Abstract: Panic disorder is a debilitating mental health condition that requires early and accurate detection for effective treatment. This study employs a Gradient Boosting Classifier to detect panic disorder using a dataset of 120,000 instances, split into training, validation, and testing subsets. Preprocessing included one-hot encoding and standardization to ensure data suitability. The model achieved a training accuracy of 99.997% and a testing accuracy of 98%. A confusion matrix analysis revealed excellent performance, with 19,158 true negatives, 841 true positives, one false positive, and no false negatives, highlighting high precision and recall. These results demonstrate the potential of Gradient Boosting for reliable mental health diagnostics, supporting early intervention and improved outcomes.

Keywords: Diagnosis; Gradient Boosting; Machine Learning; Panic Disorder.

Title: Panic Disorder Detection Using Machine Learning

Author: Faezeh Norouzi, Bruna Lino Modes Santos Machado

International Journal of Novel Research in Life Sciences                                                   

ISSN 2394-966X

Vol. 12, Issue 1, January 2025 - February 2025

Page No: 18-23

Novelty Journals

Website: www.noveltyjournals.com

Published Date: 25-January-2025

Abstract: Heart failure is a significant global health challenge, requiring effective and early diagnostic tools to improve patient outcomes. In this study, we developed a predictive model for heart failure using Support Vector Machines (SVM), leveraging clinical data from 299 patients. The dataset includes key features such as age, ejection fraction, serum sodium levels, and comorbidities like diabetes and high blood pressure. Our SVM model demonstrated exceptional predictive performance, achieving a training accuracy of 99.7% and a testing accuracy of 99.1%.

Keywords: Diagnosis; Heart Failure; Machine Learning; SVM.

Title: Heart Failure Prediction Using Support Vector Machine

Author: Fariba Ghasemi, Seyedhassan Sharifi

International Journal of Novel Research in Life Sciences                                                   

ISSN 2394-966X

Vol. 12, Issue 1, January 2025 - February 2025

Page No: 12-17

Novelty Journals

Website: www.noveltyjournals.com

Published Date: 25-January-2025

Abstract: Classification and segmentation are pivotal tasks in medical imaging that have witnessed remarkable advancements through artificial intelligence (AI). This review highlights recent developments in AI-driven classification and segmentation methodologies, focusing on applications in disease detection, tumor segmentation, and organ delineation. We provide an overview of state-of-the-art deep learning architectures, including convolutional neural networks (CNNs), UNet, and Transformers, while discussing challenges such as data scarcity, generalization, and clinical integration. Finally, we propose future directions, including hybrid frameworks and explainable AI, to address current limitations and improve clinical adoption.

Keywords: Artificial Intelligence; Classification; Deep Learning; Diagnosis; Medical Imaging.

Title: Artificial Intelligence Applications in Diagnosing Medical Diseases

Author: Hossein Abbasi

International Journal of Novel Research in Life Sciences                                                   

ISSN 2394-966X

Vol. 12, Issue 1, January 2025 - February 2025

Page No: 6-11

Novelty Journals

Website: www.noveltyjournals.com

Published Date: 25-January-2025

Abstract: Background and objectives: Efforts at improving the quality of life in individuals with insomnia have been a concern for researchers in the past decades. This study determined the effect of cognitive behavioural therapy and physiotherapy on patients suffering from insomnia.

Methods: This study involved 20 participants clinically diagnosed with insomnia. They underwent cognitive behavioural therapy and physiotherapy for six weeks. Insomnia is assessed using the insomnia severity index and the data is analysed using an independent paired t test.

Results: Participants were aged 21 – 30 years. There is a significant improvement in each of the symptoms of insomnia. Before the intervention, 91.3% had insomnia and 4.3% each of subthreshold and moderate insomnia respectively while at six weeks, 95.7% had no insomnia and 4.3% had sub-threshold insomnia. All participants were poor at ISI rating before intervention while at six weeks, 82.6% rated their effectiveness as good and 17.4% rated it fair.

Conclusion: Cognitive behavioural therapy and physiotherapy significantly reduce the severity of insomnia and fatigue, and improve the quality of life and functional performance of individuals with insomnia.

Keywords: Insomnia, cognitive behavioural therapy, physiotherapy, insomnia severity index scale.

Title: EFFECT OF COGNITIVE BEHAVIORAL THERAPY WITH PHYSIOTHERAPY ON SUBJECTS WITH INSOMNIA

Author: Saranraj Palanivel, Rajadurai.S, Arun. B, Muralidharan CK, Selvi.P, Susmitha.P, Divya Bharathi ML

International Journal of Novel Research in Life Sciences                                                   

ISSN 2394-966X

Vol. 12, Issue 1, January 2025 - February 2025

Page No: 1-5

Novelty Journals

Website: www.noveltyjournals.com

Published Date: 21-January-2025