A machine learning approach to predicting risk of myelodysplastic syndrome

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.

Machine-learning-based predictive classifier for bone marrow failure syndrome using complete blood count data

Accurate risk assessment of bone marrow failure syndrome (BMFS) is crucial for early diagnosis and intervention. Interpreting complete blood count (CBC) data is challenging without hematological expertise. To support primary physicians, we developed a predictive model using basic demographics and CBC data collected retrospectively from two major hospitals in South Korea. Binary classifiers for aplastic anemia and myelodysplastic syndrome were created and combined to form a BMFS classifier. The model demonstrated high performance in distinguishing BMFS, with consistent results across different CBC feature sets, confirmed by external validation. This algorithm provides a practical guide for primary physicians to identify BMFS based on initial CBC data, aiding in effective triage, timely referrals, and improved patient care.

A decision support system to recommend appropriate therapy protocol for AML patients

Introduction

Acute Myeloid Leukemia (AML) is one of the most aggressive hematological neoplasms, emphasizing the critical need for early detection and strategic treatment planning. The association between prompt intervention and enhanced patient survival rates underscores the pivotal role of therapy decisions. To determine the treatment protocol, specialists heavily rely on prognostic predictions that consider the response to treatment and clinical outcomes. The existing risk classification system categorizes patients into favorable, intermediate, and adverse groups, forming the basis for personalized therapeutic choices. However, accurately assessing the intermediate-risk group poses significant challenges, potentially resulting in treatment delays and deterioration of patient conditions.

Methods

This study introduces a decision support system leveraging cutting-edge machine learning techniques to address these issues. The system automatically recommends tailored oncology therapy protocols based on outcome predictions.

Results

The proposed approach achieved a high performance close to 0.9 in F1-Score and AUC. The model generated with gene expression data exhibited superior performance.

Discussion

Our system can effectively support specialists in making well-informed decisions regarding the most suitable and safe therapy for individual patients. The proposed decision support system has the potential to not only streamline treatment initiation but also contribute to prolonged survival and improved quality of life for individuals diagnosed with AML. This marks a significant stride toward optimizing therapeutic interventions and patient outcomes.

Establishment of machine learning-based tool for early detection of pulmonary embolism

BACKGROUND AND OBJECTIVES

Pulmonary embolism (PE) is a complex disease with high mortality and morbidity rate, leading to increasing society burden. However, current diagnosis is solely based on symptoms and laboratory data despite its complex pathology, which easily leads to misdiagnosis and missed diagnosis by inexperienced doctors. Especially, CT pulmonary angiography, the gold standard method, is not widely available. In this study, we aim to establish a rapid and accurate screening model for pulmonary embolism using machine learning technology. Importantly, data required for disease prediction are easily accessed, including routine laboratory data and medical record information of patients.

METHODS

We extracted features from patients' routine laboratory results and medical records, including blood routine, biochemical group, blood coagulation routine and other test results, as well as symptoms and medical history information. Samples with a feature loss rate greater than 0.8 were deleted from the original database. Data from 4723 cases were retained, 231 of which were positive for pulmonary embolism. 50 features were retained through the positive and negative statistical hypothesis testing which was used to build the predictive model. In order to avoid identification as majority-class samples caused by the imbalance of sample proportion, we used the method of Synthetic Minority Oversampling Technique (SMOTE) to increase the amount of information on minority samples. Five typical machine learning algorithms were used to model the screening of pulmonary embolism, including Support Vector Machines, Logistic Regression, Random Forest, XGBoost, and Back Propagation Neural Networks. To evaluate model performance, sensitivity, specificity and AUC curve were analyzed as the main evaluation indicators. Furthermore, a baseline model was established using the characteristics of the pulmonary embolism guidelines as a comparison model.

RESULTS

We found that XGBoost showed better performance compared to other models, with the highest sensitivity and specificity (0.99 and 0.99, respectively). Moreover, it showed significant improvement in performance compared to the baseline model (sensitivity and specificity were 0.76 and 0.76 respectively). More important, our model showed low missed diagnosis rate (0.46) and high AUC value (0.992). Finally, the calculation time of our model is only about 0.05 s to obtain the possibility of pulmonary embolism.

CONCLUSIONS

In this study, five machine learning classification models were established to assess the likelihood of patients suffering from pulmonary embolism, and the XGBoost model most significantly improved the precision, sensitivity, and AUC for pulmonary embolism screening. Collectively, we have established an AI-based model to accurately predict pulmonary embolism at early stage.

Molecular patterns identify distinct subclasses of myeloid neoplasia

Genomic mutations drive the pathogenesis of myelodysplastic syndromes and acute myeloid leukemia. While morphological and clinical features have dominated the classical criteria for diagnosis and classification, incorporation of molecular data can illuminate functional pathobiology. Here we show that unsupervised machine learning can identify functional objective molecular clusters, irrespective of anamnestic clinico-morphological features, despite the complexity of the molecular alterations in myeloid neoplasia. Our approach reflects disease evolution, informed classification, prognostication, and molecular interactions. We apply machine learning methods on 3588 patients with myelodysplastic syndromes and secondary acute myeloid leukemia to identify 14 molecularly distinct clusters. Remarkably, our model shows clinical implications in terms of overall survival and response to treatment even after adjusting to the molecular international prognostic scoring system (IPSS-M). In addition, the model is validated on an external cohort of 412 patients. Our subclassification model is available via a web-based open-access resource ( https://drmz.shinyapps.io/mds_latent ).

Prediction of risk for myeloid malignancy in clonal hematopoiesis

Background

Clonal hematopoiesis of indeterminate potential (CHIP) and clonal cytopenia of undetermined significance (CCUS) are defined by somatic mutations in genes associated with myeloid neoplasms (MN) at a variant allele fraction (VAF) ≥ 0.02, in the absence and presence of cytopenia, respectively. CHIP/CCUS is highly prevalent in adults and defining predictors of MN risk would aid clinical management and research.

Methods

We analyzed sequenced exomes of healthy UK Biobank (UKB) participants (n = 438,890) in separate derivation and validation cohorts. Genetic mutations, laboratory values, and MN outcomes were used in conditional probability-based recursive partitioning and Cox regression to determine predictors of incident MN. Combined statistical weights defined a clonal hematopoiesis risk score (CHRS). Independent CHIP/CCUS patient cohorts were used to test prognostic capability of the CHRS in the clinical setting.

Results

Recursive partitioning distinguished CHIP/CCUS cases with 10-year probabilities of MN ranging from 0.0078 - 0.85. Multivariable analysis validated partitioning variables as predictors of MN. Key features, including single DNMT3A mutations, high risk mutations, ≥ 2 mutations, VAF ≥ 0.2, age ≥ 65 years, CCUS vs CHIP and red blood cell indices, influenced MN risk in variable direction. The CHRS defined low risk (n = 10018, 88.4%), intermediate risk (n = 1196, 10.5%), and high risk (n = 123, 1.1%) groups. In clinical cohorts, most MN events occurred in high risk CHIP/CCUS patients.

Conclusions

The CHRS provides simple prognostic framework for CHIP/CCUS, distinguishing a high risk minority from the majority of CHIP/CCUS which has minimal risk for progression to MN.

Automated Bone Marrow Cell Classification for Haematological Disease Diagnosis Using Siamese Neural Network

The critical structure and nature of different bone marrow cells which form a base in the diagnosis of haematological ailments requires a high-grade classification which is a very prolonged approach and accounts for human error if performed manually, even by field experts. Therefore, the aim of this research is to automate the process to study and accurately classify the structure of bone marrow cells which will help in the diagnosis of haematological ailments at a much faster and better rate. Various machine learning algorithms and models, such as CNN + SVM, CNN + XGB Boost and Siamese network, were trained and tested across a dataset of 170,000 expert-annotated cell images from 945 patients' bone marrow smears with haematological disorders. The metrics used for evaluation of this research are accuracy of model, precision and recall of all the different classes of cells. Based on these performance metrics the CNN + SVM, CNN + XGB, resulted in 32%, 28% accuracy, respectively, and therefore these models were discarded. Siamese neural resulted in 91% accuracy and 84% validation accuracy. Moreover, the weighted average recall values of the Siamese neural network were 92% for training and 91% for validation. Hence, the final results are based on Siamese neural network model as it was outperforming all the other algorithms used in this research.

Personalized Risk Schemes and Machine Learning to Empower Genomic Prognostication Models in Myelodysplastic Syndromes

Myelodysplastic syndromes (MDS) are characterized by variable clinical manifestations and outcomes. Several prognostic systems relying on clinical factors and cytogenetic abnormalities have been developed to help stratify MDS patients into different risk categories of distinct prognoses and therapeutic implications. The current abundance of molecular information poses the challenges of precisely defining patients' molecular profiles and their incorporation in clinically established diagnostic and prognostic schemes. Perhaps the prognostic power of the current systems can be boosted by incorporating molecular features. Machine learning (ML) algorithms can be helpful in developing more precise prognostication models that integrate complex genomic interactions at a higher dimensional level. These techniques can potentially generate automated diagnostic and prognostic models and assist in advancing personalized therapies. This review highlights the current prognostication models used in MDS while shedding light on the latest achievements in ML-based research.

A comparative analysis of machine learning approaches to predict C. difficile infection in hospitalized patients

BACKGROUND

Interventions to better prevent or manage Clostridioides difficile infection (CDI) may significantly reduce morbidity, mortality, and healthcare spending.

METHODS

We present a retrospective study using electronic health record data from over 700 United States hospitals. A subset of hospitals was used to develop machine learning algorithms (MLAs); the remaining hospitals served as an external test set. Three MLAs were evaluated: gradient-boosted decision trees (XGBoost), Deep Long Short Term Memory neural network, and one-dimensional convolutional neural network. MLA performance was evaluated with area under the receiver operating characteristic curve (AUROC), sensitivity, specificity, diagnostic odds ratios and likelihood ratios.

RESULTS

The development dataset contained 13,664,840 inpatient encounters with 80,046 CDI encounters; the external dataset contained 1,149,088 inpatient encounters with 7,107 CDI encounters. The highest AUROCs were achieved for XGB, Deep Long Short Term Memory neural network, and one-dimensional convolutional neural network via abstaining from use of specialized training techniques, resampling in isolation, and resampling and output bias in combination, respectively. XGBoost achieved the highest AUROC.

CONCLUSIONS

MLAs can predict future CDI in hospitalized patients using just 6 hours of data. In clinical practice, a machine-learning based tool may support prophylactic measures, earlier diagnosis, and more timely implementation of infection control measures.

Usability of Electronic Health records in Predicting Short-term falls: Machine learning Applications in Senior Care Facilities (Preprint)

Background

Short-term fall prediction models that use electronic health records (EHRs) may enable the implementation of dynamic care practices that specifically address changes in individualized fall risk within senior care facilities.

Objective

The aim of this study is to implement machine learning (ML) algorithms that use EHR data to predict a 3-month fall risk in residents from a variety of senior care facilities providing different levels of care.

Methods

This retrospective study obtained EHR data (2007-2021) from Juniper Communities’ proprietary database of 2785 individuals primarily residing in skilled nursing facilities, independent living facilities, and assisted living facilities across the United States. We assessed the performance of 3 ML-based fall prediction models and the Juniper Communities’ fall risk assessment. Additional analyses were conducted to examine how changes in the input features, training data sets, and prediction windows affected the performance of these models.

Results

The Extreme Gradient Boosting model exhibited the highest performance, with an area under the receiver operating characteristic curve of 0.846 (95% CI 0.794-0.894), specificity of 0.848, diagnostic odds ratio of 13.40, and sensitivity of 0.706, while achieving the best trade-off in balancing true positive and negative rates. The number of active medications was the most significant feature associated with fall risk, followed by a resident’s number of active diseases and several variables associated with vital signs, including diastolic blood pressure and changes in weight and respiratory rates. The combination of vital signs with traditional risk factors as input features achieved higher prediction accuracy than using either group of features alone.

Conclusions

This study shows that the Extreme Gradient Boosting technique can use a large number of features from EHR data to make short-term fall predictions with a better performance than that of conventional fall risk assessments and other ML models. The integration of routinely collected EHR data, particularly vital signs, into fall prediction models may generate more accurate fall risk surveillance than models without vital signs. Our data support the use of ML models for dynamic, cost-effective, and automated fall predictions in different types of senior care facilities.