Harnessing machine learning to find synergistic combinations for FDA-approved cancer drugs

Combination therapy is a fundamental strategy in cancer chemotherapy. It involves administering two or more anti-cancer agents to increase efficacy and overcome multidrug resistance compared to monotherapy. However, drug combinations can exhibit synergy, additivity, or antagonism. This study presents a machine learning framework to classify and predict cancer drug combinations. The framework utilizes several key steps including data collection and annotation from the O'Neil drug interaction dataset, data preprocessing, stratified splitting into training and test sets, construction and evaluation of classification models to categorize combinations as synergistic, additive, or antagonistic, application of regression models to predict combination sensitivity scores for enhanced predictions compared to prior work, and the last step is examination of drug features and mechanisms of action to understand synergy behaviors for optimal combinations. The models identified combination pairs most likely to synergize against different cancers. Kinase inhibitors combined with mTOR inhibitors, DNA damage-inducing drugs or HDAC inhibitors showed benefit, particularly for ovarian, melanoma, prostate, lung and colorectal carcinomas. Analysis highlighted Gemcitabine, MK-8776 and AZD1775 as frequently synergizing across cancer types. This machine learning framework provides a valuable approach to uncover more effective multi-drug regimens.

Optimizing classification of diseases through language model analysis of symptoms

This paper investigated the use of language models and deep learning techniques for automating disease prediction from symptoms. Specifically, we explored the use of two Medical Concept Normalization-Bidirectional Encoder Representations from Transformers (MCN-BERT) models and a Bidirectional Long Short-Term Memory (BiLSTM) model, each optimized with a different hyperparameter optimization method, to predict diseases from symptom descriptions. In this paper, we utilized two distinct dataset called Dataset-1, and Dataset-2. Dataset-1 consists of 1,200 data points, with each point representing a unique combination of disease labels and symptom descriptions. While, Dataset-2 is designed to identify Adverse Drug Reactions (ADRs) from Twitter data, comprising 23,516 rows categorized as ADR (1) or Non-ADR (0) tweets. The results indicate that the MCN-BERT model optimized with AdamP achieved 99.58% accuracy for Dataset-1 and 96.15% accuracy for Dataset-2. The MCN-BERT model optimized with AdamW performed well with 98.33% accuracy for Dataset-1 and 95.15% for Dataset-2, while the BiLSTM model optimized with Hyperopt achieved 97.08% accuracy for Dataset-1 and 94.15% for Dataset-2. Our findings suggest that language models and deep learning techniques have promise for supporting earlier detection and more prompt treatment of diseases, as well as expanding remote diagnostic capabilities. The MCN-BERT and BiLSTM models demonstrated robust performance in accurately predicting diseases from symptoms, indicating the potential for further related research.

An Optimized Model Based on Deep Learning and Gated Recurrent Unit for COVID-19 Death Prediction

The COVID-19 epidemic poses a worldwide threat that transcends provincial, philosophical, spiritual, radical, social, and educational borders. By using a connected network, a healthcare system with the Internet of Things (IoT) functionality can effectively monitor COVID-19 cases. IoT helps a COVID-19 patient recognize symptoms and receive better therapy more quickly. A critical component in measuring, evaluating, and diagnosing the risk of infection is artificial intelligence (AI). It can be used to anticipate cases and forecast the alternate incidences number, retrieved instances, and injuries. In the context of COVID-19, IoT technologies are employed in specific patient monitoring and diagnosing processes to reduce COVID-19 exposure to others. This work uses an Indian dataset to create an enhanced convolutional neural network with a gated recurrent unit (CNN-GRU) model for COVID-19 death prediction via IoT. The data were also subjected to data normalization and data imputation. The 4692 cases and eight characteristics in the dataset were utilized in this research. The performance of the CNN-GRU model for COVID-19 death prediction was assessed using five evaluation metrics, including median absolute error (MedAE), mean absolute error (MAE), root mean squared error (RMSE), mean square error (MSE), and coefficient of determination (R2). ANOVA and Wilcoxon signed-rank tests were used to determine the statistical significance of the presented model. The experimental findings showed that the CNN-GRU model outperformed other models regarding COVID-19 death prediction.

Optimizing HCV Disease Prediction in Egypt: The hyOPTGB Framework

The paper focuses on the hepatitis C virus (HCV) infection in Egypt, which has one of the highest rates of HCV in the world. The high prevalence is linked to several factors, including the use of injection drugs, poor sterilization practices in medical facilities, and low public awareness. This paper introduces a hyOPTGB model, which employs an optimized gradient boosting (GB) classifier to predict HCV disease in Egypt. The model's accuracy is enhanced by optimizing hyperparameters with the OPTUNA framework. Min-Max normalization is used as a preprocessing step for scaling the dataset values and using the forward selection (FS) wrapped method to identify essential features. The dataset used in the study contains 1385 instances and 29 features and is available at the UCI machine learning repository. The authors compare the performance of five machine learning models, including decision tree (DT), support vector machine (SVM), dummy classifier (DC), ridge classifier (RC), and bagging classifier (BC), with the hyOPTGB model. The system's efficacy is assessed using various metrics, including accuracy, recall, precision, and F1-score. The hyOPTGB model outperformed the other machine learning models, achieving a 95.3% accuracy rate. The authors also compared the hyOPTGB model against other models proposed by authors who used the same dataset.

Hepatitis C Virus prediction based on machine learning framework: a real-world case study in Egypt

Prediction and classification of diseases are essential in medical science, as it attempts to immune the spread of the disease and discover the infected regions from the early stages. Machine learning (ML) approaches are commonly used for predicting and classifying diseases that are precisely utilized as an efficient tool for doctors and specialists. This paper proposes a prediction framework based on ML approaches to predict Hepatitis C Virus among healthcare workers in Egypt. We utilized real-world data from the National Liver Institute, founded at Menoufiya University (Menoufiya, Egypt). The collected dataset consists of 859 patients with 12 different features. To ensure the robustness and reliability of the proposed framework, we performed two scenarios: the first without feature selection and the second after the features are selected based on sequential forward selection (SFS). Furthermore, the feature subset selected based on the generated features from SFS is evaluated. Naïve Bayes, random forest (RF), K-nearest neighbor, and logistic regression are utilized as induction algorithms and classifiers for model evaluation. Then, the effect of parameter tuning on learning techniques is measured. The experimental results indicated that the proposed framework achieved higher accuracies after SFS selection than without feature selection. Moreover, the RF classifier achieved 94.06% accuracy with a minimum learning elapsed time of 0.54 s. Finally, after adjusting the hyperparameter values of the RF classifier, the classification accuracy is improved to 94.88% using only four features.

Bayesian Optimization with Support Vector Machine Model for Parkinson Disease Classification

Parkinson's disease (PD) has become widespread these days all over the world. PD affects the nervous system of the human and also affects a lot of human body parts that are connected via nerves. In order to make a classification for people who suffer from PD and who do not suffer from the disease, an advanced model called Bayesian Optimization-Support Vector Machine (BO-SVM) is presented in this paper for making the classification process. Bayesian Optimization (BO) is a hyperparameter tuning technique for optimizing the hyperparameters of machine learning models in order to obtain better accuracy. In this paper, BO is used to optimize the hyperparameters for six machine learning models, namely, Support Vector Machine (SVM), Random Forest (RF), Logistic Regression (LR), Naive Bayes (NB), Ridge Classifier (RC), and Decision Tree (DT). The dataset used in this study consists of 23 features and 195 instances. The class label of the target feature is 1 and 0, where 1 refers to the person suffering from PD and 0 refers to the person who does not suffer from PD. Four evaluation metrics, namely, accuracy, F1-score, recall, and precision were computed to evaluate the performance of the classification models used in this paper. The performance of the six machine learning models was tested on the dataset before and after the process of hyperparameter tuning. The experimental results demonstrated that the SVM model achieved the best results when compared with other machine learning models before and after the process of hyperparameter tuning, with an accuracy of 92.3% obtained using BO.

The effect of choosing optimizer algorithms to improve computer vision tasks: a comparative study

Optimization algorithms are used to improve model accuracy. The optimization process undergoes multiple cycles until convergence. A variety of optimization strategies have been developed to overcome the obstacles involved in the learning process. Some of these strategies have been considered in this study to learn more about their complexities. It is crucial to analyse and summarise optimization techniques methodically from a machine learning standpoint since this can provide direction for future work in both machine learning and optimization. The approaches under consideration include the Stochastic Gradient Descent (SGD), Stochastic Optimization Descent with Momentum, Rung Kutta, Adaptive Learning Rate, Root Mean Square Propagation, Adaptive Moment Estimation, Deep Ensembles, Feedback Alignment, Direct Feedback Alignment, Adfactor, AMSGrad, and Gravity. prove the ability of each optimizer applied to machine learning models. Firstly, tests on a skin cancer using the ISIC standard dataset for skin cancer detection were applied using three common optimizers (Adaptive Moment, SGD, and Root Mean Square Propagation) to explore the effect of the algorithms on the skin images. The optimal training results from the analysis indicate that the performance values are enhanced using the Adam optimizer, which achieved 97.30% accuracy. The second dataset is COVIDx CT images, and the results achieved are 99.07% accuracy based on the Adam optimizer. The result indicated that the utilisation of optimizers such as SGD and Adam improved the accuracy in training, testing, and validation stages.

Predictive model for progressive salinization in a coastal aquifer using artificial intelligence and hydrogeochemical techniques: a case study of the Nile Delta aquifer, Egypt

To monitor groundwater salinization due to seawater intrusion (SWI) in the aquifer of the eastern Nile Delta, Egypt, we developed a predictive regression model based on an innovative approach using SWI indicators and artificial intelligence (AI) methodologies. Hydrogeological and hydrogeochemical data of the groundwater wells in three periods (1996, 2007, and 2018) were used as input data for the AI methods. All the studied indicators were enrolled in feature extraction process where the most significant inputs were determined, including the studied year, the distance from the shoreline, the aquifer type, and the hydraulic head. These inputs were used to build four basic AI models to get the optimal prediction results of the used indicators (the base exchange index (BEX), the groundwater quality index for seawater intrusion (GQI_SWI), and water quality). The machine learning models utilized in this study are logistic regression, Gaussian process regression, feedforward backpropagation neural networks (FFBPN), and deep learning-based long-short-term memory. The FFBPN model achieved higher evaluation results than other models in terms of root mean square error (RMSE) and R² values in the testing phase, with R² values of 0.9667, 0.9316, and 0.9259 for BEX, GQI_SWI, and water quality, respectively. Accordingly, the FFBPN was used to build a predictive model for electrical conductivity for the years 2020 and 2030. Reasonable results were attained despite the imbalanced nature of the dataset for different times and sample sizes. The results show that the 1000 μS/cm boundary is expected to move inland ~9.5 km (eastern part) to ~10 km (western part) to ~12.4 km (central part) between 2018 and 2030. This encroachment would be hazardous to water resources and agriculture unless action plans are taken.

Detection of black-hole attacks in MANET using adaboost support vector machine

Mobile Ad hock Networks (MANETs) are currently used for developing the privacy and accuracy of modern networks. Furthermore, MANET applications are fit to be data-oriented systems, that introduce a secure and more robust data transmission protocol making it a topmost priority in the design. The lack of infrastructure in the existence of dynamic topology as well as limited resources of MANET is a major challenge facing those interested in the field. Further, the nonexistence of a formerly authorized trust relationship within the connected nodes produces instability of the detection process in MANETs. Basically, by adding adapted LEACH routing protocol to MANET, enhancement of the preserved nodes vitality will be achieved, moreover, the load balancing with data loss reduction provides MANET ability to tracks along with shortest and limited paths. This paper proposes a newly developed detection scheme for both active and passive black-hole attacks in MANETs. Moreover, the scheme deals with assessing a group of selected features for each node-based AdaBoost-SVM algorithm. These features are collected from cluster members nodes based on Ad hoc On-demand Multipath Distance Vector (OMDV) with LEACH routing protocol clustering approaches. Although SVM is considered a more stable classifier, there are great influences of the AdaBoost weight adaption algorithm to enhance the classification process in terms of strengthening the weights of extracted features. This hybrid algorithm is essential for active black-hole attacks as well as for identifying passive black-hole attacks in MANET. The proposed scheme is tested against the effect of mobility variation to determine the accuracy of the detection process including the routing overhead protocol. The experimental results investigated that the accuracy of detecting both active and passive black-holes attacks in MANET reached 97% with a promising time complexity for different mobility conditions. Moreover, the proposed scheme provides an accurate decision about malicious vs benign node dropping behavior using an adjustable threshold value.

HANA: A Healthy Artificial Nutrition Analysis model during COVID-19 pandemic

Background and objective

The impact of diet on COVID-19 patients has been a global concern since the pandemic began. Choosing different types of food affects peoples’ mental and physical health and, with persistent consumption of certain types of food and frequent eating, there may be an increased likelihood of death. In this paper, a regression system is employed to evaluate the prediction of death status based on food categories.

Methods

A Healthy Artificial Nutrition Analysis (HANA) model is proposed. The proposed model is used to generate a food recommendation system and track individual habits during the COVID-19 pandemic to ensure healthy foods are recommended. To collect information about the different types of foods that most of the world's population eat, the COVID-19 Healthy Diet Dataset was used. This dataset includes different types of foods from 170 countries around the world as well as obesity, undernutrition, death, and COVID-19 data as percentages of the total population. The dataset was used to predict the status of death using different machine learning regression models, i.e., linear regression (ridge regression, simple linear regularization, and elastic net regression), and AdaBoost models.

Results

The death status was predicted with high accuracy, and the food categories related to death were identified with promising accuracy. The Mean Square Error (MSE), Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and R² metrics and 20-fold cross-validation were used to evaluate the accuracy of the prediction models for the COVID-19 Healthy Diet Dataset. The evaluations demonstrated that elastic net regression was the most efficient prediction model. Based on an in-depth analysis of recent nutrition recommendations by WHO, we confirm the same advice already introduced in the WHO report¹. Overall, the outcomes also indicate that the remedying effects of COVID-19 patients are most important to people which eat more vegetal products, oilcrops grains, beverages, and cereals - excluding beer. Moreover, people consuming more animal products, animal fats, meat, milk, sugar and sweetened foods, sugar crops, were associated with a higher number of deaths and fewer patient recoveries. The outcome of sugar consumption was important and the rates of death and recovery were influenced by obesity.

Conclusions

Based on evaluation metrics, the proposed HANA model may outperform other algorithms used to predict death status. The results of this study may direct patients to eat particular types of food to reduce the possibility of becoming infected with the COVID-19 virus.