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

Computational and Mathematical Methods in Medicine, Год журнала: 2022, Номер 2022, С. 1 - 14

Опубликована: Сен. 25, 2022

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 prediction of BMT receivers along with the influences that limit their resilience. In this study, efficient classification model predicting children undergoing presented using a public dataset. Several supervised ML methods were investigated regard 80-20 train-test split ratio. To ensure minimal time and resources, only top 11 out 59 dataset features considered Chi-square feature selection method. Furthermore, hyperparameter optimization (HPO) grid search cross-validation (GSCV) technique was adopted to increase accuracy prediction. Four experiments conducted utilizing combination default optimized hyperparameters on original reduced datasets. Our investigation revealed HPO had same (94.73%) as entire parameters, however, requiring resources. Hence, proposed approach may aid development computer-aided diagnostic system satisfactory computation by medical data records.

Язык: Английский

---

Comparative Analysis of Machine Learning Algorithms in Detection of Brain Tumor

Опубликована: Сен. 1, 2022

In this paper, a machine learning approach is proposed to detect the presence of brain tumor at initial stages. The data extracted from MRI scans an affected person can be incorporated in various algorithms facilitate process. Ten were run here and results obtained extensively compared using parameters: accuracy, precision, sensitivity, specificity, F1score ROC-AUC. Among algorithms, Gradient Boosting, Random Forest AdaBoost found most promising algorithms. But Boosting algorithm aced rest with accuracy 98.78%, sensitivity 99.3% specificity 95.2% while outperforms others terms precision shows highest F1-score. Google Colab platform was used for running

Язык: Английский

---

A Machine Learning Approach for Analyzing and Predicting Suicidal Thoughts and Behaviors

Опубликована: Июль 4, 2023

Suicide is a significant public health concern, and there growing interest in using machine learning techniques to identify people who are at high risk of committing suicide. In this paper, review the current state-of-the-art suicide prediction given learning. Various features investigated with data sources used earlier studies, such as text-based from social media, electronic records, demographic data. Also, different analyzed that employed including neural networks. We compare models based on errors find Support Vector Regression (SVR) be most suitable for purpose. conclude by emphasizing potential improve prevention efforts addressing ethical concerns must discussed when implementing practice.

Язык: Английский

---

Integrating metaheuristics and artificial intelligence for healthcare: basics, challenging and future directions

Artificial Intelligence Review, Год журнала: 2024, Номер 57(8)

Опубликована: Июль 12, 2024

Abstract Accurate and rapid disease detection is necessary to manage health problems early. Rapid increases in data amount dimensionality caused challenges many disciplines, with the primary issues being high computing costs, memory low accuracy performance. These will arise since Machine Learning (ML) classifiers are mostly used these fields. However, noisy irrelevant features have an impact on ML accuracy. Therefore, choose best subset of decrease data, Metaheuristics (MHs) optimization algorithms applied Feature Selection (FS) using various modalities medical imaging or datasets different dimensions. The review starts by giving a general overview approaches AI algorithms, followed MH for healthcare applications, analysis MHs boosted wide range research databases as source access numerous field publications. final section this discusses facing application development.

Язык: Английский

---

Exploring the Performances of Stacking Classifier in Predicting Patients Having Stroke

2021 8th NAFOSTED Conference on Information and Computer Science (NICS), Год журнала: 2021, Номер unknown, С. 242 - 247

Опубликована: Дек. 21, 2021

Stroke refers to a spectrum of clinical manifestations with underlying neurological dysfunctions the brain. It is medical condition which often misdiagnosed and commonly misclassified, leading delay in initiation disease-specific treatment patients. Rapid precise detection stroke key effective management patients alleviate possible disabilities. Machine learning techniques are being adopted for their capabilities identifying hidden patterns from obtained data In this study, stacking classifier constructed by utilizing Random Forest (RF), Extra Tree (ET) Gradient Boosting Classifier (GBC) as well performances observed terms various performance metrics. A detailed comparative analysis portrayed where it that accuracies RF, ET GBC 94.63%, 94.62% 94.72% respectively whereas proposed outperformed individual classifiers' an accuracy 95%. The hyperparameter tuning accomplished all classifiers enhanced. Hence, investigative can significantly contribute predict having aid developing automated diagnosis e-healthcare systems.

Язык: Английский

---