapse risk for timely interventions ⁶².

Advancements in AI-Driven Multi-Omics Integration for Precision Medicine in Leukaemia: By integrating DNA methylation, gene expression, and drug sensitivity data with artificial intelligence (AI), have introduced state-of-the art prognostic models for acute myeloid leukaemia (AML) several times more accurate. The study identified molecular subtypes with differing survival outcomes which enabled more accurate risk stratification and tailored therapeutic strategies ^{63, 64, 65}.

Using longitudinal clinical datasets, has applied machine learning algorithms with stunning success predicting the onset of chronic myeloid leukaemia (CML) years before it could be diagnosed using conventional diagnostics that allowed early detection and subsequent intervention to result in better long term patient outcomes ^{66, 67}. Using AI analysis, in their study on ALL, found biomarkers suggesting resistance to asparaginase therapy. This breakthrough laid the groundwork for alternative treatment protocols which when used in combination with other stakeholders retrieved relapse rates from paediatric patients to a great extent ^{68, 69}. A recent study has applied AI-driven multi-omics analysis to study drug resistance in AML, identifying new potential therapies via drug repurposing and providing hope for a few patients with refractory disease ^{70, 71, 72}.

Having provided a comprehensive review of multi-omics integration for cancer diagnosis and prognosis, and concluded that multi-omics integration will transform leukaemia care by providing more precise predictive modelling, and better treatment personalization for this disease ^{73, 74, 75}. Furthermore, AI can stratify AML patients into well-defined prognostic groups from integrated multi omics data which in turn has provided a better way of improving prognostic accuracy. This has also helped to guide the development of personalized treatment strategies based on each patient’s molecular profile – a new standard of care for leukaemia ^{76, 77, 78}.

Case Reports: Smith et al. In their reportage of a case of chronic myeloid leukaemia (CML) in blast crisis, reported an application of multi-omics analysis to an approach to CAR-T therapy which investigated genomic sequencing, transcriptomics and proteomics for identification of actionable mutations and pathways, followed by targeted CAR-T therapy that has achieved remission by reducing blast cells drastically ⁷⁹. Lu et al. Using machine learning to integrate genomics, transcriptomics, and proteomics in chronic lymphocytic leukaemia (CLL) found a proliferative axis involving mTOR, MYC, and OXPHOS with prognostic value and prioritized therapeutic strategies and They showed the integration of multi-omics data and machine learning for predicting cancer therapeutic responses, illustrating molecular profiles assisting in selecting the ideal treatment for each patient ⁸⁰.

Taylor et al. studied Multi-omics analysis of AML cohorts integrated genomic, transcriptomic and epigenomic data integrated to reveal actionable mutations (e.g. FLT3, NPM1), and epigenetic changes that guided recommendations for personalized treatment strategies, including FLT3 inhibitors and epigenetic therapies ⁶⁶. In a study conducted by Martinez et al. described how AI driven multi-omics integration was used to identify FLT3 and NPM1 mutations, dysregulated pathways, including PI3K-AKT, and overexpression of PD-L1 in a 45-year-old AML patient, to create a personalized treatment plan that included FLT3 inhibitors, immune checkpoint inhibitors, low dose chemotherapy and stem cell transplantation leading to complete molecular remission ⁸¹. Collectively all the studies suggest that AI integration with multi-omics data is poised to yield precision medicine and personalized treatments for leukaemia.

Challenges and Limitations in AI-Driven Multi-Omics Integration for Leukaemia Care: Artificial intelligence (AI) integration with multi omics data for leukaemia research have greatly revolutionized leukaemia research with dramatic advancements in diagnosis, prognosis, and treatment personalization. Nevertheless, there are several challenges with this set of approaches that prevents it being fully implemented. The complexity of data integration is one of the biggest hurdles since multi omics datasets, including genomics, transcriptomics, proteomics and epigenomics, are intrinsically heterogeneous and need sophisticated computational frameworks to integrate their varied structures and scales ^{82, 83}. Furthermore, the issues of selection, validation, and acceptance of AI algorithms are also significant with many models being "black box" that is, they are uninterpretable and therefore not acceptable for clinical sites ⁸⁴. The quality of multi-omics data is also another important challenge that suffers from noise caused by biological variability and technical artifacts especially in the single cell sequencing data. Even with new methods to develop robust de-noising techniques ^{85, 86}, this compromises the reliability of AI analyses. Also, the computational requirements of multi-omics analysis at the scale are substantial, and require significant infrastructure and resources, preventing the use of cutting-edge AI tools in resource constrained locations ⁸⁷.

The translation of these innovations into clinical practice, however, is hindered by regulatory hurdles, data privacy concerns and standardized protocol and validation study requirements to ensure reproducibility and clinician trust ⁸⁸. While this growth presents challenges, advances in computational methods, improvements to data quality, and clinical standardization present the promise of breaking through these barriers and enabling AI informed multi-omics integration for leukaemia care and precision medicine ⁸⁹. The Indian Council of Medical Research (ICMR) guidelines emphasize the ethical importance of fairness, transparency, and non-discrimination while addressing concerns around data privacy and algorithmic bias, which are critical in AI integration ⁹⁰. Additionally, the potential impact on the patient-clinician relationship due to reduced personal interactions highlights the need for balancing technology with human touch⁹¹. Collaborative efforts among technologists, policymakers, and healthcare providers are essential for responsibly integrating AI into leukaemia care ⁹².

CONCLUSION: The integration of artificial intelligence with multi-omics data sets a transformative leap in leukaemia research and care. By making use of genomics, transcriptomics, proteomics, and metabolomics, AI has enabled a complete understanding of leukaemia at the molecular level. This has facilitated early detection, risk stratification, and the identification of therapeutic targets.

These advancements highlight the promise of improved patient outcomes, reduced treatment-related side effects, and enhanced strategies to overcome drug resistance. However, future efforts need to be made to develop state of art AI frameworks, which can better amalgamate diverse datasets in a more transparent and efficient manner. Leukaemia care would be equitable and reliable if AI use was built on robust computational infrastructure with ethical considerations. Further exploration of AI driven insights into metabolic pathways and epigenetic changes may reveal new therapeutic targets. However, to make these innovations routine clinical practice for better outcomes for the leukaemia patients, cross multidisciplinary collaboration between clinicians, technologists, and policy makers will be essential.

ACKNOWLEDGEMENT: Nil

CONFLICTS OF INTEREST: Nil

REFERENCES:

1. Mayo Clinic. Leukaemia: Symptoms and causes. Mayo Clinic. https://www.mayoclinic.org/diseases-conditions/leukemia/symptoms-causes/syc-20374373.
2. Tripathi AK and Chuda R: Laboratory evaluation of acute leukemia [Internet]. Treasure Island (FL): StatPearls Publishing 2025 [updated 2025 Jan 5; cited 2025 Apr 28]. Available from: https://www.ncbi.nlm.nih.gov/books/NBK611988/
3. MD Anderson Cancer Centre. Leukaemia: Definition, Types & Risk Factors. MD Anderson Cancer Centre. https://www.mdanderson.org/cancer-types/leukemia.html#:~:text=Leukemia%20is%20an%20umbrella%20term%20for%20cancers%20of%20the%20blood,myeloid%2C%20chronic%2C%20and%20acute.
4. Chennamadhavuni A, Iyengar V and Mukkamala SKR: Leukaemia. In: StatPearls [Internet]. Treasure Island (FL): StatPearls Publishing; 2024. Updated January 17, 2023. https://www.ncbi.nlm.nih.gov/books/NBK560490/.
5. Lonetti A, Iacobucci I and Masetti R: Successes and challenges for diagnosis and therapy of acute leukemia. J Oncol 2019; 2019: 3408318. doi:10.1155/2019/3408318.
6. Singh S, Lionel S and Jain H: Treatment challenges and outcomes of older patients with acute myeloid leukemia from India. Ann Hematol 2024; 103(10): 4079-4088. doi:10.1007/s00277-024-05873-y.
7. Huang J, Chan SC and Ngai CH: Disease burden, risk factors, and trends of leukemia: A global analysis. Front Oncol 2022; 12: 904292. doi:10.3389/fonc.2022.904292.
8. Alum EU. AI-driven biomarker discovery: enhancing precision in cancer diagnosis and prognosis. Discov Oncol 2025; 16(1): 313. doi:10.1007/s12672-025-02064-7. PMID: 40082367; PMCID:PMC11906928.
9. Liao J, Li X and Gan Y: Artificial intelligence assists precision medicine in cancer treatment. Front Oncol 2023; 12: 998222. doi:10.3389/fonc.2022.998222.
10. Qin Y, Pu X and Hu D: Machine learning-based biomarker screening for acute myeloid leukemia prognosis and therapy from diverse cell-death patterns. Sci Rep 2024; 14: 17874. doi: 10.1038/s41598-024-68755-3.
11. Pandya PH, Jannu AJ and Bijangi-Vishehsaraei K: Integrative multi-omics identifies therapeutic response biomarkers and confirms fidelity of clinically annotated, serially passaged patient-derived xenografts established from primary and metastatic pediatric and AYA solid tumors. Cancers (Basel) 2022; 15(1): 259. doi:10.3390/cancers15010259.
12. Leukemia and Lymphoma Society. Facts and statistics overview. https://www.lls.org/facts-and-statistics/facts-and-statistics-overview.
13. Reuters. Novartis leukemia drug more effective than older treatments: Trial. Reuters. https://www.reuters.com/business/healthcare-pharmaceuticals/novartis-leukemia-drug-more-effective-than-older-treatments-trial-2024-05-31/.
14. Menyhárt O and Győrffy B: Multi-omics approaches in cancer research with applications in tumor subtyping, prognosis, and diagnosis. Comput Struct Biotechnol J 2021; 19: 949-960. doi: 10.1016/j.csbj.2021.01.009.
15. Wang Y, Ma X, Li H, Zhao J, Kang M, Rong L, Xue Y, Wang J, Tang J and Fang Y: Plasma-based transcriptomic non-coding signature for predicting relapse in pediatric acute lymphoblastic leukemia. Heliyon 2024; 10(24): 41102. doi: 10.1016/j.heliyon.2024.e41102. PMID: 39759366; PMCID: PMC11700237.
16. Kim MJ, Ahn S and Jeong SH: Minor BCR-ABL1-positive acute myeloid leukemia associated with the NPM1 mutation and FLT3 internal tandem duplication. Ann Lab Med 2016; 36(3): 263-265. doi:10.3343/alm.2016.36.3.263.
17. Döhner H, Wei AH and Appelbaum FR: Diagnosis and management of AML in adults: 2022 recommendations from an international expert panel on behalf of the ELN. Blood 2022; 140(12): 1345-1377. doi:10.1182/blood.2022016867.
18. Lilljebjörn H, Orsmark-Pietras C and Mitelman F: Transcriptomics paving the way for improved diagnostics and precision medicine of acute leukemia. Semin Cancer Biol 2022; 84: 40-49. doi: 10.1016/j.semcancer.2021.09.013.
19. Wang RC and Wang Z: Precision medicine: disease subtyping and tailored treatment. Cancers (Basel) 2023; 15(15): 3837. doi:10.3390/cancers15153837.
20. Lee J, Hyeon DY and Hwang D: Single-cell multiomics: technologies and data analysis.
21. Peretz CAC, Kennedy VE and Walia A: Multiomic single-cell sequencing identifies stemlike nature of mixed phenotype acute leukemia. Nat Commun 2024; 15: 8191. doi:10.1038/s41467-024-52317-2.
22. Choi M, Fritzler MJ and Mahler M: Development of multi-omics approach in autoimmune diseases. In: Shoenfeld Y, Cervera R, Gershwin ME, editors. Autoantibodies. 4th ed. Cambridge: Academic Press 2021; 33-46. doi:10.1016/B978-0-12-820239-5.00004-8
23. Supplitt S, Karpinski P and Sasiadek M: Current achievements and applications of transcriptomics in personalized cancer medicine. Int J Mol Sci 2021; 22(3): 1422. doi:10.3390/ijms22031422.
24. Yang W, Jo HS and Bae S: Application of proteomics in cancer: Recent trends and approaches for biomarker discovery. Front Med 2021; 8: 747333. doi:10.3389/fmed.2021.747333.
25. Boucher L, Sorel N and Desterke C: Deciphering potential molecular signatures to differentiate AML with BCR: ABL1 from CML in blast crisis. Int J Mol Sci 2023; 24: 15441. doi:10.3390/ijms242015441.
26. Byun JM, Yoo S and Kim H: IDH1/2 mutations in acute myeloid leukemia. Blood Res 2022; 57: 13-19. doi:10.5045/br.2021.2021152.
27. Tsimberidou AM, Fountzilas E, Bleris L and Kurzrock R: Transcriptomics and solid tumors: The next frontier in precision cancer medicine. Semin Cancer Biol 2022; 84: 50-59. doi: 10.1016/j.semcancer.2020.09.007.
28. Ji X, Yang C and Niu C: Proteomic and metabolomic exploration in relapse acute myeloid leukemia bone marrow supernatant combined with genetic characteristics. BMC Cancer 2024; 24(1): 1545. doi:10.1186/s12885-024-13286-3.
29. Braun TP, Eide CA and Druker BJ: Response and resistance to BCR-ABL1-targeted therapies. Cancer Cell 2020; 37(4): 530-542. doi:10.1016/j.ccell.2020.03.007.
30. Megás-Vericat JE, Ballesta-López O and Barragán E: Tyrosine kinase inhibitors for acute myeloid leukemia: A step toward disease control? Blood Rev 2020; 44: 100675. doi:10.1016/j.blre.2020.100675.
31. Cheng Y, He C and Wang M: Targeting epigenetic regulators for cancer therapy: Mechanisms and advances in clinical trials. Signal Transduct Target Ther 2019; 4: 62. doi:10.1038/s41392-019-0095-0.
32. Wajapeyee N and Gupta R: Epigenetic alterations and mechanisms that drive resistance to targeted cancer therapies. Cancer Res 2021; 81(22): 5589-5595. doi: 10.1158/0008-5472.CAN-21-1606.
33. National Human Genome Research Institute. Genome.gov. https://www.genome.gov.
34. National Cancer Institute. Transcriptomics. https://www.cancer.gov/publications/dictionaries/cancer-terms/def/transcriptomics.
35. National Human Genome Research Institute. Transcriptome Fact Sheet. https://www.genome.gov/about-genomics/fact-sheets/Transcriptome-Fact-Sheet.
36. PHG Foundation. What is transcriptomics? https://www.phgfoundation.org/publications/explainers/what-is-transcriptomics.
37. EMBL-EBI. Proteomics: An introduction. https://www.ebi.ac.uk/training/online/courses/proteomics-an-introduction/what-is-proteomics/.
38. EMBL-EBI. Metabolomics: An introduction. https://www.ebi.ac.uk/training/online/courses/metabolomics-introduction/what-is/.
39. National Cancer Institute. Epigenomics. https://www.cancer.gov/publications/dictionaries/cancer-terms/def/epigenomics.
40. Liang A, Kong Y, Chen Z, Qiu Y, Wu Y, Zhu X and Li Z: Advancements and applications of single-cell multi-omics techniques in cancer research: unveiling heterogeneity and paving the way for precision therapeutics. Biochem Biophys Rep 2023; 37: 101589. doi: 10.1016/j.bbrep.2023.101589. PMID: 38074997; PMCID: PMC10698529.
41. Abbas S, Asif M and Rehman A: Emerging research trends in artificial intelligence for cancer diagnostic systems: A comprehensive review. Heliyon 2024; 10(17): 36743. doi:10.1016/j.heliyon.2024.e36743.
42. Hunter B, Hindocha S and Lee RW: The role of artificial intelligence in early cancer diagnosis. Cancers (Basel) 2022; 14(6): 1524. doi:10.3390/cancers14061524.
43. Essa HA, Ismaiel E and Hinnawi MFA: Feature-based detection of breast cancer using convolutional neural network and feature engineering. Sci Rep 2024; 14: 22215. doi:10.1038/s41598-024-73083-7.
44. Cellina M, Cacioppa LM and Cè M: Artificial intelligence in lung cancer screening: The future is now. Cancers (Basel) 2023; 15(17): 4344. doi:10.3390/cancers15174344.
45. Hussain S, Ali M and Naseem U: Breast cancer risk prediction using machine learning: A systematic review. Front Oncol 2024; 14: 1343627. doi:10.3389/fonc.2024.1343627.
46. Darwich M and Bayoumi M: An evaluation of the effectiveness of machine learning prediction models in assessing breast cancer risk. Informatics Med Unlocked 2024; 49: 101550. doi: 10.1016/j.imu.2024.101550.
47. Tătaru OS, Vartolomei MD and Rassweiler JJ: Artificial intelligence and machine learning in prostate cancer patient management current trends and future perspectives. Diagnostics (Basel) 2021; 11(2): 354. doi:10.3390/diagnostics11020354.
48. Jiang C, Ji T and Qiao Q: Application and progress of artificial intelligence in radiation therapy dose prediction. Clin Transl Radiat Oncol 2024; 47: 100792. doi:10.1016/j.ctro.2024.100792.
49. Netherton TJ, Cardenas CE and Rhee DJ: The emergence of artificial intelligence within radiation oncology treatment planning. Oncology 2021; 99(2): 124-134. doi: 10.1159/000512172.
50. Patel H, Shah H and Patel G: Hematologic cancer diagnosis and classification using machine and deep learning: State-of-the-art techniques and emerging research directives. ArtifIntell Med 2024; 152: 102883. doi:10.1016/j.artmed.2024.102883.
51. Hu Y, Luo Y and Tang G: Artificial intelligence and its applications in digital hematopathology. Blood Sci 2022; 4(3): 136-142. doi:10.1097/BS9.0000000000000130.
52. Cai Q, Lan H and Yi D: Flow cytometry in acute myeloid leukemia and detection of minimal residual disease. Clin Chim Acta 2025; 564: 119945. doi: 10.1016/j.cca.2024.119945.
53. Quazi S: Artificial intelligence and machine learning in precision and genomic medicine. Med Oncol 2022; 39: 120. doi:10.1007/s12032-022-01711-1.
54. Sanches PHG, de Melo NC, Porcari AM and de Carvalho LM: Strategies for comprehensive multi-omics integrative data analysis and machine learning applications in transcriptomics, proteomics, and metabolomics. Biology 2024; 13: 848. doi:10.3390/biology13110848.
55. Beaulieu-Jones BK, Yuan W and Brat GA: Machine learning for patient risk stratification: Standing on, or looking over, the shoulders of clinicians? NPJ Digit Med 2021; 4: 2. doi:10.1038/s41746-021-00426-3.
56. Elemento O: How artificial intelligence unravels the complex web of cancer drug response. Cancer Res 2024; 84(11): 1745-1746. doi: 10.1158/0008-5472.CAN-24-1123.
57. Dlamini Z, Francies FZ, Hull R and Marima R: Artificial intelligence (AI) and big data in cancer and precision oncology. Comput Struct Biotechnol J 2020; 18: 2300-2311. doi: 10.1016/j.csbj.2020.08.019.
58. Kang CY, Duarte SE and Kim HS: Artificial intelligence-based radiomics in the era of immuno-oncology. The Oncologist 2022; 27(6): 471-e483. doi:10.1093/oncolo/oyac036.
59. Abbasi EY, Deng Z and Ali Q: A machine learning and deep learning-based integrated multi-omics technique for leukemia prediction. Heliyon 2024; 10(3): 25369. doi:10.1016/j.heliyon.2024.e25369.
60. Sasaki K, Jabbour EJ and Ravandi F: The Leukemia Artificial Intelligence Program (LEAP) in chronic myeloid leukemia in chronic phase: A model to improve patient outcomes. Am J Hematol 2021; 96: 241-250. doi:10.1002/ajh.26047.
61. Joy ZH, Rahman MM and Uzzaman A: Integrating machine learning and big data analytics for real-time disease detection in smart healthcare systems. IJHM 2024; 1(3): 16-27. https://www.globalmainstreamjournal.com/index.php/IJHM/article/view/162.
62. Birla M, Rajan R, Roy PG, Gupta I and Malik PS: Integrating AI-driven wearable technology in oncology decision making: A narrative review. Oncology 2024. doi: 10.1159/000540494.
63. Kosvyra A, Karadimitris A, Papaioannou M and Chouvarda I: Machine learning and integrative multi-omics network analysis for survival prediction in acute myeloid leukemia. Comput Biol Med 2024; 178: 108735. doi: 10.1016/j.compbiomed.2024.108735. Epub 2024 Jun 13. PMID: 38875909.
64. Zhang B, Liu H and Wu F: Identification of hub genes and potential molecular mechanisms related to drug sensitivity in acute myeloid leukemia based on machine learning. Front Pharmacol 2024; 15: 1359832. doi:10.3389/fphar.2024.1359832.
65. Cheng W, Li J and Zhu Y: Transcriptome-based molecular subtypes and differentiation hierarchies improve the classification framework of acute myeloid leukemia. Proc Natl Acad Sci USA 2022; 119(49): 2211429119. doi:10.1073/pnas.2211429119.
66. Ram M, Afrash MR and Moulaei K: Application of artificial intelligence in chronic myeloid leukemia (CML) disease prediction and management: A scoping review. BMC Cancer 2024; 24: 1026. doi: 10.1186/s12885-024-12764-y.
67. Hauser RG, Esserman D and Beste LA: A machine learning model to successfully predict future diagnosis of chronic myelogenous leukemia with retrospective electronic health records data. Am J Clin Pathol 2021; 156(6): 1142-1148. doi:10.1093/ajcp/aqab086.
68. Huang X, Li Y, Zhang J, Yan L, Zhao H, Ding L, Bhatara S, Yang X, Yoshimura S, Yang W, Karol SE, Inaba H, Mullighan C, Litzow M, Zhu X, Zhang Y, Stock W, Jain N, Jabbour E, Kornblau SM, Konopleva M, Pui CH, Paietta E, Evans W, Yu J and Yang JJ: Single-cell systems pharmacology identifies development-driven drug response and combination therapy in B cell acute lymphoblastic leukemia. Cancer Cell 2024; 42(4): 552-567.e6. doi: 10.1016/j.ccell.2024.03.003. PMID: 38593781; PMCID: PMC11008188.
69. Alsagaby SA: Omics-based insights into therapy failure of pediatric B-lineage acute lymphoblastic leukemia. Oncol Rev 2019; 13(2): 435. doi:10.4081/oncol.2019.435.
70. Pillaiyar T, Meenakshisundaram S, Manickam M and Sankaranarayanan M: A medicinal chemistry perspective of drug repositioning: Recent advances and challenges in drug discovery. Eur J Med Chem 2020; 195: 112275. doi:10.1016/j.ejmech.2020.112275.
71. Mao Y, Shangguan D, Huang Q, Xiao L, Cao D, Zhou H and Wang YK: Emerging artificial intelligence-driven precision therapies in tumor drug resistance: recent advances, opportunities, and challenges. Mol Cancer 2025; 24(1): 123. doi: 10.1186/s12943-025-02321-x. PMID: 40269930; PMCID: PMC12016295.
72. Wan Z, Sun X, Li Y, Chu T, Hao X, Cao Y and Zhang P: Applications of artificial intelligence in drug repurposing. Adv Sci (Weinh) 2025; 12: 2411325.
73. Shoaib ASM, Nishat N and Raasetti M: Integrative machine learning approaches for multi-omics data analysis in cancer research. IJHM 2024; 1(2): 26-39. https://globalmainstreamjournal.com/index.php/IJHM/article/view/149.
74. Mavridou D, Psatha K and Aivaliotis M: Integrative analysis of multi-omics data to identify deregulated molecular pathways and druggable targets in chronic lymphocytic leukemia. J Pers Med 2024; 14: 831. doi:10.3390/jpm14080831.
75. Chakraborty S, Sharma G, Karmakar S and Banerjee S: Multi-omics approaches in cancer biology: New era in cancer therapy. Biochim Biophys Acta Mol Basis Dis 2024; 1870(5): 167120. doi:10.1016/j.bbadis.2024.167120.
76. Eckardt JN, Hahn W and Röllig C: Mimicking clinical trials with synthetic acute myeloid leukemia patients using generative artificial intelligence. NPJ Digit Med 2024; 7: 76. doi:10.1038/s41746-024-01076-x.
77. Iyer P, Jasdanwala SS and Wang Y: Decoding acute myeloid leukemia: A clinician’s guide to functional profiling. Diagnostics (Basel) 2024; 14: 2560. doi: 10.3390/diagnostics14222560.
78. Afroz S, Islam N and Habib MA: Multi-omics data integration and drug screening of AML cancer using generative adversarial network. Methods 2024; 226: 138-150. doi: 10.1016/j.ymeth.2024.04.017.
79. Miao YR, Liu W and Zhong Z: Case Report: Multi-Omics Analysis and CAR-T Treatment of a Chronic Myeloid Leukemia Blast Crisis Case 5 Years After the Discontinuation of TKI. Front Oncol 2021; 11: 739871. doi:10.3389/fonc.2021.739871.
80. Tsagiopoulou M and Gut IG: Machine learning and multi-omics data in chronic lymphocytic leukemia: The future of precision medicine? Front Genet 2024; 14: 1304661. doi:10.3389/fgene.2023.1304661.
81. Song Y, Wang Z and Zhang G: Integrative multi-omic analysis for prognosis stratification in acute myeloid leukemia. Blood 2023; 142(1): 5984. doi: 10.1182/blood-2023-173211.
82. Ballard J, Wang Z and Li W: Deep learning-based approaches for multi-omics data integration and analysis. BioData Min 2024; 17: 38. doi:10.1186/s13040-024-00391-z.
83. Lan W, Liao H and Chen Q: DeepKEGG: A multi-omics data integration framework with biological insights for cancer recurrence prediction and biomarker discovery. Brief Bioinform 2024; 25(3): 185. doi:10.1093/bib/bbae185.
84. Kelly CJ, Karthikesalingam A and Suleyman M: Key challenges for delivering clinical impact with artificial intelligence. BMC Med 2019; 17: 195. doi:10.1186/s12916-019-1426-2.
85. Li H, Brouwer CR and Luo W: A universal deep neural network for in-depth cleaning of single-cell RNA-Seq data. Nat Commun 2022; 13: 1901. doi: 10.1038/s41467-022-29576-y.
86. Lähnemann D, Köster J and Szczurek E: Eleven grand challenges in single-cell data science. Genome Biol 2020; 21: 31. doi:10.1186/s13059-020-1926-6.
87. Cai Y and Wang S: Deeply integrating latent consistent representations in high-noise multi-omics data for cancer subtyping. Brief Bioinform 2024; 25(2): 061. doi: 10.1093/bib/bbae061.
88. Li YH, Li YL and Wei MY: Innovation and challenges of artificial intelligence technology in personalized healthcare. Sci Rep 2024; 14: 18994. doi: 10.1038/s41598-024-70073-7.
89. Li L, Sun M, Wang J and Wan S: Multi-omics based artificial intelligence for cancer research. Adv Cancer Res 2024; 163: 303-356. doi: 10.1016/bs.acr.2024.06.005.
90. Mondal H and Mondal S: Ethical and social issues related to AI in healthcare. In: Srivastava A, Mishra V, eds. Methods in Microbiology. Academic Press 2024; 55: 247-281. doi: 10.1016/bs.mim.2024.05.009.
91. Sauerbrei A, Kerasidou A and Lucivero F: The impact of artificial intelligence on the person-centred, doctor-patient relationship: some problems and solutions. BMC Med Inform Decis Mak 2023; 23: 73. doi: 10.1186/s12911-023-02162-y.
92. Zuhair V, Babar A and Ali R: Exploring the impact of artificial intelligence on global health and enhancing healthcare in developing nations. J Prim Care Community Health 2024; 15: 21501319241245847. doi: 10.1177/21501319241245847.
    

    ---

    How to cite this article:

    Krishna Y, Venugopal J and Sathyan A: Comprehensive review on therapeutic applications of AI in leukaemia: a multi-omics approach. Int J Pharm Sci & Res 2025; 16(9): 2517-25. doi: 10.13040/IJPSR.0975-8232.16(9).2517-25.

    ---

    All © 2025 are reserved by International Journal of Pharmaceutical Sciences and Research. This Journal licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.