Prediction of complete remission and survival in acute myeloid leukemia using supervised machine learning

The state of prediction models in hematologic disease: a worrisome assessment

PURPOSE OF REVIEW

The lack of optimal treatments for haematological disorders has led to the need for prediction models for diagnosis, therapeutic decision-making and life planning. In this review, the worrying current state of predictive models in the field is discussed.

RECENT FINDINGS

Here, we reviewed 100 studies on prediction models in this field. Our analysis revealed a concerning state of affairs, with a prevalence of suboptimal research methodologies and questionable statistical practices. This includes insufficient sample sizes, inadequate model evaluations, lack of necessary reports of model results, etc. In this regard, we present statistical considerations in the development and validation process of numerous models. This will provide the reader with the statistical knowledge related to prediction model necessary to assess bias in studies, compare other published models and determine the clinical utility of models.

SUMMARY

Awareness among authors, reviewers and editors of the required statistical considerations is crucial. Reinforcing these in all studies involving prediction models is needed. We all should encourage their use in evaluating existing studies and taking them fully into account in future studies.

Revisiting the Role of Day 14 Bone Marrow Biopsy in Acute Myeloid Leukemia

In recent years, the practice of routinely obtaining day 14 bone marrow biopsies during AML intensive induction therapy has been scrutinized. While current guidelines recommend obtaining mid-induction biopsies to gauge early response to treatment and guide potential changes in future management, concerns have been raised that these biopsies may not be as prognostically accurate as hoped and subsequently may result in additional and unwarranted chemotherapy toxicity in select patients. In this review, our goal is to summarize the most recent evidence surrounding day 14 bone marrow biopsies that have been published and clarify the utility of this currently recommended practice. Here, we review major developments in mid-induction biopsy in AML, along with ongoing and future planned studies in this area, outlining the limitations of available data and our future goals.

[Advancements in artificial intelligence for the precise diagnosis and treatment of hematological malignancies]

Hematological malignancy is a highly heterogeneous disease with complex biological characteristics and diverse clinical manifestations. Therefore, precise diagnosis and treatment are crucial and urgently needed. To further improve the accuracy of diagnosis and prognostication and to promote personalized therapy, artificial intelligence (AI) has been increasingly used. This study reviewed literature published in the last 5 years and summarized the application, benefits, and drawbacks of AI in the diagnosis, treatment, and prognosis of hematologic malignancies. Although AI can effectively improve the accuracy of diagnosis and therapy, low-quality data, poor interpretability of the model, and limited clinical transformation have impeded its popularization and application. In the future, the clinical application of AI in hematologic malignancy can be accelerated by establishing standards for clinical data processing, integrating multimodal information for accurate diagnosis and prognostication, and conducting systematic clinical verification of model algorithms.

Machine learning in paediatric haematological malignancies: a systematic review of prognosis, toxicity and treatment response models

BACKGROUND

Machine Learning (ML) has demonstrated potential in enhancing care in adult oncology. However, its application in paediatric haematological malignancies is still emerging, necessitating a comprehensive review of its capabilities and limitations in this area.

METHODS

A literature search was conducted through Ovid. Studies included focused on ML models in paediatric patients with haematological malignancies. Studies were categorised into thematic groups for analysis.

RESULTS

Twenty studies, primarily on leukaemia, were included in this review. Studies were organised into thematic categories such as prognoses, treatment responses and toxicity predictions. Prognostic studies showed AUC scores between 0.685 and 0.929, indicating moderate-high predictive accuracy. Treatment response studies demonstrated AUC scores between 0.840 and 0.875, reflecting moderate accuracy. Toxicity prediction studies reported high accuracy with AUC scores from 0.870 to 0.927. Only five studies (25%) performed external validation. Significant heterogeneity was noted in ML tasks, reporting formats, and effect measures across studies, highlighting a lack of standardised reporting and challenges in data comparability.

CONCLUSION

The clinical applicability of these ML models remains limited by the lack of external validation and methodological heterogeneity. Addressing these challenges through standardised reporting and rigorous external validation is needed to translate ML from a promising research tool into a reliable clinical practice component.

IMPACT

Key message: Machine Learning (ML) significantly enhances predictive models in paediatric haematological cancers, offering new avenues for personalised treatment strategies. Future research should focus on developing ML models that can integrate with real-time clinical workflows. Addition to literature: Provides a comprehensive overview of current ML applications and trends. It identifies limitations to its applicability, including the limited diversity in datasets, which may affect the generalisability of ML models across different populations.

IMPACT

Encourages standardisation and external validation in ML studies, aiming to improve patient outcomes through precision medicine in paediatric haematological oncology.

A novel perspective on survival prediction for AML patients: Integration of machine learning in SEER database applications

Objective

The purpose of this study is to explore the epidemiological characteristics of acute myeloid leukemia (AML) and establish a more accurate model for predicting the prognosis of AML patients based on machine learning.

Methods

We obtained clinical data of a total of 87,090 AML patients between 1975 and 2019 from the SEER database. First, we used Kaplan-Meier analysis to examine the prognosis of patients in different strata. Then, we discussed the independent factors that influenced the overall survival (OS) of AML patients, using univariate and multivariate Cox regression analysis. Finally, we used 11 machine learning algorithms to predict the survival rate of AML patients at 1, 2, and 3 years, respectively. We also used five-fold cross-validation with 20 cycles to obtain the optimal parameters for each model, in order to improve the accuracy of predictions.

Results

The Kaplan-Meier analysis showed that the survival rate of patients diagnosed after 2010 was significantly higher than that of those diagnosed before. In addition, older age, male gender, and non-black race were associated with poor prognosis. Among the FAB subtypes, M3 AML had a better prognosis than other subtypes, and among the WHO subtypes, AML associated with Down syndrome had the best prognosis, followed by AML with eosinophilic abnormalities. The Cox regression analysis demonstrated that gender, age, race, and family income were significantly related to the survival of AML patients. Among the 11 machine learning models, the random forest classifier performed best on multiple evaluation metrics in predicting survival at 1, 2, and 3 years. In addition, both the XGBoost classifier and the neural network classifier showed high accuracy and reliability at each prediction stage.

Conclusion

Through in-depth analysis, this study provides a deeper understanding of the epidemiological characteristics of AML and successfully establishes a prediction model based on machine learning, which demonstrates good accuracy and reliability in predicting the prognosis of AML patients.

Predictive modeling of outcomes in acute leukemia patients undergoing allogeneic hematopoietic stem cell transplantation using machine learning techniques

BACKGROUND

Leukemia necessitates continuous research for effective therapeutic techniques. Acute leukemia (AL) patients undergoing allogeneic hematopoietic stem cell transplantation (allo-HSCT) focus on key outcomes such as overall survival (OS), relapse, and graft-versus-host disease (GVHD).

OBJECTIVE

This study aims to evaluate the capability of machine learning (ML) models in predicting OS, relapse, and GVHD in AL patients post-allo-HSCT.

METHODS

Clinical data from 1243 AL patients, with 10 years of follow-up, was utilized to develop 28 ML models. These models incorporated four feature selection methods and seven ML algorithms. Model performance was assessed using the concordance index (c-index) with multivariate analysis.

RESULTS

The multivariate model analysis showed the best FS/ML combinations were UCI_GLMN, IBMA_GLMN and IBMA_CB for OS, UCI_ST, UCI_RSF, UCI GLMB, UCI_GB, UCI_CB, MI_GLMN, IBMA_ST and IBMA GB for relapse, IBMA_GB for aGVHD and Boruta_GB for cGVHD (all p values < 0.0001, mean C-indices in 0.61-0.68)).

CONCLUSION

ML techniques, when combined with clinical variables, demonstrate high accuracy in predicting OS, relapse, and GVHD in AL patients.

Models for the marrow: A comprehensive review of AI-based cell classification methods and malignancy detection in bone marrow aspirate smears

Given the high prevalence of artificial intelligence (AI) research in medicine, the development of deep learning (DL) algorithms based on image recognition, such as the analysis of bone marrow aspirate (BMA) smears, is rapidly increasing in the field of hematology and oncology. The models are trained to identify the optimal regions of the BMA smear for differential cell count and subsequently detect and classify a number of cell types, which can ultimately be utilized for diagnostic purposes. Moreover, AI is capable of identifying genetic mutations phenotypically. This pipeline has the potential to offer an accurate and rapid preliminary analysis of the bone marrow in the clinical routine. However, the intrinsic complexity of hematological diseases presents several challenges for the automatic morphological assessment. To ensure general applicability across multiple medical centers and to deliver high accuracy on prospective clinical data, AI models would require highly heterogeneous training datasets. This review presents a systematic analysis of models for cell classification and detection of hematological malignancies published in the last 5 years (2019-2024). It provides insight into the challenges and opportunities of these DL-assisted tasks.

Optimization of diagnosis and treatment of hematological diseases via artificial intelligence

Background

Optimizing the diagnosis and treatment of hematological diseases is a challenging yet crucial research area. Effective treatment plans typically require the comprehensive integration of cell morphology, immunology, cytogenetics, and molecular biology. These plans also consider patient-specific factors such as disease stage, age, and genetic mutation status. With the advancement of artificial intelligence (AI), more "AI + medical" application models are emerging. In clinical practice, many AI-assisted systems have been successfully applied to the diagnosis and treatment of hematological diseases, enhancing precision and efficiency and offering valuable solutions for clinical practice.

Objective

This study summarizes the research progress of various AI-assisted systems applied in the clinical diagnosis and treatment of hematological diseases, with a focus on their application in morphology, immunology, cytogenetics, and molecular biology diagnosis, as well as prognosis prediction and treatment.

Methods

Using PubMed, Web of Science, and other network search engines, we conducted a literature search on studies from the past 5 years using the main keywords "artificial intelligence" and "hematological diseases." We classified the clinical applications of AI systems according to the diagnosis and treatment. We outline and summarize the current advancements in AI for optimizing the diagnosis and treatment of hematological diseases, as well as the difficulties and challenges in promoting the standardization of clinical diagnosis and treatment in this field.

Results

AI can significantly shorten turnaround times, reduce diagnostic costs, and accurately predict disease outcomes through applications in image-recognition technology, genomic data analysis, data mining, pattern recognition, and personalized medicine. However, several challenges remain, including the lack of AI product standards, standardized data, medical-industrial collaboration, and the complexity and non-interpretability of AI systems. In addition, regulatory gaps can lead to data privacy issues. Therefore, more research and improvements are needed to fully leverage the potential of AI to promote standardization of the clinical diagnosis and treatment of hematological diseases.

Conclusion

Our results serve as a reference point for the clinical diagnosis and treatment of hematological diseases and the development of AI-assisted clinical diagnosis and treatment systems. We offer suggestions for further development of AI in hematology and standardization of clinical diagnosis and treatment.

Pediatric Acute Myeloid Leukemia: Unraveling Complexities in Intensive Chemotherapy and the Emergence of Superbugs - A Case Study

Background

This case report underscores the intricate challenges in managing paediatric patients with acute myeloid leukaemia (AML) undergoing intensive chemotherapy, particularly when complicated by the emergence of multidrug-resistant pathogens such as Carbapenem-Resistant Pseudomonas aeruginosa (CRPA).

Case Presentation

An 11-year-old male with AML presented with skin purpura and persistent cough. Clinical and laboratory assessments revealed a high-risk AML profile with genetic mutations, leading to the initiation of intensive chemotherapy per the C-HUANA-AML-2015 protocol. Despite successful disease remission after initial chemotherapy courses, the patient experienced unexpected complications. Notably, septic shock, bone marrow failure, and the emergence of CRPA were encountered during the clinical course. Septic shock occurred following Course B3 chemotherapy, marked by a fever unresponsive to initial antibiotic therapy. Despite negative blood cultures, meropenem and vancomycin were initiated, successfully normalizing temperature. Subsequent challenges included persistent bone marrow suppression, perianal dermatitis, and the identification of CRPA in stool cultures, leading to altered antibiotic therapy guided by minimum inhibitory concentration (MIC) considerations. Whole-genome sequencing (WGS) of the CRPA strain revealed a highly virulent clone (ST-970) with numerous resistance and virulence genes.

Conclusion

This case report offers new insights into the complexities of pediatric AML management, with a focus on the emergence of CRPA. The discovery of a high-risk CRPA clone with detailed genomic data underscores the growing challenge of antimicrobial resistance in pediatric oncology. The persistent presence of CRPA and ongoing bone marrow failure highlight the difficulties in managing these complications. This case calls for a reassessment of treatment strategies and encourages further research to improve outcomes in pediatric AML, emphasizing the need for a multidisciplinary approach to address infectious complications and antimicrobial resistance.

Machine learning and integrative multi-omics network analysis for survival prediction in acute myeloid leukemia

BACKGROUND

Acute myeloid leukemia (AML) is the most common malignant myeloid disorder in adults and the fifth most common malignancy in children, necessitating advanced technologies for outcome prediction.

METHOD

This study aims to enhance prognostic capabilities in AML by integrating multi-omics data, especially gene expression and methylation, through network-based feature selection methodologies. By employing artificial intelligence and network analysis, we are exploring different methods to build a machine learning model for predicting AML patient survival. We evaluate the effectiveness of combining omics data, identify the most informative method for network integration and compare the performance with standard feature selection methods.

RESULTS

Our findings demonstrate that integrating gene expression and methylation data significantly improves prediction accuracy compared to single omics data. Among network integration methods, our study identifies the best approach that improves informative feature selection for predicting patient outcomes in AML. Comparative analyses demonstrate the superior performance of the proposed network-based methods over standard techniques.

CONCLUSIONS

This research presents an innovative and robust methodology for building a survival prediction model tailored to AML patients. By leveraging multilayer network analysis for feature selection, our approach contributes to improving the understanding and prognostic capabilities in AML and laying the foundation for more effective personalized therapeutic interventions in the future.

Survival prediction landscape: an in-depth systematic literature review on activities, methods, tools, diseases, and databases

Survival prediction integrates patient-specific molecular information and clinical signatures to forecast the anticipated time of an event, such as recurrence, death, or disease progression. Survival prediction proves valuable in guiding treatment decisions, optimizing resource allocation, and interventions of precision medicine. The wide range of diseases, the existence of various variants within the same disease, and the reliance on available data necessitate disease-specific computational survival predictors. The widespread adoption of artificial intelligence (AI) methods in crafting survival predictors has undoubtedly revolutionized this field. However, the ever-increasing demand for more sophisticated and effective prediction models necessitates the continued creation of innovative advancements. To catalyze these advancements, it is crucial to bring existing survival predictors knowledge and insights into a centralized platform. The paper in hand thoroughly examines 23 existing review studies and provides a concise overview of their scope and limitations. Focusing on a comprehensive set of 90 most recent survival predictors across 44 diverse diseases, it delves into insights of diverse types of methods that are used in the development of disease-specific predictors. This exhaustive analysis encompasses the utilized data modalities along with a detailed analysis of subsets of clinical features, feature engineering methods, and the specific statistical, machine or deep learning approaches that have been employed. It also provides insights about survival prediction data sources, open-source predictors, and survival prediction frameworks.

Identification of a novel monocyte/macrophage-related gene signature for predicting survival and immune response in acute myeloid leukemia

Acute myeloid leukemia (AML) is a heterogeneous hematological tumor with poor immunotherapy effect. This study was to develop a monocyte/macrophage-related prognostic risk score (MMrisk) and identify new therapeutic biomarkers for AML. We utilized differentially expressed genes (DEGs) in combination with single-cell RNA sequencing to identify monocyte/macrophage-related genes (MMGs). Eight genes were selected for the construction of a MMrisk model using univariate Cox regression analysis and LASSO regression analysis. We then validated the MMrisk on two GEO datasets. Lastly, we investigated the immunologic characteristics and advantages of immunotherapy and potential targeted drugs for MMrisk groups. Our study identified that the MMrisk is composed of eight MMGs, including HOPX, CSTB, MAP3K1, LGALS1, CFD, MXD1, CASP1 and BCL2A1. The low MMrisk group survived longer than high MMrisk group (P < 0.001). The high MMrisk group was positively correlated with B cells, plasma cells, CD4 memory cells, Mast cells, CAFs, monocytes, M2 macrophages, Endothelial, tumor mutation, and most immune checkpoints (PD1, Tim-3, CTLA4, LAG3). Furthermore, drug sensitivity analysis showed that AZD.2281, Axitinib, AUY922, ABT.888, and ATRA were effective in high-risk MM patients. Our research shows that MMrisk is a potential biomarker which is helpful to identify the molecular characteristics of AML immunology.

Using machine learning to unravel the intricacy of acute myeloid leukemia

Not available.

Development and validation of a cuproptosis-related prognostic model for acute myeloid leukemia patients using machine learning with stacking

Our objective is to develop a prognostic model focused on cuproptosis, aimed at predicting overall survival (OS) outcomes among Acute myeloid leukemia (AML) patients. The model utilized machine learning algorithms incorporating stacking. The GSE37642 dataset was used as the training data, and the GSE12417 and TCGA-LAML cohorts were used as the validation data. Stacking was used to merge the three prediction models, subsequently using a random survival forests algorithm to refit the final model using the stacking linear predictor and clinical factors. The prediction model, featuring stacking linear predictor and clinical factors, achieved AUC values of 0.840, 0.876 and 0.892 at 1, 2 and 3 years within the GSE37642 dataset. In external validation dataset, the corresponding AUCs were 0.741, 0.754 and 0.783. The predictive performance of the model in the external dataset surpasses that of the model simply incorporates all predictors. Additionally, the final model exhibited good calibration accuracy. In conclusion, our findings indicate that the novel prediction model refines the prognostic prediction for AML patients, while the stacking strategy displays potential for model integration.

Unlocking the Potential of Artificial Intelligence in Acute Myeloid Leukemia and Myelodysplastic Syndromes

PURPOSE OF THE REVIEW

This review aims to elucidate the transformative impact and potential of machine learning (ML) in the diagnosis, prognosis, and clinical management of myelodysplastic syndromes (MDS) and acute myeloid leukemia (AML). It further aims to bridge the gap between current advances of ML and their practical application in these diseases.

RECENT FINDINGS

Recent advances in ML have revolutionized prognostication, diagnosis, and treatment of MDS and AML. ML algorithms have proven effective in predicting disease progression, optimizing treatment responses, and in the stratification of patient groups. Particularly, the use of ML in genomic and epigenomic data analysis has unveiled novel insights into the molecular heterogeneity of MDS and AML, leading to better-informed therapeutic strategies. Furthermore, deep learning techniques have shown promise in analyzing complex patterns in bone marrow biopsy images, providing a potential pathway towards early and accurate diagnosis. While still in the nascent stages, ML applications in MDS and AML signify a paradigm shift towards precision medicine. The integration of ML with traditional clinical practices could potentially enhance diagnostic accuracy, refine risk stratification, and improve therapeutic approaches. However, challenges related to data privacy, standardization, and algorithm interpretability must be addressed to realize the full potential of ML in this field. Future research should focus on the development of robust, transparent ML models and their ethical implementation in clinical settings.

Artificial intelligence-based prediction models for acute myeloid leukemia using real-life data: A DATAML registry study

We designed artificial intelligence-based prediction models (AIPM) using 52 diagnostic variables from 3687 patients included in the DATAML registry treated with intensive chemotherapy (IC, N = 3030) or azacitidine (AZA, N = 657) for an acute myeloid leukemia (AML). A neural network called multilayer perceptron (MLP) achieved a prediction accuracy for overall survival (OS) of 68.5% and 62.1% in the IC and AZA cohorts, respectively. The Boruta algorithm could select the most important variables for prediction without decreasing accuracy. Thirteen features were retained with this algorithm in the IC cohort: age, cytogenetic risk, white blood cells count, LDH, platelet count, albumin, MPO expression, mean corpuscular volume, CD117 expression, NPM1 mutation, AML status (de novo or secondary), multilineage dysplasia and ASXL1 mutation; and 7 variables in the AZA cohort: blood blasts, serum ferritin, CD56, LDH, hemoglobin, CD13 and disseminated intravascular coagulation (DIC). We believe that AIPM could help hematologists to deal with the huge amount of data available at diagnosis, enabling them to have an OS estimation and guide their treatment choice. Our registry-based AIPM could offer a large real-life dataset with original and exhaustive features and select a low number of diagnostic features with an equivalent accuracy of prediction, more appropriate to routine practice.

Recent advances in precision medicine for acute myeloid leukemia

PURPOSE OF REVIEW

Acute myeloid leukemia (AML) is a heterogeneous disease, in which treatment response and patient survival are highly conditioned by the leukemia biology. The aim of this review is to summarize recent advances in AML classification, risk stratification models, measurable residual disease (MRD) and the increasing number of treatment options that are paving the way towards precision medicine in AML.

RECENT FINDINGS

AML classification and risk stratification were recently updated by incorporating novel molecular markers that are important for diagnosis and outcome prediction. In addition, the impact of co-mutational patterns is under investigation and novel approaches using machine learning algorithms are starting to be used for individualized risk estimation. Molecular markers are also becoming useful in predicting response to non-intensive treatments. MRD informs of treatment response with high sensitivity, allowing dynamic patient risk assessment and early intervention. Finally, important advances were made in AML therapy, with an increasing number of targeted therapies becoming available and many novel treatment approaches being under development with promising early results.

SUMMARY

A better understanding of AML biology is leading to improved risk stratification and important advances in treatments, which are allowing the development of precision medicine in AML at an unprecedented pace.

Prognostic impact of the AML ELN2022 risk classification in patients undergoing allogeneic stem cell transplantation

For most patients with acute myeloid leukemia (AML), an allogeneic hematopoietic stem cell transplantation (HSCT) offers the highest chance of cure. Recently, the European LeukemiaNet (ELN) published updated recommendations on the diagnosis and risk classification in AML based on genetic factors at diagnosis as well as a dynamic adjustment (reclassification) according to the measurable residual disease (MRD) status for the favorable and intermediate risk groups. Validation of the ELN2022 risk classification has not been reported. We retrospectively analyzed 522 AML patients who received an HSCT at a median age of 59 (range 16-76) years. For patients with adequate material available and in remission prior to HSCT (n = 229), the MRD status was evaluated. Median follow-up after HSCT was 3.0 years. ELN2022 risk at diagnosis was in 22% favorable, in 26% intermediate, and in 52% adverse. ELN2022 risk at diagnosis is associated with the cumulative incidence of relapse/progression (CIR), event-free survival (EFS), and overall survival (OS) in the whole patient cohort, as well as the subgroup of patients transplanted in first remission. However, the risk stratification based on the ELN2022 classification did not significantly improve outcome prognostication in comparison to the ELN2017 classification. In our study, the newly added group of patients with myelodysplasia-related gene mutations did not have adverse outcomes. Re-classifying these patients into the intermediate risk group and adjusting the grouping for all AML patients by MRD at HSCT, led to a refined and improved risk stratification, which should be validated in independent studies.