A Systematic Review of Machine Learning Techniques in Hematopoietic Stem Cell Transplantation (HSCT)

Pre-transplant and transplant parameters predict long-term survival after hematopoietic cell transplantation using machine learning

BACKGROUND

Allogeneic hematopoietic stem transplantation (allo-HSCT) constitutes a curative treatment for various hematological malignancies. However, various complications limit the therapeutic efficacy of this approach, increasing the morbidity and decreasing the overall survival of allo-HSCT recipients. In everyday clinical practice, various laboratory and clinical biomarkers and scorning systems have been developed and implemented focusing on the recognition of high-risk patients for organ dysfunction-related complications and those who might experience low overall survival. However, the predictive accuracy of developed scores has been reported deficient in some studies. The aim of the current retrospective study is to develop a machine learning (ML) model to predict the long-term survivorship of patients who receive allo-HSCT based on clinical pre- and post-allo-HSCT variables, and on transplantation-related characteristics.

METHODS

For this purpose, a database of 564 allo-HSCT recipients incorporating 16 clinical and laboratory variables and the survivorship status of the patients during follow-up (Alive, Dead, Alive but follow-up less than 24 months) was used. An ML model was developed and tested, based on the previously published Data Ensemble Refinement Greedy Algorithm (DEGRA) algorithm.

RESULTS

A predictive ML model was built with 92.02 % accuracy. The eight parameters included in the algorithm were the following: CD34+ cells infused, patients' age and gender, conditioning regimen toxicity, disease risk index (DRI), graft source, and platelet and neutrophil engraftment.

CONCLUSION

To our knowledge, this is the first AI model incorporating post-HSCT variables for the prediction of mortality in adult HSCT recipients. In the era of precision medicine, the recognition of patients who undergo allo-HSCT and face a great risk for mortality and morbidity, with high-accuracy algorithms is crucial.

The Applications of Machine Learning in the Management of Patients Undergoing Stem Cell Transplantation: Are We Ready?

Hematopoietic stem cell transplantation (HSCT) is a life-saving therapy for hematologic malignancies, such as leukemia and lymphoma and other severe conditions but is associated with significant risks, including graft versus host disease (GVHD), relapse, and treatment-related mortality. The increasing complexity of clinical, genomic, and biomarker data has spurred interest in machine learning (ML), which has emerged as a transformative tool to enhance decision-making and optimize outcomes in HSCT. This review examines the applications of ML in HSCT, focusing on donor selection, conditioning regimen, and prediction of post-transplant outcomes. Machine learning approaches, including decision trees, random forests, and neural networks, have demonstrated potential in improving donor compatibility algorithms, mortality and relapse prediction, and GVHD risk stratification. Integrating "omics" data with ML models has enabled the identification of novel biomarkers and the development of highly accurate predictive tools, supporting personalized treatment strategies. Despite promising advancements, challenges persist, including data standardization, algorithm interpretability, and ethical considerations regarding patient privacy. While ML holds promise for revolutionizing HSCT management, addressing these barriers through multicenter collaborations and regulatory frameworks remains essential for broader clinical adoption. In addition, the potential of ML can cope with some challenges such as data harmonization, patients' data protection, and availability of adequate infrastructure. Future research should prioritize larger datasets, multimodal data integration, and robust validation methods to fully realize ML's transformative potential in HSCT.

Comparison of oral zinc supplement and placebo effect in improving the T-cells regeneration in patients undergoing autologous hematopoietic stem cell transplantation: Clinical trial study

BACKGROUND

Immune reconstitution is a significant factor in the success of "hematopoietic stem cell transplantation" (HSCT). Delaying the immune reconstitution increases the risk of infections and relapse after transplantation. T-cell recovery after HSCT is mainly thymus-dependent, and thymic atrophy is associated with various clinical conditions that correlate with HSCT outcomes. Thymus rejuvenation can improve immune reconstitution after transplantation.Zinc (Zn) plays a pivotal role in thymus rejuvenation. Zn deficiency can lead to thymic atrophy, which increases susceptibility to infections. Zn supplementation restores the immune system by increasing thymus output and T-cell repertoire production.We designed this protocol to investigate the effect of oral Zn supplementation on T-cell recovery in patients undergoing HSCT.

METHODS

Forty eligible candidates for autologous-HSCT will be selected. They will be randomly divided into Zn and placebo groups. Subsequently, they will receive 3 Zn or placebo tablets for the first 30 days post-HSCT (+1 to +30), followed by 1 pill or placebo for days (+31 to +90). The copy numbers of "recent thymic emigrants" T cells and "T cell Receptor Excision Circles" (TREC) will be assessed before and after the intervention in peripheral blood mononuclear cells (PBMCs). All patients will be followed up 365 days post-HSCT for relapse and infection.

CONCLUSION

This clinical trial is the first to determine the efficiency of "Zn gluconate" as daily Supplementation in T cell recovery post-HSCT.If successful, an available and inexpensive drug will improve immune system reconstruction after HSCT, reduce the risk of infection, particularly viral infections, and increase patient survival.

Gut microbiota and graft-versus-host disease in hematopoietic stem cell transplant patients

Background and Objectives

Graft-versus-host disease (GvHD) frequently complicates hematopoietic stem cell transplantation (HSCT). Emerging evidence suggests a correlation between gut microbiota and GvHD risk. This study aims to elucidate the microbiota profiles in HSCT patients before and after transplantation and their association with GvHD.

Materials and Methods

This study, conducted from December 2022 to December 2023, involved the collection of 15 stool samples from HSCT patients. Bacterial content was quantified using real-time PCR, while interleukin-6 levels were assessed via ELISA.

Results

Among the 15 participants (8 male, 7 female), 9 underwent allogeneic HSCT (allo-HSCT) and 6 received autologous HSCT. In the aGvHD group, there was a significant reduction in the abundance of Bacteroides and Bifidobacterium compared to those without aGvHD. Additionally, declines were observed in Clostridium and Firmicutes populations. The genus Blautia also showed reduced prevalence in the aGvHD group, whereas no significant differences were noted in the uncomplicated group. ELISA analysis revealed that interleukin-6 levels remained within the normal range (30-960 pg/ml) with no significant elevation in the aGvHD group.

Conclusion

The study highlights a notable association between alterations in gut microbiota, specifically reductions in certain bacterial populations and the development of aGvHD following allo-HSCT.

Data Preprocessing Techniques for AI and Machine Learning Readiness: Scoping Review of Wearable Sensor Data in Cancer Care

BACKGROUND

Wearable sensors are increasingly being explored in health care, including in cancer care, for their potential in continuously monitoring patients. Despite their growing adoption, significant challenges remain in the quality and consistency of data collected from wearable sensors. Moreover, preprocessing pipelines to clean, transform, normalize, and standardize raw data have not yet been fully optimized.

OBJECTIVE

This study aims to conduct a scoping review of preprocessing techniques used on raw wearable sensor data in cancer care, specifically focusing on methods implemented to ensure their readiness for artificial intelligence and machine learning (AI/ML) applications. We sought to understand the current landscape of approaches for handling issues, such as noise, missing values, normalization or standardization, and transformation, as well as techniques for extracting meaningful features from raw sensor outputs and converting them into usable formats for subsequent AI/ML analysis.

METHODS

We systematically searched IEEE Xplore, PubMed, Embase, and Scopus to identify potentially relevant studies for this review. The eligibility criteria included (1) mobile health and wearable sensor studies in cancer, (2) written and published in English, (3) published between January 2018 and December 2023, (4) full text available rather than abstracts, and (5) original studies published in peer-reviewed journals or conferences.

RESULTS

The initial search yielded 2147 articles, of which 20 (0.93%) met the inclusion criteria. Three major categories of preprocessing techniques were identified: data transformation (used in 12/20, 60% of selected studies), data normalization and standardization (used in 8/20, 40% of the selected studies), and data cleaning (used in 8/20, 40% of the selected studies). Transformation methods aimed to convert raw data into more informative formats for analysis, such as by segmenting sensor streams or extracting statistical features. Normalization and standardization techniques usually normalize the range of features to improve comparability and model convergence. Cleaning methods focused on enhancing data reliability by handling artifacts like missing values, outliers, and inconsistencies.

CONCLUSIONS

While wearable sensors are gaining traction in cancer care, realizing their full potential hinges on the ability to reliably translate raw outputs into high-quality data suitable for AI/ML applications. This review found that researchers are using various preprocessing techniques to address this challenge, but there remains a lack of standardized best practices. Our findings suggest a pressing need to develop and adopt uniform data quality and preprocessing workflows of wearable sensor data that can support the breadth of cancer research and varied patient populations. Given the diverse preprocessing techniques identified in the literature, there is an urgency for a framework that can guide researchers and clinicians in preparing wearable sensor data for AI/ML applications. For the scoping review as well as our research, we propose a general framework for preprocessing wearable sensor data, designed to be adaptable across different disease settings, moving beyond cancer care.

A literature review: machine learning-based stem cell investigation

Background and Objective

Stem cell (SC) is a crucial factor of the human organ that is significantly important for clinical solutions. However, consideration of SC in the therapeutic or disease classification process is complex in terms of accurate classification and prediction. To overcome this issue, Machine learning (ML) is the most effective technique that is frequently used in cell-based clinical applications for diagnosis, treatment, and disease identification. Recently it has been implemented for SC observation which is a crucial factor for clinical solutions. Thus, the objective of this review work is to represent the effectiveness of ML techniques for SC observation from clinical perspectives with current challenges and future direction for further improvement.

Methods

In this study, we conducted a short review of ML-based applications in SCs investigation and classification for the improvement of clinical solutions. We explored studies from five scientific databases (Web of Science, Google Scholar, Scopus, ScienceDirect, and PubMed) with several keywords related to the objective of our research study. After primary and secondary screening, 15 articles were utilized for this research study and summarized the observation results in terms of ten aspects (year of publication, focused area, objective, experimented datasets, selected ML classifiers, experimental procedure, classification parameter, overall performance in terms of accuracy, advancements, and limitations) with their current limitations and future improvement directions.

Key Content and Findings

The majority of the existing literature review works are limited to focusing on specific SC-based investigation, limited evaluation attributes, and lack of challenges and future improvement suggestions. Also, most of the review work didn't consider the investigation of the effectiveness of the ML technique in SC biology. Therefore, in this paper, we investigate existing literature related to the development of clinical solutions considering ML techniques, in the area of SC and cell culture processes and highlight current challenges and future directions.

Conclusions

The majority of studies focused on the disease identification process and implemented the convolutional neural network and support vector machine techniques. The prime limitations of the investigated studies are related to the focused area, investigated SCs, the small number of experimental datasets, and validation techniques. None of the studies provided complete evidence to determine an optimal ML technique for SC to build classification or predictive models. Therefore, further concern is required to develop and improve the developed solutions including other ML techniques, large datasets, and advanced evaluation processes.

The State of Artificial Intelligence in Pediatric Surgery: A Systematic Review

BACKGROUND

Artificial intelligence (AI) has been recently shown to improve clinical workflows and outcomes - yet its potential in pediatric surgery remains largely unexplored. This systematic review details the use of AI in pediatric surgery.

METHODS

Nine medical databases were searched from inception until January 2023, identifying articles focused on AI in pediatric surgery. Two authors reviewed full texts of eligible articles. Studies were included if they were original investigations on the development, validation, or clinical application of AI models for pediatric health conditions primarily managed surgically. Studies were excluded if they were not peer-reviewed, were review articles, editorials, commentaries, or case reports, did not focus on pediatric surgical conditions, or did not employ at least one AI model. Extracted data included study characteristics, clinical specialty, AI method and algorithm type, AI model (algorithm) role and performance metrics, key results, interpretability, validation, and risk of bias using PROBAST and QUADAS-2.

RESULTS

Authors screened 8178 articles and included 112. Half of the studies (50%) reported predictive models (for adverse events [25%], surgical outcomes [16%] and survival [9%]), followed by diagnostic (29%) and decision support models (21%). Neural networks (44%) and ensemble learners (36%) were the most commonly used AI methods across application domains. The main pediatric surgical subspecialties represented across all models were general surgery (31%) and neurosurgery (25%). Forty-four percent of models were interpretable, and 6% were both interpretable and externally validated. Forty percent of models had a high risk of bias, and concerns over applicability were identified in 7%.

CONCLUSIONS

While AI has wide potential clinical applications in pediatric surgery, very few published AI algorithms were externally validated, interpretable, and unbiased. Future research needs to focus on developing AI models which are prospectively validated and ultimately integrated into clinical workflows.

LEVEL OF EVIDENCE

2A.

Brave new world: expanding home care in stem cell transplantation and advanced therapies with new technologies

Hematopoietic stem cell transplantation and cell therapies like CAR-T are costly, complex therapeutic procedures. Outpatient models, including at-home transplantation, have been developed, resulting in similar survival results, reduced costs, and increased patient satisfaction. The complexity and safety of the process can be addressed with various emerging technologies (artificial intelligence, wearable sensors, point-of-care analytical devices, drones, virtual assistants) that allow continuous patient monitoring and improved decision-making processes. Patients, caregivers, and staff can also benefit from improved training with simulation or virtual reality. However, many technical, operational, and above all, ethical concerns need to be addressed. Finally, outpatient or at-home hematopoietic transplantation or CAR-T therapy creates a different, integrated operative system that must be planned, designed, and carefully adapted to the patient's characteristics and distance from the hospital. Patients, clinicians, and their clinical environments can benefit from technically improved at-home transplantation.

An artificial intelligence-driven predictive model for pediatric allogeneic hematopoietic stem cell transplantation using clinical variables

BACKGROUND

Hematopoietic stem cell transplantation (HSCT) is a procedure with high morbidity and mortality. Identifying patients for maximum benefit and risk assessment is crucial in the decision-making process. This has led to the development of predictive risk models for HSCT in adults, which have limitations when applied to pediatric population. Our goal was to develop an automatic learning algorithm to predict survival in children with malignant disorders undergoing HSCT.

METHODS

We studied allogenic HSCTs performed on children with malignant disorders at a third-level hospital between 1991 and 2021. Survival was analyzed using the Kaplan-Meier method, log-rank test for the univariate analysis, and Cox regression for the multivariate analysis. A prognostic index was constructed based on these findings. Lastly, we constructed a predictive model using a random forest algorithm to forecast 1-year survival after HSCT.

RESULTS

We analyzed 229 HSCTs in 201 patients with a median follow-up of 1.64 years. Variables that impacted on the multivariate analysis were older age (hazard ratio [HR] 1.40, 95% confidence interval [CI] 1.12-1.76, p = .003), oldest period of HSCT (HR 0.46, 95% CI 0.29-0.73, p < .001), and mismatched donor (HR 2.65, 95% CI 1.51-4.65, p = .001). Our prognostic index was associated with 3-year overall survival (OS; p < .001). A random forest was developed using as variables: diagnosis, age, year of HSCT, time from diagnosis to HSCT, disease stage, donor type, and conditioning. This achieved 72% accuracy in predicting 1-year OS.

CONCLUSIONS

Our index and random forest was effective in predicting 1-year survival. However, further validation in diverse populations is necessary to establish their generalizability.

Machine learning applications and challenges in graft-versus-host disease: a scoping review

PURPOSE OF REVIEW

This review delves into the potential of artificial intelligence (AI), particularly machine learning (ML), in enhancing graft-versus-host disease (GVHD) risk assessment, diagnosis, and personalized treatment.

RECENT FINDINGS

Recent studies have demonstrated the superiority of ML algorithms over traditional multivariate statistical models in donor selection for allogeneic hematopoietic stem cell transplantation. ML has recently enabled dynamic risk assessment by modeling time-series data, an upgrade from the static, "snapshot" assessment of patients that conventional statistical models and older ML algorithms offer. Regarding diagnosis, a deep learning model, a subset of ML, can accurately identify skin segments affected with chronic GVHD with satisfactory results. ML methods such as Q-learning and deep reinforcement learning have been utilized to develop adaptive treatment strategies (ATS) for the personalized prevention and treatment of acute and chronic GVHD.

SUMMARY

To capitalize on these promising advancements, there is a need for large-scale, multicenter collaborations to develop generalizable ML models. Furthermore, addressing pertinent issues such as the implementation of stringent ethical guidelines is crucial before the widespread introduction of AI into GVHD care.

A pilot study of implication of machine learning for relapse prediction after allogeneic stem cell transplantation in adults with Ph-positive acute lymphoblastic leukemia

The posttransplant relapse in Ph-positive ALL increases the risk of death. There is an unmet need for instruments to predict the risk of relapse and plan prophylaxis. In this study, we analyzed posttransplant data by machine learning algorithms. Seventy-four Ph-positive ALL patients with a median age of 30 (range 18-55) years who previously underwent allo-HSCT, were retrospectively enrolled. Ninety-three percent of patients received prophylactic/preemptive TKIs after allo-HSCT. The values of the BCR::ABL1 level at serial assessments and over variables were collected in specified intervals after allo-HSCT. They were used to model relapse risk with several machine-learning approaches. GBM proved superior to the other algorithms and provided a maximal AUC score of 0.91. BCR::ABL1 level before and after allo-HSCT, prediction moment, and chronic GvHD had the highest value in the model. It was shown that after Day + 100, both error rates do not exceed 22%, while before D + 100, the model fails to make accurate predictions. As a result, we determined BCR::ABL1 levels at which the relapse risk remains low. Thus, the current BCR::ABL1 level less than 0.06% in patients with chronic GvHD predicts low risk of relapse. At the same time, patients without chronic GVHD after allo-HSCT should be classified as high risk with any level of BCR::ABL1. GBM model with posttransplant laboratory values of BCR::ABL1 provides a high prediction of relapse after allo-HSCT in the era of TKIs prophylaxis. Validation of this approach is warranted.

Machine Learning for the Prediction of Survival Post-Allogeneic Hematopoietic Cell Transplantation: A Single-Center Experience

INTRODUCTION

Prediction of outcomes following allogeneic hematopoietic cell transplantation (HCT) remains a major challenge. Machine learning (ML) is a computational procedure that may facilitate the generation of HCT prediction models. We sought to investigate the prognostic potential of multiple ML algorithms when applied to a large single-center allogeneic HCT database.

METHODS

Our registry included 2,697 patients that underwent allogeneic HCT from January 1976 to December 2017. 45 pretransplant baseline variables were included in the predictive assessment of each ML algorithm on overall survival (OS) as determined by area under the curve (AUC). Pretransplant variables used in the EBMT ML study (Shouval et al., 2015) were used as a benchmark for comparison.

RESULTS

On the entire dataset, the random forest (RF) algorithm performed best (AUC 0.71 ± 0.04) compared to the second-best model, logistic regression (LR) (AUC = 0.69 ± 0.04) (p < 0.001). Both algorithms demonstrated improved AUC scores using all 45 variables compared to the limited variables examined by the EBMT study. Survival at 100 days post-HCT using RF on the full dataset discriminated patients into different prognostic groups with different 2-year OS (p < 0.0001). We then examined the ML methods that allow for significant individual variable identification, including LR and RF, and identified matched related donors (HR = 0.49, p < 0.0001), increasing TBI dose (HR = 1.60, p = 0.006), increasing recipient age (HR = 1.92, p < 0.0001), higher baseline Hb (HR = 0.59, p = 0.0002), and increased baseline FEV1 (HR = 0.73, p = 0.02), among others.

CONCLUSION

The application of multiple ML techniques on single-center allogeneic HCT databases warrants further investigation and may provide a useful tool to identify variables with prognostic potential.

Children's Oncology Group's 2023 blueprint for research: Cellular therapy and stem cell transplantation

Since the publication of the last Cellular Therapy and Stem Cell Transplant blueprint in 2013, Children's Oncology Group cellular therapy-based trials advanced the field and created new standards of care across a wide spectrum of pediatric cancer diagnoses. Key findings include that tandem autologous transplant improved survival for patients with neuroblastoma and atypical teratoid/rhabdoid brain tumors, one umbilical cord blood (UCB) donor was safer than two UCB donors, killer immunoglobulin receptor (KIR) mismatched donors did not improve survival for pediatric acute myeloid leukemia when in vivo T-cell depletion is used, and the depth of remission as measured by next-generation sequencing-based minimal residual disease assessment pretransplant was the best predictor of relapse for acute lymphoblastic leukemia. Plans for the next decade include optimizing donor selection for transplants for acute leukemia/myelodysplastic syndrome, using novel engineered cellular therapies to target a wide array of malignancies, and developing better treatments for cellular therapy toxicities such as viral infections and graft-vs-host disease.

The Critical Exploration into Current Evidence behind the Role of the Nutritional Support in Adult Patients Who Undergo Haematogenic Stem Cell Transplantation

Haematopoietic stem cell transplantation (HSCT) is a treatment option for many haematological conditions in patients of all ages. Nutritional support is important at each stage of treatment, but particular nutritional needs and dictated support occur during the preparatory (conditioning regimen) and post-transplant periods. Patients may require nutritional treatment by the enteral or parenteral route. The quantitative and qualitative composition of meals may change. Vitamin requirements, including vitamin D and vitamin C, might also be different. An adequately composed diet, adapted to the needs of the patient, may influence the occurrence of complications such as graft-versus-host disease (GvHD), gastrointestinal disorders, infections, and reduced survival time. Haematological diseases as well as transplantation can negatively affect the intestinal flora, with negative consequences in the form of mucosal inflammation and disorders of a functional nature. Currently, aspects related to nutrition are crucial in the care of patients after HSCT, and numerous studies, including randomized trials on these aspects, are being conducted. This study serves the critical analysis of current scientific evidence regarding nutritional support for patients after HSCT.

Artificial intelligence and its impact on the domains of universal health coverage, health emergencies and health promotion: An overview of systematic reviews

BACKGROUND

Artificial intelligence is fueling a new revolution in medicine and in the healthcare sector. Despite the growing evidence on the benefits of artificial intelligence there are several aspects that limit the measure of its impact in people's health. It is necessary to assess the current status on the application of AI towards the improvement of people's health in the domains defined by WHO's Thirteenth General Programme of Work (GPW13) and the European Programme of Work (EPW), to inform about trends, gaps, opportunities, and challenges.

OBJECTIVE

To perform a systematic overview of systematic reviews on the application of artificial intelligence in the people's health domains as defined in the GPW13 and provide a comprehensive and updated map on the application specialties of artificial intelligence in terms of methodologies, algorithms, data sources, outcomes, predictors, performance, and methodological quality.

METHODS

A systematic search in MEDLINE, EMBASE, Cochrane and IEEEXplore was conducted between January 2015 and June 2021 to collect systematic reviews using a combination of keywords related to the domains of universal health coverage, health emergencies protection, and better health and wellbeing as defined by the WHO's PGW13 and EPW. Eligibility criteria was based on methodological quality and the inclusion of practical implementation of artificial intelligence. Records were classified and labeled using ICD-11 categories into the domains of the GPW13. Descriptors related to the area of implementation, type of modeling, data entities, outcomes and implementation on care delivery were extracted using a structured form and methodological aspects of the included reviews studies was assessed using the AMSTAR checklist.

RESULTS

The search strategy resulted in the screening of 815 systematic reviews from which 203 were assessed for eligibility and 129 were included in the review. The most predominant domain for artificial intelligence applications was Universal Health Coverage (N = 98) followed by Health Emergencies (N = 16) and Better Health and Wellbeing (N = 15). Neoplasms area on Universal Health Coverage was the disease area featuring most of the applications (21.7 %, N = 28). The reviews featured analytics primarily over both public and private data sources (67.44 %, N = 87). The most used type of data was medical imaging (31.8 %, N = 41) and predictors based on regions of interest and clinical data. The most prominent subdomain of Artificial Intelligence was Machine Learning (43.4 %, N = 56), in which Support Vector Machine method was predominant (20.9 %, N = 27). Regarding the purpose, the application of Artificial Intelligence I is focused on the prediction of the diseases (36.4 %, N = 47). With respect to the validation, more than a half of the reviews (54.3 %, N = 70) did not report a validation procedure and, whenever available, the main performance indicator was the accuracy (28.7 %, N = 37). According to the methodological quality assessment, a third of the reviews (34.9 %, N = 45) implemented methods for analysis the risk of bias and the overall AMSTAR score below was 5 (4.01 ± 1.93) on all the included systematic reviews.

CONCLUSION

Artificial intelligence is being used for disease modelling, diagnose, classification and prediction in the three domains of GPW13. However, the evidence is often limited to laboratory and the level of adoption is largely unbalanced between ICD-11 categoriesand diseases. Data availability is a determinant factor on the developmental stage of artificial intelligence applications. Most of the reviewed studies show a poor methodological quality and are at high risk of bias, which limits the reproducibility of the results and the reliability of translating these applications to real clinical scenarios. The analyzed papers show results only in laboratory and testing scenarios and not in clinical trials nor case studies, limiting the supporting evidence to transfer artificial intelligence to actual care delivery.

Survival Prediction of Children Undergoing Hematopoietic Stem Cell Transplantation Using Different Machine Learning Classifiers by Performing Chi-Square Test and Hyperparameter Optimization: A Retrospective Analysis

Bone marrow transplant (BMT) is an effective surgical treatment for bone marrow-related disorders. However, several associated risk factors can impair long-term survival after BMT. Machine learning (ML) technologies have been proven useful in survival prediction of BMT receivers along with the influences that limit their resilience. In this study, an efficient classification model predicting the survival of children undergoing BMT is presented using a public dataset. Several supervised ML methods were investigated in this regard with an 80-20 train-test split ratio. To ensure prediction with minimal time and resources, only the top 11 out of the 59 dataset features were considered using Chi-square feature selection method. Furthermore, hyperparameter optimization (HPO) using the grid search cross-validation (GSCV) technique was adopted to increase the accuracy of prediction. Four experiments were conducted utilizing a combination of default and optimized hyperparameters on the original and reduced datasets. Our investigation revealed that the top 11 features of HPO had the same prediction accuracy (94.73%) as the entire dataset with default parameters, however, requiring minimal time and resources. Hence, the proposed approach may aid in the development of a computer-aided diagnostic system with satisfactory accuracy and minimal computation time by utilizing medical data records.

Application of Machine Learning Methods for Epilepsy Risk Ranking in Patients with Hematopoietic Malignancies Using

Machine learning methods to predict the risk of epilepsy, including vascular epilepsy, in oncohematological patients are currently considered promising. These methods are used in research to predict pharmacoresistant epilepsy and surgical treatment outcomes in order to determine the epileptogenic zone and functional neural systems in patients with epilepsy, as well as to develop new approaches to classification and perform other tasks. This paper presents the results of applying machine learning to analyzing data and developing diagnostic models of epilepsy in oncohematological and cardiovascular patients. This study contributes to solving the problem of often unjustified diagnosis of primary epilepsy in patients with oncohematological or cardiovascular pathology, prescribing antiseizure drugs to patients with single seizure syndromes without finding a disease associated with these cases. We analyzed the hospital database of the V.A. Almazov Scientific Research Center of the Ministry of Health of Russia. The study included 66,723 treatment episodes of patients with vascular diseases (I10–I15, I61–I69, I20–I25) and 16,383 episodes with malignant neoplasms of lymphoid, hematopoietic, and related tissues (C81–C96 according to ICD-10) for the period from 2010 to 2020. Data analysis and model calculations indicate that the best result was shown by gradient boosting with mean accuracy cross-validation score = 0.96. f1-score = 98, weighted avg precision = 93, recall = 96, f1-score = 94. The highest correlation coefficient for G40 and different clinical conditions was achieved with fibrillation, hypertension, stenosis or occlusion of the precerebral arteries (0.16), cerebral sinus thrombosis (0.089), arterial hypertension (0.17), age (0.03), non-traumatic intracranial hemorrhage (0.07), atrial fibrillation (0.05), delta absolute neutrophil count (0.05), platelet count at discharge (0.04), transfusion volume for stem cell transplantation (0.023). From the clinical point of view, the identified differences in the importance of predictors in a broader patient model are consistent with a practical algorithm for organic brain damage. Atrial fibrillation is one of the leading factors in the development of both ischemic and hemorrhagic strokes. At the same time, brain infarction can be accompanied both by the development of epileptic seizures in the acute period and by unprovoked epileptic seizures and development of epilepsy in the early recovery and in a longer period. In addition, a microembolism of the left heart chambers can lead to multiple microfocal lesions of the brain, which is one of the pathogenetic aspects of epilepsy in elderly patients. The presence of precordial fibrillation requires anticoagulant therapy, the use of which increases the risk of both spontaneous and traumatic intracranial hemorrhage.

Gaps and Opportunities of Artificial Intelligence Applications for Pediatric Oncology in European Research: A Systematic Review of Reviews and a Bibliometric Analysis

The application of artificial intelligence (AI) systems is emerging in many fields in recent years, due to the increased computing power available at lower cost. Although its applications in various branches of medicine, such as pediatric oncology, are many and promising, its use is still in an embryonic stage. The aim of this paper is to provide an overview of the state of the art regarding the AI application in pediatric oncology, through a systematic review of systematic reviews, and to analyze current trends in Europe, through a bibliometric analysis of publications written by European authors. Among 330 records found, 25 were included in the systematic review. All papers have been published since 2017, demonstrating only recent attention to this field. The total number of studies included in the selected reviews was 674, with a third including an author with a European affiliation. In bibliometric analysis, 304 out of the 978 records found were included. Similarly, the number of publications began to dramatically increase from 2017. Most explored AI applications regard the use of diagnostic images, particularly radiomics, as well as the group of neoplasms most involved are the central nervous system tumors. No evidence was found regarding the use of AI for process mining, clinical pathway modeling, or computer interpreted guidelines to improve the healthcare process. No robust evidence is yet available in any of the domains investigated by systematic reviews. However, the scientific production in Europe is significant and consistent with the topics covered in systematic reviews at the global level. The use of AI in pediatric oncology is developing rapidly with promising results, but numerous gaps and challenges persist to validate its utilization in clinical practice. An important limitation is the need for large datasets for training algorithms, calling for international collaborative studies.

Prediction and recommendation by machine learning through repetitive internal validation for hepatic veno-occlusive disease/sinusoidal obstruction syndrome and early death after allogeneic hematopoietic cell transplantation

Using traditional statistical methods, we previously analyzed the risk factors and treatment outcomes of veno-occlusive disease/sinusoidal obstruction syndrome (VOD/SOS) after allogeneic hematopoietic cell transplantation. Within the same cohort, we applied machine learning to create prediction and recommendation models. We analyzed 2572 transplants using eXtreme Gradient Boosting (XGBoost) to predict post-transplant VOD/SOS and early death. Using the XGBoost and SHapley Additive exPlanations (SHAP), we found influential factors and devised recommendation models, which were internally verified by repetitive ten-fold cross-validation. SHAP values suggested that gender, busulfan dosage, age, forced expiratory volume, and Disease Risk Index were significant factors for VOD/SOS. The areas under the receiver operating characteristic curves and the areas under the precision-recall curve of the models were 0.740, 0.144 for all VOD/SOS, 0.793, 0.793 for severe to very severe VOD/SOS, and 0.746, 0.304 for early death. According to our single feature recommendation, following the busulfan dosage was the most effective for preventing VOD/SOS. The recommendation method for six adjustable feature sets was also validated, and a subgroup corresponding to five to six features showed significant preventive power for VOD/SOS and early death. Our personalized treatment set recommendation showed reproducibility in repetitive internal validation, but large external cohorts should prospectively validate our model.

Dynamic forecasting of severe acute graft-versus-host disease after transplantation

Forecasting of severe acute graft-versus-host disease (aGVHD) after transplantation is a challenging 'large p, small n' problem that suffers from nonuniform data sampling. We propose a dynamic probabilistic algorithm, daGOAT, that accommodates sampling heterogeneity, integrates multidimensional clinical data and continuously updates the daily risk score for severe aGVHD onset within a two-week moving window. In the studied cohorts, the cross-validated area under the receiver operator characteristic curve (AUROC) of daGOAT rose steadily after transplantation and peaked at ≥0.78 in both the adult and pediatric cohorts, outperforming the two-biomarker MAGIC score, three-biomarker Ann Arbor score, peri-transplantation features-based models and XGBoost. Simulation experiments indicated that the daGOAT algorithm is well suited for short time-series scenarios where the underlying process for event generation is smooth, multidimensional and where there are frequent and irregular data missing. daGOAT's broader utility was demonstrated by performance testing on a remotely different task, that is, prediction of imminent human postural change based on smartphone inertial sensor time-series data.

Recent Development of Graphene Based Electrochemical Sensor for Detecting Hematological Malignancies-Associated Biomarkers: A Mini-Review

Hematologic malignancies are a group of malignant diseases of the hematologic system that seriously endanger human health, mainly involving bone marrow, blood and lymphatic tissues. However, among the available treatments for malignant hematologic diseases, low detection rates and high recurrence rates are major problems in the treatment process. The quantitative detection of hematologic malignancies-related biomarkers is the key to refine the pathological typing of the disease to implement targeted therapy and thus improve the prognosis. In recent years, bioelectrochemical methods for tumor cell and blood detection have attracted the attention of an increasing number of scientists. The development of biosensor technology, nanotechnology, probe technology, and lab-on-a-chip technology has greatly facilitated the development of bioelectrochemical studies of cells, especially for blood and cell-based assays and drug resistance differentiation. To improve the sensitivity of detection, graphene is often used in the design of electrochemical sensors. This mini-review provides an overview of the types of hematological malignancies-associated biomarkers and their detection based on graphene assisted electrochemical sensors.

Monitoring beliefs and physiological measures in students at risk for COVID-19 using wearable sensors and smartphone technology: Protocol for a mobile health study

BACKGROUND

The COVID-19 pandemic has impacted lives significantly and greatly affected an already vulnerable population, college students, in relation to mental health and public safety. Social distancing and isolation have brought about challenges to student's mental health. Mobile health apps and wearable sensors may help to monitor students at risk for COVID-19 and support their mental well-being.

OBJECTIVE

Through the use of a wearable sensor and smartphone-based survey completion, this study aimed to monitor students at risk for COVID-19.

METHODS

We conducted a prospective study of students, undergraduate and graduate, at a public university in the Midwest. Students were instructed to download the Fitbit, Social Rhythms, and Roadmap 2.0 apps onto their personal mobile devices (Android or iOS). Subjects consented to provide up to 10 saliva samples during the study period. Surveys were administered through the Roadmap 2.0 app at five timepoints - at baseline, 1-month later, 2-months later, 3-months later, and at study completion. The surveys gathered information regarding demographics, COVID-19 diagnoses and symptoms, and mental health resilience, with the aim of documenting the impact of COVID-19 on the college student population.

RESULTS

This study enrolled 2,158 college students between September 2020 and January 2021. Subjects are currently being followed on-study for one academic year. Data collection and analysis are ongoing.

CONCLUSIONS

This study examined student health and well-being during the COVID-19 pandemic. It also assessed the feasibility of wearable sensor use and survey completion in a college student population, which may inform the role of our mobile health tools on student health and well-being. Finally, using wearable sensor data, biospecimen collection, and self-reported COVID-19 diagnosis, our results may provide key data towards the development of a model for the early prediction and detection of COVID-19.

CLINICALTRIAL

ClinicalTrials.gov NCT04766788.

The Contemporary Approach to CALR-Positive Myeloproliferative Neoplasms

CALR mutations are a revolutionary discovery and represent an important hallmark of myeloproliferative neoplasms (MPN), especially essential thrombocythemia and primary myelofibrosis. To date, several CALR mutations were identified, with only frameshift mutations linked to the diseased phenotype. It is of diagnostic and prognostic importance to properly define the type of CALR mutation and subclassify it according to its structural similarities to the classical mutations, a 52-bp deletion (type 1 mutation) and a 5-bp insertion (type 2 mutation), using a statistical approximation algorithm (AGADIR). Today, the knowledge on the pathogenesis of CALR-positive MPN is expanding and several cellular mechanisms have been recognized that finally cause a clonal hematopoietic expansion. In this review, we discuss the current basis of the cellular effects of CALR mutants and the understanding of its implementation in the current diagnostic laboratorial and medical practice. Different methods of CALR detection are explained and a diagnostic algorithm is shown that aids in the approach to CALR-positive MPN. Finally, contemporary methods joining artificial intelligence in accordance with molecular-genetic biomarkers in the approach to MPN are presented.