Systematic review of machine learning applications in the early prediction and management of chronic lymphocytic leukaemia

Abstract

Objective: This review assesses the efficacy of machine learning (ML) models for classification and management of Chronic Lymphocytic Leukaemia (CLL).

Methods: Twenty studies published between 2014 and 2023 were reviewed, focusing on supervised ML models to predict patient outcomes or guide treatment decisions. Studies were identified through PubMed, Google Scholar, and IEEExplore, with the final search in March 2023. Inclusion criteria consisted of studies focused on ML applications in CLL. Exclusion criteria included studies lacking sufficient methodology or focused solely on experimental settings without clinical validation. Most studies used small, single-centre datasets, potentially contributing to overfitting and limited applicability to real-world settings.

Results: Despite dataset limitations, all reviewed studies reported positive outcomes, with some demonstrating improvements in clinical workflows. Our findings advocate developing ML models using larger, multimodal, and multi-institutional datasets. Improved model interpretability and NLP implementation to harness unstructured clinical data were identified as key areas for advancement. Additionally, innovations like cross-site federated learning and automated redaction could help address data integration and privacy challenges.

Conclusion: This review underscores the transformative potential of ML in CLL management. However, addressing limitations, including diverse datasets and enhanced model interpretability, is crucial for fully leveraging ML capabilities in haemato-oncology.

Keywords

chronic lymphocytic leukaemia explainable AI machine learning model interpretability natural language processing

Introduction

Chronic Lymphocytic Leukaemia (CLL) represents a significant haematological malignancy, accounting for 25–30% of adult leukaemia cases and predominantly affecting elderly populations with a median age of 70.¹ This indolent disorder is characterised by the clonal proliferation of mature B-lymphocytes, manifesting through varied clinical presentations ranging from asymptomatic disease to systemic symptoms. Diagnosis employs a multimodal approach incorporating peripheral blood smear examination, flow cytometry immunophenotyping to identify prognostic markers that guides treatment.² The management landscape has evolved substantially, transitioning from traditional chemotherapy to targeted approaches including Bruton tyrosine kinase inhibitors (ibrutinib, acalabrutinib) and B-cell lymphoma-2 inhibitors (venetoclax), alongside established chemoimmunotherapy regimens for specific patient subgroups.^3,4 Treatment strategies are individualised based on age, comorbidities, genetic profile, and disease stage, with asymptomatic patients often managed through watchful waiting. The disease course is complicated by significant immune dysfunction, leading to increased susceptibility to infections and various autoimmune manifestations including haemolytic anaemia and immune thrombocytopenia.^5–8 Additional complications also include secondary malignancies and Richter’s Syndrome, a particularly aggressive transformation occurring in 2–10% of cases. This complex interplay of disease manifestations, treatment options, and complications, combined with its long natural history, presents an ideal scenario for ML applications to enhance classification, prognostication and treatment selection.

Given the challenges in CLL management, such as inefficiencies in flow cytometry gating, inconsistent genomic profiling, and difficulties in tailoring therapy for heterogeneous patient populations, ML models offer significant potential to address these gaps and enhance patient care across the complex CLL spectrum. In diagnosis, ML models could expedite identification of high-risk patients and optimise specialist referrals in resource-constrained settings. ML-based risk stratification may enable earlier treatment initiation for those at risk of rapid deterioration, while predictive models for life-threatening complications, particularly infections, could facilitate pre-emptive interventions to reduce mortality. In treatment selection, ML algorithms could personalise therapeutic choices by predicting individual responses and detecting early signs of resistance or transformation to Richter’s Syndrome. ML models could also be integrated into electronic patient records (EPRs) to provide real-time decision support and streamline data analysis for improved clinical workflows. However, challenges remain, including small, single-centre datasets limiting generalisability, a lack of prospective validation, and technical barriers in data integration.⁹ Additionally, successful implementation will require addressing varying data standards across institutions, information governance and privacy concerns, and the need for clinician training to interpret and trust ML outputs. Despite these hurdles, ML holds promise for improving risk stratification and treatment optimisation, but success will depend on robust databases, standardised protocols, and careful clinical implementation, maintaining its complementary role with physician expertise.^10–12 Given the complexity and heterogeneity of leukaemia and the rapid progress of ML techniques, it would be challenging to cover all leukaemia subtypes in a single literature review due to the significant amount of published literature and advances, as demonstrated in Figure 1.

Figure 1.

Number of studies exploring ML applications in haemato-oncology published on PubMed from 2001 to 2023.

This review will focus specifically on CLL, as it is a particularly interesting subtype of leukaemia due to its highly variable clinical course and long natural history, often spanning years or even decades. This provides a unique opportunity to collect large longitudinal datasets that capture the complex dynamics of CLL, consisting of remissions, relapses, complications, and treatment strategies, such as watch-and-wait, chemotherapy, targeted therapies, and stem cell transplantation. The management of CLL is complex and requires a personalised approach based on patient characteristics, disease stage, molecular and genetic markers. ML techniques could play a crucial role in various aspects of CLL management, namely:

• Improving accuracy and efficiency of CLL diagnosis and classification

• Identifying novel prognostic markers and developing risk stratification models

• Predicting treatment response and guiding the selection of optimal therapies

• Predicting the likelihood of developing complications, such as infections or other malignancies and monitoring disease progression to detect early signs of relapse

• Optimising supportive care and managing treatment-related complications

The primary objectives of this literature review are to provide an overview of the current state of ML applications in CLL, identify the key methodological approaches, data types used, and performance metrics used in existing studies, discuss the limitations and challenges of current research, and highlight potential areas for future research, development, and implementation.

Methodology

For a study to be included in this review, the study must have been published between 2013 and 2023, be a full-access paper, and use data from at least 100 patients or samples to train and test classification, treatment recommendation or predictive models for CLL or its subtypes. The samples must be real-world human data, and not machine-generated synthetic data. The datasets used for training and testing must be cited or at least the data type(s) must be described. The diagnostic modalities that the study can include lab-based methods such as immunophenotyping, genomics, cellular morphology, and histology, as well as other sources such as demographics, blood tests, drug orders, or clinical notes. Predictions generated by models can include disease trajectory/prognosis, risk of developing complications or providing treatment recommendations. The primary search method was through Google Scholar and PubMed with combinations of search strings, booleans, and wildcards, such as:

(“CLL” OR “chronic lymphoid leuk?emia” OR “chronic lymphocytic leuk?emia”) AND (“machine learning” OR “artificial intelligence” OR “ML” OR “AI” OR “deep learning” OR “neural network*” OR “support vector machine*” OR “SVM” OR “random forest*” OR “predictive model*” OR “NLP” OR “natural language processing”)

The results were supplemented with studies from the AIForHealth dashboard, which used a BERT model to identify studies on PubMED that utilised ML models, and categorised each study by subject matter, input data type, and algorithm type.¹³ A Python script was used to automatically extract the latest cohort of studies and apply filters to rapidly identify CLL-specific studies (refer to Appendix 1). Despite the consistently increasing amount of literature in this field, a significant number of publications were excluded because they were editorials, letters, technical papers, and literature reviews (see Figure 2). A subgroup consisted of potentially qualifying publications studied other haematological diseases (classified as false positive studies), while many promising studies did not satisfy the search criteria because they had a small number of samples and/or patients.

Figure 2.

Consort diagram illustrating the literature review search process.

Results

The literature search, conducted on December 2023, identified a total of 20 studies meeting the inclusion criteria, spanning from 2014 to 2023^14–33 (see Table 1). Over half these studies were published within the last 3 years, reflecting a growing interest and rapid advancements in the field. The analysis revealed a predominance of flow cytometry (FC)-specific models, which was closely followed by an equal distribution between genomics and morphology-based models. In contrast, models utilising laboratory data, free-text or multiple data types were comparatively rare, constituting only six studies. Additionally, a single study stood out for its exclusive use of NLP to analyse free-text electronic patient record (EPR) data. Many studies focused on developing and implementing diagnostic models, showcasing the critical need for accurate identification and classification of CLL, while a smaller number of studies ventured into predictive modelling and only one study was dedicated to modelling treatment recommendations, highlighting a potential area for future research emphasis (see Figure 3(a)–3(d)). All the studies had an average of 1888 samples for training and testing models per study, but over two-thirds of these studies used fewer than 1000 samples.

Table 1.

Details of the qualifying studies published between 2014–23 that implemented ML models for CLL classification or prediction. Studies are grouped by the datatype(s) used.

Datatype(s) used	Reference	Year of publication	Number of patients/samples used	Reported metrics	Feature selection/classification or predictive models	Explainable AI	Use of NLP models
FC	¹⁴	2020	20,622	Avg F1: 0.78; weighted F1: 0.94 (incl. Test set of 2348 cases); 70% classified with ≥0.95 confidence; F1 (B-NHL vs. healthy): 0.98	Deep learning approach using SOMs and CNNs	Saliency maps and density plots	—
FC	¹⁵	2020	3417	Overall acc.: 96.02%; NPV: 95.87%; PPV: 96.69%; spec.: 99.26%; sens.: 83.57%	UMAP (uniform manifold approximation and projection) for feature extraction and dimensionality reduction	—	—
FC	¹⁶	2022	236	For F-DNN/L-DNN: Acc.: 99.91%/100%, sens.: 99.26%/80.83%, spec.: 99.94%/100%, PPV: 98.98%/88.07%, NPV: 99.96%/100%, F1: 99.12%/84.30%	Deep neural networks (DNN)	—	—
FC	¹⁷	2023	157	AUC of 0.95, compared to 0.78 for CLL-IPI	Algorithmic population descriptions (ALPODS) XAI algorithm	ALPODS XAI	—
FC	¹⁸	2023	113	Pearson correlation (MRD: Manual vs. DeepFlow): 0.98; bland-altman bias: 0.2237 log10; 95% LOA: ±1.0282 log¹⁰	AI-assisted MFC workflow	—	—
FC	¹⁹	2023	456	Pearson’s r: >0.99; prec.: 100%; rec.: 97.5%; F1: 98.7%	Computational pipeline using FlowSOM, unsupervised clustering algorithms	—	—
Free-text	²⁰	2023	534	Prec.: 0.956; rec.: 0.987; F1: 0.97154	Proprietary EHRead® technology based on NLP and machine learning	—	EHRead® technology
Genomics	²¹	2014	308	Acc.: 99.2% (training), 98.5% (validation); C-stat: 0.81 / 0.77 (epigenetic), 0.68/0.67 (IGHV); good concordance between predicted and observed outcomes	Support vector model	—	—
Genomics	²²	2019	275	5-years treatment: Prec.: 90%, rec.: 69.23%	GMM-EM algorithm	—	—
				No treatment: Prec.: 88.57%, rec.: 96.88%
				Time to treatment: Avg prec.: 89.29%, Acc.: 88.89%, AUC: 0.911
Genomics	²³	2022	2606	First-choice CLL diagnosis: 72%; AUC: 0.997; sens.: 96.4%; spec.: 98.8%	Machine learning and geometric mean naïve bayesian (GMNB) classifier	—	—
Genomics	²⁴	2023	217	Acc.: 86.4%; sens.: 85.0%; spec.: 87.5%	NN, DeepSHAP autoencoder filter for genes selection (DSAF-GS), autoencoder	DeepSHAP	—
Lab tests	²⁵	2022	1577	Incorrect predictions: 10.6%; AUC for CLL: 0.905	RBFN-based model	—	—
Lab tests	²⁶	2023	682	Acc.: 98.55%; AUC: 100%; rec.: 100%; F1: 97.14%	XGB	—	—
Mixed	²⁷	2019	737	C-statistics: 0.932 (RSF), 0.917 (GBM)	>1 models including cox proportional hazards, RSF, LR and others	—	—
Mixed	²⁸	2020	4149	Prec.: 72%; rec.: 75%; MCC: 0.56; PR-AUC: 0.78	Ensemble/Genetic algorithm consisting of many base learners such as RF, perceptrons, XGB, LR, KNN and others	SHAP	Bag-of-words
Mixed	²⁹	2022	109	Auroc: 0.88; AUPRC: 0.78; accuracy: 0.8669; sens.: 0.915; spec.: 0.7857; prec.: 0.857	Gradient boosting model (GBM)	SHAP and decision tree	—
Morphology	³⁰	2020	374	CLL-specific performance: Prec.: 99.71%; rec.: 98.42%; F1: 99.06%; avg. Fivefold cross-validation accuracy: 100%	Transfer learning, PCA	—	—
Morphology	³¹	2021	754	Acc. At patch level: 91.2%; Acc. At case level: 95.56%; CLL accuracy at patch level: 63.07%; CLL accuracy at case level: 62.07%	EfficientNet convolutional neuronal network algorithm	—	—
Morphology	³²	2022	135	Accuracy: Unsupervised clustering model achieved 0.925, with mean accuracies of 0.835 (mixed), 0.662 (supervised), 0.876 (fusion), and 0.891 (selection)	Unsupervised clustering, cellular feature engineering	—	—
				AUC: Unsupervised model achieved 0.978, with mean AUCs of 0.961 (mixed), 0.841 (supervised), 0.969 (fusion), and 0.973 (selection)
				Mean values: Unsupervised (0.902, 0.973), mixed (0.835, 0.961), supervised (0.662, 0.841), fusion (0.876, 0.969), selection (0.891, 0.973)
Morphology	³³	2023	284	Prec.: 0.98; rec.: 0.96; F1: 0.97	D-CNN and VGG-16	—	—

Figure 3.

Visualisations illustrating characteristics of the qualifying studies. (a) Histogram of the qualifying studies by publication date. (b) Pie chart showing the breakdown of qualifying studies by data source. (c) Bar chart illustrating the qualifying studies by sample size used for ML model testing and training. (d) Bar chart illustrating the qualifying studies by the intended aim of the ML model output.

Discussion

Over the past decade, there has been a clear trend towards increasing complexity and diversity in the application of ML techniques in CLL. Early studies focused on using classical ML methods on single data types like many other models in other leukaemias, while more recent studies have explored the integration of multiple data types, the use of deep learning and unsupervised methods, and the application of techniques like transfer learning (TL) and convolutional neural networks (CNNs) for morphological analysis. The latest studies continue to refine these approaches, introducing novel XAI techniques and expanding ML applications, yet underscore a persisting gap in the use of NLP and large-scale, real-world datasets.

Flow cytometry models

Zhao et al.’s deep learning approach, utilising Self-Organising Maps (SOMs) and CNNs, demonstrated great potential for automation in FC analysis.¹⁴ Their impressive F1 score and visual explainability tools surpassed traditional manual gating strategies. Ng et al. further solidified the path towards automation with their groundbreaking application of Uniform Manifold Approximation and Projection (UMAP) for unsupervised feature extraction.¹⁵ This method showcased not only high accuracy but also the potential for cost-effectiveness in clinical diagnostics. Salama et al. integrated deep neural network (DNN) models into clinical practice a step further, achieving promising accuracy and specificity.¹⁶ However, their work also highlighted the ongoing challenge of detecting low-level minimal residual disease (MRD). Hoffman et al. introduced a novel approach with their Algorithmic population descriptions (ALPODS) algorithm, identifying cell populations predictive of outcomes and underlining the effectiveness of ML models in prognostic assessments.¹⁷ Bazinet et al. built upon this by comparing their model within DeepFlow software against expert analysis, demonstrating strong correlation and accuracy.¹⁸ Finally, Nguyen et al.’s work with Flow Self-Organising Map (FlowSOM) validated the capacity of ML models for rapid, accurate analysis and rare event detection, while emphasising the need for larger cohort validation for broader adoption.¹⁹

While detecting low-level MRD is not currently an established aspect of CLL management, there is clear evidence of future utility to optimise patient management.³⁴ FC in CLL is a cornerstone in the initial CLL diagnostic workup, as well as MRD detection. Despite this, a recurring theme across the studies that developed and tested FC-specific models is the challenge of dataset limitations, either in size, diversity, or source. For instance, Zhao et al.’s model faced potential limitations due to FC data quality, and similar concerns were echoed in Bazinet et al.’s study, which relied on a small, single-centre dataset, which raises questions about the generalisability and robustness of these models across different patient populations and clinical settings.^14,18 Ng et al. and Salama et al. both highlighted the cost-effectiveness and practical integration of AI models in clinical settings, yet they also acknowledged the need for further research to fully understand the feasibility and economic impact of these technologies.^15,16 Additionally, Salama et al.’s model demonstrated a gap in detecting low-level MRD, which is a critical aspect in CLL management. Hoffman et al.’s study was limited by its retrospective design and relatively small sample size, restricting the extrapolation of its findings.¹⁷ Moreover, a common shortfall across these studies is the lack of detailed analysis on the impact of demographic and clinical factors on model performance, as well as a general absence of detailed descriptions of the models’ architectures, which hinders model reproducibility, development, and prospective validation.

NLP models

Loscertales et al. demonstrated the potential of NLP for real-world data extraction from unstructured EHR data by employing the proprietary EHRead model to generate clinical, treatment, and survival profiles of CLL patients in Spain.²⁰ While EHRead exhibited promising recall, precision, and F1 scores for CLL concept detection, certain limitations warrant consideration. The study’s reliance on a single-centre dataset up to 2018 raises concerns about the model’s generalisability and its applicability to more recent data. Moreover, the lack of transparency regarding EHRead’s architecture, training dataset, and performance across diverse sites hinders a robust assessment of its wider utility. Additionally, by incorporating only gender and date of birth alongside unstructured data, the study may have overlooked other influential factors such as ethnicity and mortality, potentially resulting in an incomplete patient profile. The exclusion of potential confounders like socioeconomic status and geographic location could further obscure variations in clinical characteristics and CLL management practices.

Genomics models

The use of a Support Vector Machine (SVM) model based on epigenetic biomarkers by Queirós et al. to identify CLL subgroups marked a significant advance in understanding the heterogeneity of CLLs and its implications for treatment and prognosis.²¹ This paved the way for integrating epigenetic factors into CLL classification. Orgueira et al. further showcased the potential of transcriptomic patterns in predicting treatment timelines by applying the Gaussian Mixture Model-Expectation Maximisation (GMM-EM) algorithm for patient stratification based on gene expression, moving beyond traditional prognostic markers.²² Their deep survival model achieved high precision and accuracy despite its small sample size, indicating the growing role of deep learning in CLL prognostics. Zhang et al.’s study using the Geometric Mean Naïve Bayesian Classifier (GMNB) algorithm for differential diagnosis marked a significant advancement in precision medicine by employing a targeted transcriptome approach to distinguish between various hematologic and solid tumours, including CLL.²³ Morabito et al. further expanded the scope by introducing the DeepSHAP Autoencoder Filter for Genes Selection (DSAF-GS), which combines deep learning with XAI to not only predict treatment outcomes but also to uncover new biological pathways and networks involved in CLL.²⁴

Several limitations were demonstrated in these studies, beginning with Queirós et al., a notable shortfall was the lack of external validation and reliance on a single DNA methylation analysis platform, raising questions about the model’s generalisability and robustness.²¹ This issue of external validation was also evident in Morabito et al.'s study, where the model’s applicability beyond the initial Italian cohort remains untested. Furthermore, both studies, along with Orgueira et al.’s work, did not provide insights into the functional significance of the identified biomarkers or gene patterns, which potentially limits the understanding of their biological relevance in CLL.²² Orgueira et al. and Morabito et al. also faced challenges due to small sample sizes and absence of comparative analysis with existing methods, in which the latter would provide a more nuanced understanding of their models’ efficacy.^22,24 Zhang et al.’s study, while ambitious in scope, omitted comparisons between its algorithm and key diagnostic standards for CLL, specifically blood count, film examination, and FC, which are fundamental for initial diagnosis and confirmation.²³ The critique of not including immunohistochemistry is retracted, acknowledging its limited relevance to CLL diagnostics. This omission leaves a gap in understanding the relative strengths and weaknesses of their AI approach. Similarly to the FC models, there was a general lack of transparency regarding the models’ architectures.

Laboratory models

Haider et al.’s development of a predictive model using morphological and immature fraction-related parameters from full blood count (FBC) results is a notable advancement.²⁵ The Radial Basis Function Network (RBFN)-based model was demonstrated to be effective in early differentiation among various types of leukaemia. However, the study’s lack of external validation, particularly with datasets from multiple centres, limits the generalisability of its findings. Similarly, Padmanabhan et al.’s application of Extreme Gradient Boosting (XGB) for CLL diagnosis and screening based on routine FBC results, represented a significant advancement.²⁶ However, there was a reliance on a small dataset from a single centre and both contextual clinical data and unstructured data were not integrated.

Multimodal models

Chen D et al. broke new ground with their use of unsupervised clustering alongside demographics and laboratory test results to predict time to first treatment for CLL patients.²⁷ This work not only improved prognostic prediction but also demonstrated the performance of RSF and GBM in patient risk stratification. Building on this, Agius et al. developed a multimodal ensemble model utilising a genetic algorithm (GA) to build an ensemble model and data from the Danish CLL registry.²⁸ Their model proved effective in combining diverse data types, offering resilience to incomplete data, and improving interpretability through SHAP analysis. Finally, Meiseles et al.’s gradient boosting machine (GBM) model effectively predicted treatment necessity while incorporating feature importance analysis.²⁹

A notable shortcoming in Chen et al.’s study lies in its lack of exploration into the specific features learned by the models, obscuring potential details regarding the underlying biological mechanisms.²⁷ Both Chen et al. and Meiseles et al. relied on single-centre datasets, which raises concerns about the generalisability of their findings.^27,29 Agius et al.’s bag-of-words approach for extracting features from clinical data may not fully utilise the richness of such data; implementing more advanced NLP techniques on clinical free-text could potentially add depth to the analysis.²⁸ While their model proved robust with missing data, further validation, and exploration of its generalisability across diverse populations are crucial for wider applicability.

Morphology models

Zhang et al.’s application of TL and Principal Component Analysis (PCA) achieved a perfect cross-validation accuracy for CLL, setting a new standard in classification accuracy and demonstrating the potential of automated subtype differentiation.³⁰ Steinbuss et al.’s use of Efficient Neural Networks (EfficientNet) achieved high accuracy in classifying lymph node subtypes based on cellular morphology, suggesting the potential to improve accuracy in the diagnosis and treatment of lymph node cancers.³¹ Chen et al.’s unsupervised clustering-based model successfully identified distinct morphological cellular phenotypes associated with CLL progression stages, offering insights into CLL progression and potential new treatment targets.³² Finally, Wang et al.’s deep CNN algorithm demonstrated high accuracy in lymphocyte identification, showcasing its potential to develop new diagnostic tests for CLL and other blood cancers.³³

Despite the advances, certain limitations should be noted. The practical applicability of the TL/PCA-based model in Zhang et al.’s study is questionable due to the narrow dataset, lack of interpretability and clinical validation.³⁰ This indicates potential issues with generalising the model to other datasets and limits its immediate use in clinical practice. Steinbuss et al.s use of EfficientNet faced challenges due to a relatively small sample size considering the diversity of subtypes analysed, and the potential skill bias introduced by single annotator involvement.³¹ These limitations suggest the model may not be accurate for all subtypes of lymph node cancer and could be influenced by the annotator’s specific skills. Chen et al.’s unsupervised clustering-based model was constrained by a small, single-centre cohort and the absence of detailed model architecture, potentially limiting its generalisability, and hindering understanding of how the model functions.³² Lastly, Wang et al.’s deep CNN algorithm was limited by its retrospective nature and its inability to distinguish between disease progression and infection.³³ This highlights that the model cannot predict future disease development and might misinterpret CLL symptoms as those of other infections.

These findings underscore the potential for morphology models to automate histopathological analysis and refine CLL classification as a result. However, for effective clinical integration, these models require further validation, clarity, and adjustments to address dataset diversity and interpretability challenges.

XAI and NLP applications

Only a quarter of the reviewed studies explored XAI, highlighting an area for expanded focus. Agius et al., Meiseles et al., and Morabito et al. applied SHAP to enhance interpretability.^24,28,29 Zhao et al. used saliency maps and density plots to pinpoint important features, potentially aiding human experts.¹⁴ However, such visualisations might oversimplify model decision-making and can be computationally demanding in high-dimensional settings. Further development is needed to optimise their robustness, accuracy, and practicality. Hoffman et al.’s ALPODS offers sample-based explanations of CLL-specific immune cell populations relevant to outcomes.¹⁷ While valuable, the study lacks clarity on how these explanations were produced and their ease of use by healthcare professionals. Future studies that utilise ALPODS should prioritise transparency to build trust and assess its impact on clinical workflows. Morabito et al. employed DeepSHAP with a neural network (NN) to pinpoint genes predictive of treatment outcomes.²⁴ Yet, the benefits of validating their findings with external datasets, compare its performance against other XAI methodologies, and enhancing the computational efficiency of SHAP would help to ascertain the utility of this XAI approach. Agius et al. and Meiseles et al. both used SHAP to rank feature importance and reveal risk factors, although potential variability of SHAP values calls for a more consistent metric within these approaches.^28,29 Larger and more diverse datasets could further boost robustness. Notably, only Loscertales et al. focused exclusively on free-text data, likely due to the scarcity of accessible real-world clinical datasets and inherent complexities in integrating textual and non-textual data.²⁰ Developing strategies to address these challenges would greatly expand the utility of free-text in future research.

The case for multimodal ML models

While Table 1 illustrates the performance of various ML models using reported metrics, it is crucial to consider their practical applicability in diverse clinical environments encountered in CLL management. Monomodal models often trained on homogenous datasets may not adequately reflect the complexities of real-world data, which are characterised by variability and incomplete data. In contrast, multimodal models that integrate heterogeneous data types are typically more robust, as exemplified by CLL-TIM’s performance. These models leverage multiple data sources to effectively compensate for missing features in any single data type. Such models are more suited to address challenges such as interoperability and data standardisation prevalent in healthcare settings. Therefore, while the metrics in controlled settings are informative, the real value of ML models lies in their ability to operate effectively within the intricate ecosystem of EPRs, thereby offering a more comprehensive approach to patient management in CLL. This integration is pivotal in harnessing the full potential of ML to enhance disease characterisation, diagnostic precision, and the personalisation of therapeutic strategies. However, interoperability with existing EHR systems remains a major challenge, as data formats and standards vary widely across healthcare providers, making the integration of ML tools cumbersome. Additionally, the legal and regulatory landscape, including compliance with TRIPOD guidelines and distinguishing the definition of the ML application as either research and development or a medical device, adds layers of complexity.³⁵

To address these challenges, future research should also focus on the development of ML models that can operate effectively under these constraints. This involves designing models that are adaptable to different data standards and can provide reliable outputs even with incomplete data. Furthermore, ensuring that these models adhere to stringent regulatory standards will be crucial for their acceptance and integration into clinical practice. These steps are necessary to move from the experimental application of ML in CLL management to their routine use in patient care, providing a more holistic approach to disease management that leverages the full potential of ML technologies

Limitations of the review

Several limitations of this review warrant consideration. The substantial heterogeneity across the reviewed studies encompassed diverse ML architectures, varied dataset characteristics and inconsistent outcome measures across diverse modalities including flow cytometry, genomics and morphological data. This variability precluded meaningful quantitative synthesis and meta-analysis. The heterogeneity coupled with insufficient dataset descriptions in some studies, such as fundamental details like indicating the number of samples per patient (e.g., whether there was one or more than one sample per patient) complicated the assessment of data quality and limited the generalisability of findings across different clinical settings. Furthermore, the reliance on a single reviewer for study selection and data extraction introduces potential selection bias, although this was partially mitigated through structured inclusion criteria.

Ethical considerations

As ML models become increasingly integrated into the CLL clinical care pathways, it is crucial to address ethical concerns with inclusive development approaches such as improved transparency, patient and public involvement (PPI) events and strong adherence to information governance (IG) legislation. Holding regular PPI events would serve as a forum for patients to share their thoughts regarding the models’ intended use, potential benefits, and risks, which would also help inform the direction of research and development. Transparency in the provision of clear and accessible documentation about the models’ data sources, architecture, performance metrics and XAI implementation is critical for building trust with healthcare professionals as end-users and patients.^36–38 In addition to these considerations, data privacy and security remain paramount, with robust IG frameworks, anonymisation techniques and sharing protocols must be enforced to protect patient confidentiality. All these principles align with National Institute for Health and Care Excellence (NICE)’s commitment to involving patients and the public in healthcare decision-making, ensuring that ML models serve the best interests of all users.³⁹ An additional critical ethical consideration in the future, when models become more sophisticated and autonomous, is accountability and liability in the event of clinical errors. To alleviate this, clear guidelines and policies must be established to determine roles and responsibilities of healthcare providers, researchers, and model developers. Ongoing education and training for healthcare professionals on the appropriate use and interpretation of model outputs are also necessary to ensure the safe model integration into clinical practice.

Conclusion

This review has highlighted the advances in ML applications in CLL management, particularly in diagnosis and classification. Several studies demonstrated that ML models can accurately diagnose CLL, especially using FC and morphological data. However, this progress also underscores critical gaps and limitations in the current research landscape, which align with broader trends in ML applications in haematology and oncology.^40,41

Current ML research in CLL management has largely produced narrow, single-purpose models using limited datasets or cohorts and often utilise single-modal data. While effective within their limited scope, these models do not address the complex, multifaceted nature of CLL management. Even the more advanced multimodal approaches fall short of a truly comprehensive solution, notably lacking integration of NLP to leverage the vast number of insights contained in unstructured clinical data. This fragmented approach has resulted in a collection of specialised tools rather than a cohesive system capable of supporting the full spectrum of CLL management.

Future research should prioritise the development and validation of NLP models capable of extracting clinically relevant information from unstructured data sources in CLL. These models could significantly enhance ML-assisted CLL management by incorporating previously underutilised data from clinical notes, pathology reports, and patient-reported outcomes. The output of such models would serve dual purposes: providing actionable information for clinical decision-making or research and generating additional input features for more complex predictive models. This could pave the way for novel methods to integrate diverse data types as additional inputs while addressing challenges of data harmonisation, quality, and IG. To facilitate multi-centre collaborations while maintaining patient confidentiality, future studies should explore advanced federated learning approaches and innovative data anonymisation techniques. Access to large longitudinal, real-world datasets would enable the development of ML models capable of capturing the temporal aspects of CLL progression and treatment response. XAI techniques are instrumental for effective prospective evaluation of the impact of these models on patient outcomes, clinical decision-making, and healthcare resource utilisation.

Equally important is the development of robust frameworks for continuous monitoring and mitigation of potential biases in ML models for CLL. This includes ensuring equitable performance across diverse patient populations and addressing potential disparities in model outcomes.

By pursuing these directions, the role of ML models is likely to change from isolated tools and become part of a more comprehensive, ML-assisted CLL management system. Such a system would not only improve diagnostics, but also enhance treatment planning, predict outcomes, and ultimately improve patient care across the entire CLL journey. This holistic approach to ML in CLL aligns with the broader roadmap for AI in haematology and oncology.⁴¹ Realising this potential will require collaborative efforts between clinicians, data scientists, and healthcare systems.

Supplemental Material

Supplemental Material - Systematic review of machine learning applications in early prediction and management of chronic lymphocytic leukaemia

Supplemental Material for Systematic review of machine learning applications in early prediction and management of chronic lymphocytic leukaemia by Mohammad Al-Agil, Piers Patten EM and Anwar Alhaq in Health Informatics Journal

Footnotes

ORCID iD

Mohammad Al-Agil

Author contributions

MA: Conceptualisation, Methodology, Investigation, Writing – Original Draft Preparation and Writing – Review & Editing. PEMP and AA: Conceptualisation, Supervision and Writing – Review & Editing.

Funding

The author(s) disclosed receipt of the following financial support for the research, authorship, and/or publication of this article: PEMP was supported by MRC grant MR/T005106/1. The other authors received no financial support for the research, authorship, and/or publication of this article.

Declaration of conflicting interests

The author(s) declared no potential conflicts of interest with respect to the research, authorship, and/or publication of this article.

Supplemental Material

Supplemental material for this article is available online.

Appendix

References

Kay

Hampel

Van Dyke

, et al. CLL update 2022: a continuing evolution in care. Blood Rev 2022; 54: 100930. https://www.sciencedirect.com/science/article/pii/S0268960X22000042

Matutes

Polliack

. Morphological and immunophenotypic features of chronic lymphocytic leukemia. Rev Clin Exp Hematol 2000; 4(1): 22–47. https://onlinelibrary.wiley.com/doi/abs/10.1046/j.1468-0734.2000.00002.x

Thompson

Tam

O’Brien

, et al. Fludarabine, cyclophosphamide, and rituximab treatment achieves long-term disease-free survival in IGHV-mutated chronic lymphocytic leukemia. Blood 2016; 127(3): 303–309.

Tam

Thompson

. BTK inhibitors in CLL: second-generation drugs and beyond. Blood Adv 2024; 8(9): 2300–2309.

Guarana

Nucci

. Infections in patients with chronic lymphocytic leukemia. Hematol Transfus Cell Ther 2023; 45(3): 387–393. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10499585/

da Cunha-Bang

Simonsen

Rostgaard

, et al. Improved survival for patients diagnosed with chronic lymphocytic leukemia in the era of chemo-immunotherapy: a Danish population-based study of 10455 patients. Blood Cancer J 2016; 6(11): e499. https://www.nature.com/articles/bcj2016105

Murru

Galitzia

Barabino

, et al. Prediction of severe infections in chronic lymphocytic leukemia: a simple risk score to stratify patients at diagnosis. Ann Hematol 2024; 103(5): 1655–1664. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11009768/

Andersen

Eriksen

Brieghel

, et al. And predictors of infection among patients prior to treatment of chronic lymphocytic leukemia: a Danish nationwide cohort study. Haematologica 2018; 103(7): e300–e303. https://haematologica.org/article/view/8535

Radakovich

Nagy

Nazha

. Artificial intelligence in hematology: current challenges and opportunities. Curr Hematol Malig Rep 2020; 15(3): 203–210.

10.

Sivapalaratnam

. Artificial intelligence and machine learning in haematology. Br J Haematol 2019; 185(2): 207–208. https://onlinelibrary.wiley.com/doi/abs/10.1111/bjh.15774

11.

El Achi

Khoury

. Artificial intelligence and digital microscopy applications in diagnostic hematopathology. Cancers 2020; 12(4): 797. https://www.mdpi.com/2072-6694/12/4/797

12.

Salah

Muhsen

Salama

, et al. Machine learning applications in the diagnosis of leukemia: current trends and future directions. Int J Lab Hematol 2019; 41(6): 717–725. https://onlinelibrary.wiley.com/doi/abs/10.1111/ijlh.13089

13.

Zhang

Whebell

Gallifant

, et al. An interactive dashboard to track themes, development maturity, and global equity in clinical artificial intelligence research. medRxiv; 2021. https://www.medrxiv.org/content/10.1101/2021.11.23.21266758v1

14.

Zhao

Mallesh

Höllein

, et al. Hematologist-level classification of mature B-cell neoplasm using deep learning on multiparameter flow cytometry data. Cytometry A 2020; 97(10): 1073–1080. https://pubmed.ncbi.nlm.nih.gov/32519455/

15.

Zuromski

. Augmented human intelligence and automated diagnosis in flow cytometry for hematologic malignancies. Am J Clin Pathol 2021; 155(4): 597–605.

16.

Salama

Otteson

Camp

, et al. Artificial intelligence enhances diagnostic flow cytometry workflow in the detection of minimal residual disease of chronic lymphocytic leukemia. Cancers 2022; 14(10): 2537. https://www.mdpi.com/2072-6694/14/10/2537

17.

Hoffmann

Eminovic

Wilhelm

, et al. Prediction of clinical outcomes with explainable artificial intelligence in patients with chronic lymphocytic leukemia. Curr Oncol 2023; 30(2): 1903–1915. https://www.mdpi.com/1718-7729/30/2/148

18.

Bazinet

Wang

, et al. Automated quantification of measurable residual disease in chronic lymphocytic leukemia using an artificial intelligence-assisted workflow. Cytometry B Clin Cytom 2023; 106; 264–271. https://onlinelibrary.wiley.com/doi/abs/10.1002/cyto.b.22116

19.

Nguyen

Baldwin

, et al. Computational flow cytometry provides accurate assessment of measurable residual disease in chronic lymphocytic leukaemia. Br J Haematol 2023; 202(4): 760–770. https://onlinelibrary.wiley.com/doi/abs/10.1111/bjh.18802

20.

Loscertales

Abrisqueta-Costa

Gutierrez

, et al. Real-world evidence on the clinical characteristics and management of patients with chronic lymphocytic leukemia in Spain using natural language processing: the SRealCLL study. Cancers 2023; 15(16): 4047.

21.

Queirós

Villamor

Clot

, et al. A B-cell epigenetic signature defines three biologic subgroups of chronic lymphocytic leukemia with clinical impact. Leukemia 2015; 29(3): 598–605. https://www.nature.com/articles/leu2014252

22.

Mosquera Orgueira

Antelo Rodríguez

Alonso Vence

, et al. Time to treatment prediction in chronic lymphocytic leukemia based on new transcriptional patterns. Front Oncol 2019; 9: 79. https://www.frontiersin.org/articles/10.3389/fonc.2019.00079

23.

Zhang

Qureshi

Wahid

, et al. Differential diagnosis of hematologic and solid tumors using targeted transcriptome and artificial intelligence. Am J Pathol 2022; 193(1): 51–59. https://ajp.amjpathol.org/article/S0002-9440(22)00313-3/fulltext

24.

Morabito

Adornetto

Monti

, et al. Genes selection using deep learning and explainable artificial intelligence for chronic lymphocytic leukemia predicting the need and time to therapy. Front Oncol 2023; 13: 1198992. https://www.frontiersin.org/articles/10.3389/fonc.2023.1198992

25.

Haider

Ujjan

Khan

, et al. Beyond the in-practice CBC: the research CBC parameters-driven machine learning predictive modeling for early differentiation among leukemias. Diagnostics 2022; 12(1): 138. https://www.mdpi.com/2075-4418/12/1/138

26.

Padmanabhan

El Alaoui

Elomri

, et al. Machine learning for diagnosis and screening of chronic lymphocytic leukemia using routine complete blood count (CBC) results. In: Healthcare Transformation with Informatics and Artificial Intelligence. IOS Press; 2023. 279–282. https://ebooks.iospress.nl/doi/10.3233/SHTI230483

27.

Chen

Goyal

, et al. Improved interpretability of machine learning model using unsupervised clustering: predicting time to first treatment in chronic lymphocytic leukemia. JCO Clin Cancer Inform 2019; 3: 1–11. https://ascopubs.org/doi/full/10.1200/CCI.18.00137

28.

Agius

Brieghel

Andersen

, et al. Machine learning can identify newly diagnosed patients with CLL at high risk of infection. Nat Commun 2020; 11(1): 363. https://www.nature.com/articles/s41467-019-14225-8

29.

Meiseles

Paley

Ziv

, et al. Explainable machine learning for chronic lymphocytic leukemia treatment prediction using only inexpensive tests. Comput Biol Med 2022; 145: 105490. https://www.sciencedirect.com/science/article/pii/S0010482522002827

30.

Zhang

Cui

Guo

, et al. Classification of digital pathological images of non-Hodgkin’s lymphoma subtypes based on the fusion of transfer learning and principal component analysis. Med Phys 2020; 47(9): 4241–4253. https://onlinelibrary.wiley.com/doi/abs/10.1002/mp.14357

31.

Steinbuss

Kriegsmann

Zgorzelski

, et al. Deep learning for the classification of non-hodgkin lymphoma on histopathological images. Cancers 2021; 13(10): 2419. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8156071/

32.

Chen

El Hussein

Xing

, et al. Chronic lymphocytic leukemia progression diagnosis with intrinsic cellular patterns via unsupervised clustering. Cancers 2022; 14(10): 2398. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9139505/

33.

Wang

Liu

Wang

, et al. Enhancing morphological analysis of peripheral blood cells in chronic lymphocytic leukemia with an artificial intelligence-based tool. Leuk Res 2023; 130: 107310. https://www.sciencedirect.com/science/article/pii/S0145212623005751

34.

Munir

Cairns

Bloor

, et al. Chronic lymphocytic leukemia therapy guided by measurable residual disease. N Engl J Med 2024; 390(4): 326–337. DOI: 10.1056/NEJMoa2310063.

35.

Collins

Moons

KGM

Dhiman

, et al. TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods. Br Med J 2024; 385: e078378.

36.

Barredo Arrieta

Díaz-Rodríguez

Del Ser

, et al. Explainable Artificial Intelligence (XAI): concepts, taxonomies, opportunities and challenges toward responsible AI. Inf Fusion 2020; 58: 82–115. https://www.sciencedirect.com/science/article/pii/S1566253519308103

37.

Ribeiro

Singh

Guestrin

. ‘Why should I trust you?’: explaining the predictions of any classifier. arXiv; 2016. https://arxiv.org/abs/1602.04938

38.

Lundberg

Lee

. A unified approach to interpreting model predictions. arXiv; 2017. DOI: 10.48550/arXiv.1705.07874. https://arxiv.org/abs/1705.07874

39.

NICE . Patient and public involvement policy | Public Involvement Programme|Public involvement - putting you at the heart of our work. https://www.nice.org.uk/about/nice-communities/nice-and-the-public/public-involvement/public-involvement-programme/patient-public-involvement-policy

40.

Mishra

Awasthi

Cywinski

, et al. Artificial intelligence in healthcare: 2022 year in review. 2023. https://www.researchgate.net/publication/368983262_Artificial_Intelligence_in_Healthcare_2022_Year_in_Review. DOI: 10.13140/RG.2.2.19573.86241/1

41.

Rösler

Altenbuchinger

Baeßler

, et al. An overview and a roadmap for artificial intelligence in hematology and oncology. J Cancer Res Clin Oncol 2023; 149: 7997–8006.

Supplementary Material

Please find the following supplemental material available below.

For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.

For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.

0.00 MB

0.07 MB