Current Signal Transduction Therapy - Volume 17, Issue 3, 2022

Electrocardiogram (ECG) is widely used in the healthcare domain because of its usage as a diagnostics tool for several cardiovascular diseases. It becomes essential to study and analyse the ECG data with the help of classification techniques. In this review paper, a brief overview of ECG signal information is presented. Various approaches for diagnosing cardiovascular diseases have been discussed, along with the need for accurate ECG signal analysis. These approaches are mainly based on the principles of machine learning and deep learning. The advantages and limitations of these techniques in the detection of cardiovascular diseases are presented within the scope of future work. This study can be helpful for researchers in bridging the gap between current approaches and future techniques for the detection of arrhythmia conditions.

Introduction: Osteoarthritis (OA) is a common chronic inflammatory neurodegenerative joint disorder that causes disability among the geriatric population. It involves the loss of the articular cartilage that covers the end of a long bone thereby failing to prevent the friction between the joints. Methods: The literature on the prevalence of OA and different risk factors like physical inactivity, obesity, and joint injury was searched through Google scholar, PubMed, research gate, Wikipedia, etc for the review. Results: OA has affected around 303 million people globally. It affects the knee, hip, hands, and spine joints owing to common symptoms like pain, swelling, and disability. Further, OA-associated disability causes depression leading to an economic and social burden with physical isolation, thus making it more severe for older people in their day-to-day lifestyle. Presently, no permanent cure has been developed for OA. Although, there are many risk factors of OA, among them, the most prominent one is considered to be “aging”. Most people crossing the age of 65–70 years have been associated with changes in the joints (one or more) about the development of OA. Several theories related to cellular aging and cell senescence with OA development. However, aging alone does not cause this condition; it is accelerated by the abnormal signal transduction followed by the progression of OA. The blueprint of possible management of OA by the different approaches has been the prime concern of this review work. Conclusion: An outline of the risk factors of abnormal signal transduction and different treatment approaches, including regenerative therapy, synthetic drugs, and naturopathy manipulating them concerning OA are discussed in this review which might be an answer to the age-old issue of geriatrics.

Background: Diabetes is one of the most common diseases and is a major public health problem worldwide. It is also the leading high-risk cause of death and disability in the world. To avoid further complications due to diabetes, regular monitoring of blood glucose levels is very important. All the current methods used to measure blood glucose are invasive, which require finger piercing, and this invasive method is more painful and more likely to cause infection. However, patients need to be directed toward developing non-invasive techniques to relieve pain. Objective: In this paper, the author uses non-invasive techniques that utilize near infrared sensors for glucose level determination from the fingertip without requiring needles and test strips. Methods: Near Infrared (NIR) optical signal is transmitted through one side of the fingertip and then received from the other side, through which blood glucose’s molecular count is predicted by analyzing the variation in the received signal’s intensity after its reflection. The signal is then filtered and amplified before going into the microcontroller to be displayed on an LCD. The glucose readings are also sent to a phone via Wi-Fi and displayed through an Android application using IoT. Results: The designed hardware is calibrated with regression analysis by a pre-calibrated conventional blood sugar machine. The derived equation is being set concerning voltage vs. blood sugar measurement. Finally, the device is being tested with 5 individual subjects with 10 reading each. Conclusion: The device is designed to measure blood glucose in a non-invasive way, and by integrating the IoT into the device, you have the freedom to measure your blood glucose remotely, except that it is available over the internet. If so, the same works fine.

Aims: In this paper, Forkhead box O (FOXO) protein using the ensemble learning algorithm is predicted. When FOXO is in excess in the human body, it leads to LNCap prostate cancer cells, and if deficit leading neurodegenerative diseases. Objective: Neurodegenerative diseases, like Alzheimer's and Parkinson's, are neurological illnesses that are caused by damaged brain cells. For prediction of FOXO protein, Gradient Boosted Machine (GBM) and Random forest (RF) techniques are used. Method: The main idea of using GBM is its non-linear nature but it is difficult for any single decision tree to fit all training. To overcome this, an RF algorithm is used. RF combines the results at the end of the process by average or majority rules, while the GBM algorithm combines the results along the way. Results: A total of 29.16% improvement has been observed by RF over GBM. Average square error is also evaluated to check the testing and training of data for 100 trees on 100 tree sizes. Conclusion: In this paper, a computational model for the prediction of FOXO protein using ensemble learning techniques (Random Forest and GBM) has been proposed. If the dataset has many variable features and the prediction accuracy is not as important then RF can be considered. On the other hand, GBMs are better suited for datasets that have very few or fewer input features and where high accuracy predictions are required. However, there are instances when either GBM or RF can perform equally well depending on how they are tuned.

Background: The study of breast cancer detection begins with the WBCD dataset for most researchers, as it is a very well-known dataset. We use this dataset as a benchmark in this paper to study ML algorithms like SVM, DT, RF, KNN, NB classifiers, Logistic Regression, Extra Trees, Bagging Classifiers with hard and soft voting, Ensemble techniques and Extreme Gradient Boosting classifiers like XG Boost and 2 deep learning models with regularization and without regularization. Objective: The primary objective is to revisit how the existing classifiers fare with the WBCD dataset and suggest a method with Grid search and Randomized search by selecting the best hyper parameters to apply with and without PCA and check if the WBCD dataset can be classified in lesser time without compromising accuracy. Methods: We explore PCA as a feature extraction technique in this dataset and use techniques like Feature Scaling K Fold stratified cross-validation technique, K best etc. We implement Grid search CV along with PCA in the pipeline to tune the hyper parameters across various classifiers and reduce the training and prediction time without compromising accuracy. Last but not least, this paper also compares the accuracy, precision and recall of various ML techniques for manually selected features by observing the feature importance score and the correlation matrix. Results: In our experiment with all features, we get an accuracy of 97.9 percent for Extra trees and Ensemble techniques with RF, KNN and Extra Trees with soft voting strategy and using feature selection with PCA and grid search, we get an accuracy of 99.1 percent with SVM (kernel trick). We also demonstrate that the running time of training and prediction also reduces if hyper parameters of classifiers are tuned appropriately, which is taken care of by Grid and Randomized Hyper Parameter Grids. Conclusion: It is shown in this paper that Feature subset selection or feature ranking may not be the best way and not the only way to be applied to the WBCD dataset along with PCA. In datasets where features are closely correlated , a method for hyper parameter tuning using either Grid or Randomized Search can be accompanied with PCA to extract the best feature combinations and then fed into the classifiers to get good accuracy scores and can be executed in a much quicker time.

Introduction: Ultrasound imaging is a standard examination during pregnancy that can measure specific biometric parameters towards prenatal diagnosis and estimating gestational age. Fetal head circumference (HC) is a significant factor in determining fetus growth and health. Methods: This paper proposes a multi-task deep convolutional neural network for automatic segmentation and estimation of HC (Fetal head circumference) ellipse by minimizing a compound cost function composed of segmentation dice score and MSE of ellipse parameters. Ultrasoundbased fetal biometric measurements, such as head circumference (HC) and biparietal diameter (BPD (Biparietal Diameter)), are commonly used to evaluate the gestational age and diagnose fetal central nervous system (CNS) pathology. Since manual measurements are operator-dependent and time-consuming, there have been numerous researches on automated methods. However, existing computerized methods still are not satisfactory in terms of accuracy and reliability, owing to difficulties in dealing with various artefacts in ultrasound images. Results: This paper focuses on fetal head biometry and develops a deep-learning-based method for estimating HC (Fetal head circumference) and BPD (Biparietal Diameter) with a high degree of accuracy and reliability. Conclusion: The proposed method effectively identifies the head boundary by differentiating tissue image patterns concerning the ultrasound propagation direction. The proposed method was trained with 102 labelled data set and tested to 70 ultrasound images. We achieved a success rate of 92.31% for HC (Fetal head circumference) and BPD (Biparietal Diameter) estimations and an accuracy of 87.14% for the plane acceptance check.

Background: Prior Authorization is a widely used process by health insurance companies in the United States before they agree to cover prescribed medication under medical insurance. However, the traditional approach includes long-length papers, leading to patients' delayed processing of their claims. This delay may deteriorate the patient’s medical condition. Also, due to man-made errors, there is a chance of incorrect decision-making on the claims. On the other hand, physicians are losing their time getting their prescribed medication approved. It is essential to reduce the wait time of patients and the tedious work of physicians for healthcare to be effective. This demands advanced technology that can boost the decision-making process of prior authorization methodology. Objective: This work aims to digitize the prior authorization process by implementing classification algorithms to classify the initial authorization applications into Accepted/Rejected/Partially Accepted classes. A web application that inputs prior authorization claim details and outputs the predicted class of the claim was proposed. Methods: Analyzed and collected significant features by implementing feature selection. Developed classification models using Artificial Neural Networks and Random Forest. Implemented model validation techniques to evaluate classifier performance. Results: From the research findings, generic medication cost, type of health insurance plan, addictive nature and side effects of the prescribed drug, patient physical qualities like Age/Gender/Current Medical condition are the significant attributes that impact the decisionmaking process in the prior authorization process. Then, implemented classifiers exhibited accurate performance on the Train and Test data. Amongst Artificial Neural Networks classification model portrayed higher accuracy. Further a confusion matrix was further analyzed for developed models. In addition, k-fold cross-validation and availed performance evaluation metrics were conducted to validate the model performance. Conclusion: Ameliorated Healthcare by removing time and location barriers in the Prior Authorization process while ensuring patients get quality and economical medication. The proposed web application with a machine learning predictive model as a backend automates the prior authorization process by classifying the applications in a few seconds.