Search

This article discusses the integration of Artificial Intelligence (AI) and Machine Learning (ML) technologies in cancer research. It highlights how these technologies are transforming the diagnosis, treatment, and prevention of cancer by providing sophisticated analytical capabilities. The paper explores the mathematical foundations and practical implementations of AI and ML techniques in various aspects of cancer research, including detection, diagnosis, prognosis, and personalized treatment strategies. It also reviews influential algorithms such as Support Vector Machines (SVM), Convolutional Neural Networks (CNNs), and clustering techniques, and their roles in improving diagnostic accuracy and treatment efficacy. Please note that this preprint has not been peer-reviewed. [Extracted from the article]

A research report from Soochow University in Suzhou, China, introduces a new algorithm called Multi-scale and Auto-tuned Semi-supervised Deep Subspace Clustering (MASDSC) for brain tumor clustering in medical imaging. The algorithm addresses the limitations of traditional unsupervised deep subspace clustering algorithms by incorporating a semi-supervised learning framework and a multi-scale feature extraction mechanism. It also employs a Bayesian optimization algorithm for adaptive tuning of hyperparameters. The MAS-DSC algorithm achieves excellent clustering results on standard datasets and demonstrates robustness and enhanced clustering performance on a brain tumor dataset. The research has been peer-reviewed and published in Computers Materials & Continua. [Extracted from the article]

A recent report from the Saveetha School of Engineering in Chennai, India, discusses the development of a deep learning framework using a convolution neural network algorithm for breast cancer detection and classification. Breast cancer is a significant health concern globally, affecting both men and women. The proposed framework aims to improve the efficiency and accuracy of breast cancer diagnosis by automatically analyzing breast images. The research concludes that the deep learning framework, specifically the convolution neural network, is highly reliable compared to existing algorithms. This research has been peer-reviewed and provides valuable insights into the field of cancer detection. [Extracted from the article]

A research paper from the Kalasalingam Academy of Research and Education in Tamil Nadu, India, introduces a model called Taylor-Tunicate Swarm Algorithm-based Generative Adversarial Networks (Taylor-TSA-based GANs) for cancer prediction. The model incorporates the Taylor series with the Tunicate Swarm Algorithm and uses the Yeo-Johnson transformation for data transformation. The feature fusion is evaluated by Deep Stacked Autoencoder, and the fused feature is given as input to the cancer prediction done by GAN trained by Taylor-TSA. The research concludes that the developed model is effective and efficient, with high accuracy, a low false positive rate, and a high true positive rate. [Extracted from the article]

A report from the China University of Petroleum (East China) discusses the need for modern technology, specifically artificial intelligence, to support the diagnosis of breast cancer. The existing computer-aided diagnostic systems for breast cancer are costly and limited in their capabilities. The report proposes the use of improved algorithms and a simple integrated system for pre-diagnosis of breast cancer based on CNN and Pyqt5. The system utilizes tensorflow and pytorch frameworks and includes a human-computer interaction GUI system interface. The research has been peer-reviewed and more information can be obtained from the China University of Petroleum (East China). [Extracted from the article]

A study conducted by researchers at Prince Sattam bin Abdulaziz University in Saudi Arabia explores the issue of balancing generation and demand in interconnected microgrids (MGs) to address security, power quality, and reliability concerns. The study proposes an optimized fractional order load frequency control (LFC) scheme with cascaded outer and inner control loops. The proposed controller, based on a modified version of the liver cancer optimization algorithm (MLCA), achieves better disturbance rejection compared to traditional LFC methods. The study also considers the contribution of electric vehicles and the high penetration of renewables to test the stability of the proposed LFC technique. The results confirm the superior response and improved performance of the proposed controller. [Extracted from the article]

A recent study conducted at Shiraz University aimed to improve the accuracy of breast cancer diagnosis by using a feature selection algorithm based on particle swarm optimization (PSO) combined with machine learning methods. The researchers tested their algorithm on three common breast cancer datasets and found that it significantly improved accuracy while reducing the number of features needed for diagnosis. The study suggests that the proposed algorithm has the potential to enhance breast cancer diagnosis and reduce cost and time. Further information on the study can be found in the International Journal of Computational Intelligence Systems. [Extracted from the article]

Researchers at Chitkara University in Punjab, India have developed an improved lung cancer segmentation technique using nature-inspired optimization approaches. The study focused on the precise identification of tumor nodules in lung cancer Computed Tomography (CT) images. The researchers integrated four nature-inspired swarm intelligent techniques with the K-means algorithm to address the visual challenges of segmentation. The results showed that the K-means algorithm with Cuckoo Search Algorithm (CSA) significantly improved the quality of lung cancer segmentation compared to other optimization approaches. This research provides a valuable tool for researchers to improve the segmentation of medical image datasets for identifying the targeted region of interest. [Extracted from the article]

A recent report from Universiti Malaya discusses research on cancer treatment using optimal control supported by swarm intelligence. The study aims to develop hybrid techniques that combine optimal control theory with evolutionary algorithms and multi-objective swarm algorithms to reduce cancerous cells while minimizing the use of chemotherapy medications and toxicity. Two hybrid techniques were proposed and evaluated, with MOEA/D emerging as the most effective algorithm in reducing tumor size and cancer drug concentration. The study highlights the importance of integrating optimal control theory and evolutionary algorithms for optimizing cancer chemotherapy treatment. [Extracted from the article]

A recent report from Lanzhou University in China discusses the use of a new algorithm called Hierarchical Learning-Enhanced Chaotic Crayfish Optimization Algorithm (HLCCOA) to improve the accuracy of extreme learning machine diagnostics in breast cancer. The HLCCOA algorithm addresses the limitations of traditional crayfish optimization algorithms by utilizing chaotic sequences for population position initialization and implementing a hierarchical learning mechanism. Rigorous testing shows that the HLCCOA-optimized extreme learning machine model outperforms other benchmark models in terms of accuracy, sensitivity, and specificity for breast cancer diagnosis. This research highlights the potential practicality and robustness of the HLCCOA algorithm in improving breast cancer diagnostics. [Extracted from the article]

A recent study conducted by researchers at Wenzhou University in China focuses on improving the accuracy of image segmentation for breast cancer diagnosis. The study proposes a refined whale optimization algorithm that combines a quantum phase interference mechanism and an enhanced solution quality strategy. The algorithm is compared to other state-of-the-art algorithms and is tested on benchmark datasets to validate its performance. The results demonstrate the effectiveness of the segmentation method in both low and high threshold levels, making it a valuable technique for practical applications. The study has been peer-reviewed and provides potential avenues for further research in breast cancer diagnosis. [Extracted from the article]

Researchers from Graphic Era (Deemed to be University) have conducted a study on lung cancer prediction using machine learning algorithms. The study highlights the increasing cases of lung cancer due to the excessive growth of PM 2.5 in aerosol, with the highest mortality rate among other types of cancer. The researchers aimed to compare twelve potential machine learning algorithms to accurately predict positive cases of lung cancer based on clinical data and symptoms. The study found that the K-Nearest Neighbor Model and Bernoulli Naive Bayes Model were the most significant methods for early lung cancer prediction. [Extracted from the article]

A report from Universiti Teknologi PETRONAS in Malaysia discusses research on colon cancer. The researchers developed an efficient approach for colon cancer segmentation and image synthesis using advanced generative adversarial networks (GANs) guided by the Sine Cosine Algorithm (SCA) for hyperparameter tuning. The method achieved state-of-the-art results, outperforming existing methods, and shows promise in enhancing the accuracy and robustness of colon cancer diagnosis and treatment. This research could lead to better diagnosis and treatment of colon cancer. The full report can be accessed through IEEE Access. [Extracted from the article]

A study conducted in Beijing, China, focused on brain cancer, specifically gliomas, which have the highest mortality rate among brain tumors. The researchers proposed a hierarchical multi-scale attention feature fusion medical image classification network (HMAC-Net) to improve the classification of glioma risk. The network framework consists of three parallel layers: global feature extraction, local feature extraction, and multi-scale feature fusion. The results of the study showed that HMAC-Net performed the best in both qualitative and quantitative analysis. The research has been peer-reviewed and published in Computers Materials & Continua. [Extracted from the article]

A recent study conducted by researchers at Princess Nourah bint Abdulrahman University in Riyadh, Saudi Arabia, has developed a new approach called Swin-GA-RF to enhance the classification of cervical cells in Pap smear images for the detection of cervical cancer. The Swin-GA-RF approach combines the Swin transformer, genetic algorithm feature selection, and a random forest classifier. The researchers compared the performance of Swin-GA-RF with pre-trained CNN models and found that Swin-GA-RF outperformed other models in both binary and five-class classification tasks. These findings suggest that the Swin-GA-RF approach could be a valuable tool for early diagnosis and screening programs for cervical cancer. [Extracted from the article]

Researchers at the University of Mustapha Stambouli in Algeria have developed a new method for accurately classifying breast cancer using machine learning techniques. The method, called Correlation technique-Modified Grey Wolf Optimizer (CMGWO), involves two stages: feature selection and classification. The researchers used the Wisconsin Diagnostic Breast Cancer (WDBC) database to test the performance of their method and found that it significantly increased the accuracy rate of classification. The study concludes that CMGWO is a reliable approach for detecting breast cancer, with an accuracy rate of 99.12%. [Extracted from the article]

A recent report from the School of Electronics Engineering discusses research on brain cancer and the challenges of accurately separating tumor regions from healthy tissue in medical imaging. The researchers propose a novel semantic segmentation architecture called IC-Net, which combines elements from various models to improve brain tumor segmentation in MRI images. The IC-Net design outperforms other segmentation techniques, achieving notable outcomes in accuracy, loss, specificity, sensitivity, and Dice similarity coefficient. This research has the potential to enhance the accuracy of brain tumor segmentation and improve medical imaging analysis in the field of oncology. [Extracted from the article]

A recent report from Universitas Multimedia Nusantara highlights the global concern of breast cancer, which is the leading cancer type in terms of new cases and among the top five cancer types with the most deaths. The research aims to improve the identification of breast cancer comorbidities and ultimately reduce the number of deaths from this condition. The study utilizes network analysis and community detection algorithms to identify comorbidities associated with breast cancer. The findings reveal several diseases that are commonly associated with breast cancer, providing valuable insights for medical professionals. [Extracted from the article]

A recent study conducted by researchers at Tzu Chi University in Taiwan aimed to predict the risk factors of disease recurrence in patients with advanced-stage head and neck cancer. The study utilized a machine learning algorithm called eXtreme Gradient Boosting (XGBoost) to analyze clinical data from 187 patients who received surgery and adjuvant radiotherapy with or without chemotherapy. The researchers found that pathological lymph node status and whether the patient was receiving chemotherapy were the most important factors associated with treatment outcome. The study concluded that further research is needed to develop a stronger model for predicting outcomes in these patients. [Extracted from the article]

A study conducted by researchers at the University of Health Sciences in Adana, Turkey, has developed a deep machine learning algorithm to diagnose thyroid cancer. The algorithm addresses the challenges of multi-dimensional big data and randomly distributed missing data, which are common in thyroid cancer diagnoses. The algorithm achieved 100% training and 83% testing preciseness for unseen data, and its computational time efficiency was also examined. This research provides valuable insights into the use of machine learning in diagnosing thyroid cancer. [Extracted from the article]

A new study conducted at the University of Kastamonu in Turkey has developed an innovative method for the automated detection of colon cancer using artificial intelligence. The researchers utilized a convolutional neural network (CNN) and the Fishier Mantis Optimizer algorithm to improve the accuracy and efficiency of colon cancer diagnosis. The proposed method was evaluated using a comprehensive dataset of colon cancer images and demonstrated superior performance compared to traditional diagnostic approaches. The integration of deep learning techniques and bio-inspired optimization algorithms holds promise for enhancing early detection and diagnosis of colon cancer. [Extracted from the article]

A recent study conducted at Mohamed Sathak Engineering College in Tamil Nadu, India, focused on the detection and classification of brain tumors using magnetic resonance imaging (MRI). The researchers proposed an algorithm called Adaptive Convolutional Autoencoder-based Snow Avalanches (ACAE-SA) to automate the detection and categorization of brain tumors from MRI images. The algorithm was found to be effective and outperformed existing techniques. This research has been peer-reviewed and published in the journal Signal Image and Video Processing. For more information, readers can contact the researchers at Mohamed Sathak Engineering College. [Extracted from the article]

A research study conducted at the KLS Gogte Institute of Technology in Belagavi, India, has explored the use of super-resolution (SR) reconstruction techniques for improving the spatial resolution of pathology images in prostate cancer diagnosis. The study compared various machine learning, deep learning, and generative adversarial network (GAN) algorithms and evaluated their performance using different metrics. The results showed that the SRGAN algorithm outperformed other algorithms, achieving high-quality image resolution and fine details. The application of SRGAN could provide a cost-effective solution for enhancing the accuracy of cancer diagnosis by improving the visualization of cellular and tissue structures in pathology images. [Extracted from the article]

A recent study conducted at Kanazawa University in Japan explores the use of machine learning algorithms for the diagnosis of cervical cancer. The researchers propose a novel feature selection strategy called the Binary Harris Hawks Optimization (BHHO) algorithm, which aims to reduce the number of features used in diagnosis while improving accuracy. The BHHO algorithm demonstrates better stability and accuracy compared to other common wrapper-based feature selection methods, not only on cervical cancer datasets but also on other disease datasets. This research contributes to the ongoing efforts to improve early diagnosis and treatment of cervical cancer, which is one of the leading causes of cancer-related deaths among females worldwide. [Extracted from the article]

A recent study conducted at the University of Virginia has developed an algorithm to predict radiation-induced immune suppression (RIIS) in lung cancer patients treated with stereotactic body radiation therapy (SBRT). RIIS is a side effect of radiation therapy that can decrease immunological function and increase susceptibility to infections. The algorithm uses patient data, including radiation therapy treatment plans and blood data, to predict the fraction of lymphocytes killed by the treatment plan and the time dependence of absolute lymphocyte count (ALC) following SBRT. The algorithm demonstrated accurate predictions of post-treatment ALC and has the potential to reduce immune cell toxicity while maintaining treatment quality. [Extracted from the article]

A recent study conducted by researchers at the University of Granada in Spain has developed a new app called PaiNEd that aims to assess pain experience in survivors of breast cancer. The app includes an algorithm that determines whether patients are experiencing pain predominantly related to central sensitization (CS) symptoms. The study found that the app demonstrated reliability in evaluating pain experience and could be a valuable tool for healthcare professionals involved in pain education programs. This research provides a potential solution for assessing and managing pain in breast cancer survivors. [Extracted from the article]

A new report from the University of Massachusetts discusses the use of large language models (LLMs) like ChatGPT and Bard in clinical decision-making for cancer screening. The study evaluated the accuracy of these models in responding to open-ended and select-all-that-apply prompts based on the American College of Radiology Appropriateness Criteria. The results showed similar performances between ChatGPT and Bard, with ChatGPT slightly more accurate in select-all-that-apply scenarios. Prompt engineering techniques were also used to improve the accuracy of the models' outputs. The study suggests that LLMs have potential in aiding clinical decision-making processes, especially when guided by well-engineered prompts. Further research in diverse clinical situations is needed to better understand the impact of LLMs in radiology. [Extracted from the article]

A recent study conducted by researchers at Shanxi Medical University in China proposes a novel methodology for the early detection of gastric cancer. The study combines the use of the Alexandria Net (Alexnet), Extreme Learning Machine (ELM), and a modified metaheuristic algorithm to enhance the accuracy and efficiency of gastric cancer detection. The researchers applied this methodology to a practical dataset and found that it outperformed several state-of-the-art methods in terms of precision, accuracy, recall, specificity, F1-score, and Area Under the Curve (AUC). The study concludes that the combination of Alexnet and ELM with the modified metaheuristic algorithm has the potential to significantly impact the field of gastric cancer detection. [Extracted from the article]

A recent report from investigators at the School of Computing in Tamil Nadu, India, discusses the use of swarm intelligent metaheuristic optimization algorithms-based artificial neural network models for breast cancer diagnosis. The report emphasizes the importance of early detection and the use of optimization algorithms to improve accuracy and efficiency in predicting breast cancer. The researchers compare different approaches and highlight the significance of swarm intelligent algorithms-based optimized artificial neural network models. The report also discusses evaluation metrics and future research directions in this field. This research has been peer-reviewed and provides valuable insights into breast cancer diagnosis. [Extracted from the article]

Researchers from Shandong University in China have developed a new strategy for diagnosing oral cancer using a combination of effective learning and medical imaging. The strategy utilizes Gated Recurrent Unit (GRU) networks optimized by an improved version of the Northern Goshawk Optimization (NGO) algorithm. This approach has several advantages, including the ability to analyze large and complex datasets, high accuracy, and the capacity to detect oral cancer at an early stage. The study demonstrates the efficiency of this approach in accurately diagnosing oral cancer. [Extracted from the article]

A recent report from Sun Yat-sen University in Guangzhou, China discusses the research on natural killer cells (NKCs) and their potential in cancer immunotherapy. The researchers utilized deep learning techniques to analyze the morphology and motion characteristics of NKCs in tumor contexts. They proposed an improved two-shot tracking algorithm, Distance Cascade Matching and the Re-Search method, to overcome the challenges of tracking small NKCs in complex backgrounds. The study found that polarized NKCs are more likely to move along their polarization direction and approach cancer cells, and under equilibrium, NKCs display a Boltzmann distribution on the cancer cell surface. This research provides valuable insights into the dynamics of NKCs and their interactions with cancer cells. [Extracted from the article]

Researchers from the University of Malaysia Perlis have developed a new method for detecting and segmenting the nucleus cell region in Pap smear images for cervical cancer screening. The proposed method, which includes color adjustment, k-means, and a modified Bradley algorithm, has been found to significantly and efficiently segment the nucleus cell region compared to the original Bradley algorithm. The researchers achieved high accuracy, sensitivity, and F-measure results, indicating the effectiveness of their approach. This research provides a new perspective on improving the convenience and accuracy of cervical cancer screening. [Extracted from the article]

Researchers from Regeneron Pharmaceuticals Inc. conducted a study on the application of multiple validated algorithms for identifying incident breast cancer among individuals with atopic dermatitis (AD). They tested two algorithms in multiple insurance claims databases and found that Algorithm 2 provided similar estimates to those of the Surveillance, Epidemiology, and End Results (SEER) program. However, they noted that the replicability of these algorithms in different data sources or subpopulations is rarely tested, and caution should be exercised when using them to calculate incidence or prevalence estimates. The study was supported by Sanofi and published in Pharmacoepidemiology and Drug Safety. [Extracted from the article]

A recent study conducted by researchers at Shanghai University of Electric Power explores the use of privacy-preserving algorithms in breast cancer prediction. The researchers highlight the need for pre-diagnosis testing to alleviate the strain on healthcare resources. They propose a highly optimized two-party logistic regression algorithm based on the CKKS scheme, which aims to enhance the accuracy and efficiency of pre-diagnosis testing while upholding data privacy. Simulation experiments demonstrate that the model's prediction accuracy exceeds 96% for two-sided encrypted data. This research contributes to the field of machine learning in healthcare and offers potential solutions for collaborative training of models while protecting private data. [Extracted from the article]

A research study conducted in Bucharest, Romania, analyzed the management of ectopic mediastinal thyroid (EMT) in relation to cancer and non-malignant findings. The study reviewed 89 original articles and classified them into four groups: studies/case series, malignant EMTs, benign EMTs without thyroid anomalies, and benign EMTs with thyroid anomalies. The researchers proposed a 10-item algorithm to navigate the EMT domain. The study found that the clinical index of suspicion for EMT remains low, but the rate of cancer is higher than previously reported. Surgery was found to have a good overall outcome. [Extracted from the article]

A recent report from the North China University of Science and Technology discusses the use of the Internet of Medical Things (IoMT) in cancer diagnosis and treatment. The report introduces a new algorithm called Dependent Nearest Neighbor Powered Twin Support Vector Machine (DTWSVM) for predicting cancer recurrence. The algorithm achieved an average accuracy of 91.53% across seven cancer datasets, outperforming other existing models. The researchers suggest that the DTWSVM algorithm could improve prediction accuracy and assist clinicians in making treatment decisions. [Extracted from the article]

Researchers at Fuzhou University in Fujian, China have developed a deep learning model fusion algorithm for the diagnosis of gastric mucosa-associated lymphoid tissue (MALT) lymphoma. The algorithm uses hematoxylin-eosin (H&E) whole slide images (WSIs) to accurately diagnose MALT lymphoma, which is a type of malignant tumor originating from the lymphohematopoietic system. The proposed framework achieved an accuracy of 98.53% using image patches and 94.96% on 258 WSIs, demonstrating its potential use in clinical practice. The research was funded by the National Natural Science Foundation of China and the Fujian Health Commission. [Extracted from the article]

Researchers at Shaqra University in Saudi Arabia have developed a new method for detecting and quantifying Breast Arterial Calcification (BAC) in mammograms. The method combines Enhanced Wolf Pack Algorithm (EWPA) for feature selection and Dense-kUNet segmentation for image classification. The proposed technique achieved high precision, recall, F-measure, and accuracy when compared to other methods on the Digital Database for Screening Mammography (DDSM). This research provides a promising approach to improve breast cancer screening and diagnosis. [Extracted from the article]

A new research study from the Autonomous University in Morelos, Mexico, has developed an improved object detection algorithm for breast cancer screening. The algorithm combines the Khalil conformable derivative and the Hessian matrix to enhance image quality and accuracy in identifying breast cancer. The research found that the algorithm provides better visual identification of conditions such as breast cancer, calcifications, and cerebral arteriovenous malformations, improving the accuracy of clinical diagnosis and subsequent monitoring. The study has been peer-reviewed and offers potential applications in medical image processing and analysis. [Extracted from the article]

A study conducted by researchers at Sun Yat-sen University in Guangdong, China, has developed a novel classification model to predict the recurrence of early-stage nasopharyngeal carcinoma after radiotherapy. The model combines unsupervised diagnostic feature learning with Adaboost ensemble learning, resulting in an accuracy of 80.33%, sensitivity of 79.55%, specificity of 80.43%, and GMean of 79.99%. The researchers believe that this model can be a valuable tool for medical professionals in predicting the likelihood of recurrence in the cervical lymph nodes following radiotherapy for early-stage nasopharyngeal carcinoma. [Extracted from the article]

This article discusses a study that compares seven different algorithms for tracing fibre-like structures in biomedical images. The analysis of these structures can help in understanding processes like angiogenesis and the effects of certain treatments. The study found that no single algorithm outperformed the others in all metrics, but the Trace Ridges algorithm ranked first in terms of total distance error. The algorithm is fully automatic and combines various image-processing techniques to accurately delineate the fibre-like structures. The article also provides information on where to access the code for the Trace Ridges algorithm. Please note that this preprint has not been peer-reviewed. [Extracted from the article]

Researchers from the College of Animal Sciences and Technology in Tongliao, China have developed a novel machine learning method for the early detection of brain tumors. The method combines the advantages of Gated Recurrent Unit (GRU) networks and the Enhanced Hybrid Dwarf Mongoose Optimization (EHDMO) algorithm to analyze MRI images and accurately detect brain tumors. The proposed method achieved high sensitivity, specificity, positive predictive value, negative predictive value, and accuracy, outperforming other recent methods. This research provides a promising approach to automate and improve brain tumor detection using advanced technology. [Extracted from the article]

Researchers from Hebei University in Baoding, China have developed a new algorithm for diagnosing neuroblastoma, a type of malignant solid tumor in children. The algorithm uses a network model based on the U-Net structure, with DenseNet as the encoder, to extract features from whole slide images of neuroblastoma. The algorithm achieved high accuracy in segmenting and counting poorly differentiated and differentiated cells, which can help determine the histopathological types and prognostic effects of neuroblastoma. The research has been peer-reviewed and published in the journal Signal Image and Video Processing. [Extracted from the article]

Researchers from Sohag University have developed a new algorithm, called RBNRO-DE, for gene selection in cancer classification using high-dimensional data. The algorithm was tested on 22 cancer datasets and compared to other meta-heuristic algorithms. The results showed that the RBNRO-DE algorithm achieved optimal convergence and classification accuracy up to 100%, with a feature reduction size of 98%. This research highlights the potential of RNA sequencing as a technique for gene profiling and quantification in cancer research. [Extracted from the article]

Insilico Medicine, an AI-driven biotech company, has developed a groundbreaking algorithm called Quantum-assisted Fragment-based Automated Structure Generator (QFASG) that aids in automated drug design. QFASG uses advanced chemoinformatic techniques to create new small-molecule structures from a library of molecular fragments. The researchers successfully applied QFASG to generate new small-molecule inhibitors for two pharmacological targets involved in cancer pathogenesis. The algorithm's fully automated pipeline streamlines the process of structure generation and optimization, providing researchers with a powerful tool for accelerating the drug discovery process. [Extracted from the article]

Researchers at Lovely Professional University in Phagwara, India have developed a hybrid feature selection technique to improve the speed and performance of machine learning models in diagnosing breast cancer. The technique combines Regularized Neighborhood Component Analysis (RNCA) and Binary Teaching Learning Based Optimization (BTLBO) algorithms to select the best features for classification. The results of the study showed that the hybrid model outperformed other feature selection methods in terms of classification accuracy, recall, and AUC measures. This research has been peer-reviewed and published in The International Arab Journal of Information Technology. [Extracted from the article]

A recent study by researchers at the University of Pennsylvania School of Medicine has examined the role of health care algorithms in perpetuating racial and ethnic disparities. The study found that removing race from a kidney function algorithm had unintended consequences, such as reducing chemotherapy access and eligibility for clinical trials for Black patients. The researchers emphasized the importance of intentionality in algorithm development and suggested strategies to mitigate disparities, including using non-race variables and refining algorithms to minimize disparities across groups. The study highlights the need for transparency and a race-aware approach in algorithm development to promote health care equity. [Extracted from the article]

A study conducted by researchers at the Nanyang Institute of Technology in Henan, China, proposes a new methodology for the early diagnosis of melanoma skin cancer using dermoscopic images. The method involves scaling and enhancing the quality of the images, extracting features based on the Gray-Level Co-occurrence Matrix (GLCM), and using a newly developed version of the Archimedes Optimization Algorithm (DAOA) to select the most relevant features. The selected features are then classified using a Support Vector Machine (SVM) to distinguish between benign and malignant lesions. The proposed method achieved high values for performance indicators and demonstrated an accuracy of 88%, sensitivity of 96%, specificity of 81%, precision of 97%, and F-measure of 97% for the diagnosis of melanoma. [Extracted from the article]

Northwestern University researchers have developed an AI-powered transfer learning approach that repurposes publicly available data to predict combinations of gene perturbations that can transform cell type or restore diseased cells to health. This approach has the potential to control cell behavior and transitions across cell types, which could be applied to regrowing injured tissues or transforming cancer cells back into normal cells. The researchers trained their AI to learn how gene expression gives rise to cell behavior using publicly available gene expression data and developed an algorithm to predict gene combinations that are most likely to induce a desired reprogramming transition. This approach addresses the main challenges of controlling cell behavior and can be applied to various biomedical conditions. [Extracted from the article]