A Systematic Review of Machine Learning Techniques in Hematopoietic Stem Cell Transplantation (HSCT).
Ontology highlight
ABSTRACT:
SUBMITTER: Gupta V
PROVIDER: S-EPMC7663237 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:BackgroundMachine learning has been used to develop predictive models to support clinicians in making better and more reliable decisions. The high volume of collected data in the lung transplant process makes it possible to extract hidden patterns by applying machine learning methods. Our study aims to investigate the application of machine learning methods in lung transplantation.MethodA systematic search was conducted in five electronic databases from January 2000 to June 2022. Then, the title, abstracts, and full text of extracted articles were screened based on the PRISMA checklist. Then, eligible articles were selected according to inclusion criteria. The information regarding developed models was extracted from reviewed articles using a data extraction sheet.ResultsSearches yielded 414 citations. Of them, 136 studies were excluded after the title and abstract screening. Finally, 16 articles were determined as eligible studies that met our inclusion criteria. The objectives of eligible articles are classified into eight main categories. The applied machine learning methods include the Support vector machine (SVM) (n = 5, 31.25%) technique, logistic regression (n = 4, 25%), Random Forests (RF) (n = 4, 25%), Bayesian network (BN) (n = 3, 18.75%), linear regression (LR) (n = 3, 18.75%), Decision Tree (DT) (n = 3, 18.75%), neural networks (n = 3, 18.75%), Markov Model (n = 1, 6.25%), KNN (n = 1, 6.25%), K-means (n = 1, 6.25%), Gradient Boosting trees (XGBoost) (n = 1, 6.25%), and Convolutional Neural Network (CNN) (n = 1, 6.25%). Most studies (n = 11) employed more than one machine learning technique or combination of different techniques to make their models. The data obtained from pulmonary function tests were the most used as input variables in predictive model development. Most studies (n = 10) used only post-transplant patient information to develop their models. Also, UNOS was recognized as the most desirable data source in the reviewed articles. In most cases, clinicians succeeded to predict acute diseases incidence after lung transplantation (n = 4) or estimate survival rate (n = 4) by developing machine learning models.ConclusionThe outcomes of these developed prediction models could aid clinicians to make better and more reliable decisions by extracting new knowledge from the huge volume of lung transplantation data.
| S-EPMC9784000 | biostudies-literature
Project description:Acute myeloid leukemia (AML) is the most common type of acute leukemia in adults. Recent advances in understanding its molecular basis have opened the way to new therapeutic strategies, including targeted therapies. However, despite an improvement in prognosis it has been documented in recent years (especially in younger patients) that allogenic hematopoietic stem cell transplantation (allo-HSCT) remains the only curative treatment in AML and the first therapeutic option for high-risk patients. After allo-HSCT, relapse is still a major complication, and is observed in about 50% of patients. Current evidence suggests that relapse is not due to clonal evolution, but instead to the ability of the AML cell population to escape immune control by a variety of mechanisms including the altered expression of HLA-molecules, production of anti-inflammatory cytokines, relevant metabolic changes and expression of immune checkpoint (ICP) inhibitors capable of "switching-off" the immune response against leukemic cells. Here, we review the main mechanisms of immune escape and identify potential strategies to overcome these mechanisms.
| S-EPMC7016529 | biostudies-literature
Project description:Security vulnerabilities play a vital role in network security system. Fuzzing technology is widely used as a vulnerability discovery technology to reduce damage in advance. However, traditional fuzz testing faces many challenges, such as how to mutate input seed files, how to increase code coverage, and how to bypass the format verification effectively. Therefore machine learning techniques have been introduced as a new method into fuzz testing to alleviate these challenges. This paper reviews the research progress of using machine learning techniques for fuzz testing in recent years, analyzes how machine learning improves the fuzzing process and results, and sheds light on future work in fuzzing. Firstly, this paper discusses the reasons why machine learning techniques can be used for fuzzing scenarios and identifies five different stages in which machine learning has been used. Then this paper systematically studies machine learning-based fuzzing models from five dimensions of selection of machine learning algorithms, pre-processing methods, datasets, evaluation metrics, and hyperparameters setting. Secondly, this paper assesses the performance of the machine learning techniques in existing research for fuzz testing. The results of the evaluation prove that machine learning techniques have an acceptable capability of prediction for fuzzing. Finally, the capability of discovering vulnerabilities both traditional fuzzers and machine learning-based fuzzers is analyzed. The results depict that the introduction of machine learning techniques can improve the performance of fuzzing. We hope to provide researchers with a systematic and more in-depth understanding of fuzzing based on machine learning techniques and provide some references for this field through analysis and summarization of multiple dimensions.
| S-EPMC7433880 | biostudies-literature
Project description:Previous adolescent and young adult (AYA) research suggests patients undergoing hematopoietic stem cell transplantation (HSCT) experience severe physiological stress. The goal of this study was to identify unmet needs, interests, and preferences for mindfulness to inform the development of a mindfulness-based stress reduction intervention. Semi-structured interviews were conducted at three time points: prior to (n = 20), immediately after (n = 13), and three months post HSCT (n = 16) in the same AYA patients. Interviews assessed stress reduction strategies used, interest in mindfulness, and current quality of life. Three major thematic categories emerged from interview data across all time points: Concerns, Coping Strategies, and Mindfulness Activities. Prior to HSCT, two additional themes emerged including: Hope for the Future and Getting the Body Moving-Physical Activity. Most participants were not familiar with the term "mindfulness" prior to HSCT; but after being provided the definition of mindfulness, participants expressed interest in an online mindfulness-based intervention (e.g., ZOOM), stating: "I think it's necessary" and "It would definitely be useful". Participants suggested an intervention immediately following HSCT may decrease isolation concerns stating: "[in the hospital] You kind of feel like a hamster in a cage" and "you obviously have a lot of time to just be sitting by yourself in a hospital room". The results suggest that a mindfulness-based online intervention is of interest to AYA HSCT patients and may be beneficial in decreasing physiological stress and improving quality of life.
| S-EPMC9179916 | biostudies-literature
Project description:Allogeneic stem cell transplantation (allo-SCT) outcomes in patients with Hodgkin lymphoma (HL) remain poorly defined. We performed a meta-analysis of allo-SCT studies in HL patients. The primary endpoints were 6-month, 1-year, 2-year and 3-year relapse-free survival (RFS) and overall survival (OS). A total of 42 reports (1850 patients) was included. The pooled estimates (95% confidence interval) for 6-month, 1-year, 2-year and 3-year RFS were 77 (59-91)%, 50 (42-57)%, 37 (31-43)% and 31 (25-37)%, respectively. The corresponding numbers for OS were 83 (75-91)%, 68 (62-74)%, 58 (52-64)% and 50 (41-58)%, respectively. There was statistical heterogeneity among studies in all outcomes. In meta-regression, accrual initiation year in 2000 or later was associated with higher 6-month (P=0.012) and 1-year OS (P=0.046), and pre-SCT remission with higher 2-year OS (P=0.047) and 1-year RFS (P=0.016). In conclusion, outcomes of allo-SCT in HL have improved over time, with 5-10% lower non-relapse mortality and relapse rates, and 15-20% higher RFS and OS in studies that initiated accrual in 2000 or later compared with earlier studies. However, there is no apparent survival plateau, demonstrating the need to improve on current allo-SCT strategies in relapsed/refractory HL.
| S-EPMC5092068 | biostudies-literature
Project description:IntroductionIn 1995, the use of autologous hematopoietic stem-cell transplantation (AHSCT), which was previously used to treat hematological tumors, was introduced for severe autoimmune diseases such as multiple sclerosis (MS). AHSCT has proven its safety over the past few years due to technical advances and careful patient selection in transplant centers. While most studies have reported that AHSCT led to decreased Expanded Disability Status Scale (EDSS) scores, some patients reported increased EDSS scores following the procedure. Given the contradictory results, we aimed to conduct a comprehensive systematic review and meta-analysis to investigate the efficacy and safety of AHSCT.MethodsPubMed, Web of Science, and Scopus were searched in March 2022 using a predefined search strategy. We included cohort studies, clinical trials, case-control studies, and case series that investigated the efficacy or safety of AHSCT in patients with MS. PICO in the present study was defined as follows: problem or study population (P): patients with MS; intervention (I): AHSCT; comparison (C): none; outcome (O): efficacy and safety.ResultsAfter a two-step review process, 50 studies with a total of 4831 patients with MS were included in our study. Our analysis showed a significant decrease in EDSS score after treatment (standardized mean difference [SMD]: -0.48, 95% CI -0.75, -0.22). Moreover, the annualized relapse rate was also significantly reduced after AHSCT compared to the pretreatment period (SMD: -1.58, 95% CI -2.34, -0.78). The pooled estimate of progression-free survival after treatment was 73% (95% CI 69%, 77). Furthermore, 81% of patients with MS who received AHSCT remained relapse-free (95% CI 76%, 86%). Investigating event-free survival, which reflects the absence of any disease-related event, showed a pooled estimate of 63% (95% CI 54%, 73%). Also, the MRI activity-free survival was 89% (95% CI 84%) among included studies with low heterogeneity. New MRI lesions seem to appear in nearly 8% of patients who underwent AHSCT (95% CI 4%, 12%). Our meta-analysis showed that 68% of patients with MS experience no evidence of disease activity (NEDA) after AHSCT (95% CI 59%, 77). The overall survival after transplantation was 94% (95% CI 91%, 96%). In addition, 4% of patients died from transplant-related causes (95% CI 2%, 6%).ConclusionCurrent data encourages a broader application of AHSCT for treating patients with MS while still considering proper patient selection and transplant methods. In addition, with increasing knowledge and expertise in the field of stem-cell therapy, AHSCT has become a safer treatment approach for MS.
| S-EPMC9333355 | biostudies-literature
Project description:ObjectivesThis systematic review aimed to assess the performance and clinical feasibility of machine learning (ML) algorithms in prediction of in-hospital mortality for medical patients using vital signs at emergency departments (EDs).DesignA systematic review was performed.SettingThe databases including Medline (PubMed), Scopus and Embase (Ovid) were searched between 2010 and 2021, to extract published articles in English, describing ML-based models utilising vital sign variables to predict in-hospital mortality for patients admitted at EDs. Critical appraisal and data extraction for systematic reviews of prediction modelling studies checklist was used for study planning and data extraction. The risk of bias for included papers was assessed using the prediction risk of bias assessment tool.ParticipantsAdmitted patients to the ED.Main outcome measureIn-hospital mortality.ResultsFifteen articles were included in the final review. We found that eight models including logistic regression, decision tree, K-nearest neighbours, support vector machine, gradient boosting, random forest, artificial neural networks and deep neural networks have been applied in this domain. Most studies failed to report essential main analysis steps such as data preprocessing and handling missing values. Fourteen included studies had a high risk of bias in the statistical analysis part, which could lead to poor performance in practice. Although the main aim of all studies was developing a predictive model for mortality, nine articles did not provide a time horizon for the prediction.ConclusionThis review provided an updated overview of the state-of-the-art and revealed research gaps; based on these, we provide eight recommendations for future studies to make the use of ML more feasible in practice. By following these recommendations, we expect to see more robust ML models applied in the future to help clinicians identify patient deterioration earlier.
| S-EPMC8565537 | biostudies-literature
Project description:Skin lesions are essential for the early detection and management of a number of dermatological disorders. Learning-based methods for skin lesion analysis have drawn much attention lately because of improvements in computer vision and machine learning techniques. A review of the most-recent methods for skin lesion classification, segmentation, and detection is presented in this survey paper. The significance of skin lesion analysis in healthcare and the difficulties of physical inspection are discussed in this survey paper. The review of state-of-the-art papers targeting skin lesion classification is then covered in depth with the goal of correctly identifying the type of skin lesion from dermoscopic, macroscopic, and other lesion image formats. The contribution and limitations of various techniques used in the selected study papers, including deep learning architectures and conventional machine learning methods, are examined. The survey then looks into study papers focused on skin lesion segmentation and detection techniques that aimed to identify the precise borders of skin lesions and classify them accordingly. These techniques make it easier to conduct subsequent analyses and allow for precise measurements and quantitative evaluations. The survey paper discusses well-known segmentation algorithms, including deep-learning-based, graph-based, and region-based ones. The difficulties, datasets, and evaluation metrics particular to skin lesion segmentation are also discussed. Throughout the survey, notable datasets, benchmark challenges, and evaluation metrics relevant to skin lesion analysis are highlighted, providing a comprehensive overview of the field. The paper concludes with a summary of the major trends, challenges, and potential future directions in skin lesion classification, segmentation, and detection, aiming to inspire further advancements in this critical domain of dermatological research.
| S-EPMC10572538 | biostudies-literature
Project description:AbstractSerial prognostic evaluation after allogeneic hematopoietic cell transplantation (allo-HCT) might help identify patients at high risk of lethal organ dysfunction. Current prediction algorithms based on models that do not incorporate changes to patients' clinical condition after allo-HCT have limited predictive ability. We developed and validated a robust risk-prediction algorithm to predict short- and long-term survival after allo-HCT in pediatric patients that includes baseline biological variables and changes in the patients' clinical status after allo-HCT. The model was developed using clinical data from children and young adults treated at a single academic quaternary-care referral center. The model was created using a randomly split training data set (70% of the cohort), internally validated (remaining 30% of the cohort) and then externally validated on patient data from another tertiary-care referral center. Repeated clinical measurements performed from 30 days before allo-HCT to 30 days afterwards were extracted from the electronic medical record and incorporated into the model to predict survival at 100 days, 1 year, and 2 years after allo-HCT. Naïve-Bayes machine learning models incorporating longitudinal data were significantly better than models constructed from baseline variables alone at predicting whether patients would be alive or deceased at the given time points. This proof-of-concept study demonstrates that unlike traditional prognostic tools that use fixed variables for risk assessment, incorporating dynamic variability using clinical and laboratory data improves the prediction of mortality in patients undergoing allo-HCT.
| S-EPMC10844815 | biostudies-literature
Project description:BackgroundThe population of survivors following allogeneic HSCT continues to increase, and yet their experiences of recovery and long-term survivorship have not been fully characterized. This paper presents a study protocol examining over time the functional status, psychosocial adjustment, health-related quality of life, and symptom experience of survivors who have undergone allogeneic transplantation. The aims of the study are to: 1) explore the patterns of change in these health outcomes during the survivorship phase; 2) characterize subgroups of survivors experiencing adverse outcomes; and 3) examine relationships among outcomes and demographic and clinical factors (such as age, graft-versus-host disease (GVHD), and disease relapse).MethodsIn this longitudinal observational study, adults who survive a minimum of 3 years from date of allogeneic transplantation complete a series of questionnaires annually. Demographic and clinical data are collected along with a series of patient-reported outcome measures, specifically: 1) Medical Outcomes Study SF- 36; 2) Functional Assessment of Chronic Illness Therapy (FACIT) - General, 3) FACIT-Fatigue; 4) FACIT- Spiritual; 5) Psychosocial Adjustment to Illness Scale; 6) Rotterdam Symptom Checklist-Revised; and 7) Pittsburgh Sleep Quality Index.ConclusionsThis study will provide multidimensional patient-reported outcomes data to expand the understanding of the survivorship experience across the trajectory of allogeneic transplantation recovery. There are a number of inherent challenges in recruiting and retaining a diverse and representative sample of long-term transplant survivors. Study results will contribute to an understanding of outcomes experienced by transplant survivors, including those with chronic GVHD, malignant disease relapse, and other late effects following allogeneic transplantation.Trial registrationClinicalTrials.gov: NCT00128960.
| S-EPMC3101119 | biostudies-literature