Recommender System for the Efficient Treatment of COVID-19 Using a Convolutional Neural Network Model and Image Similarity

Abstract

Background: Hospitals face a significant problem meeting patients’ medical needs during epidemics, especially when the number of patients increases rapidly, as seen during the recent COVID-19 pandemic. This study designs a treatment recommender system (RS) for the efficient management of human capital and resources such as doctors, medicines, and resources in hospitals. We hypothesize that a deep learning framework, when combined with search paradigms in an image framework, can make the RS very efficient. Methodology: This study uses a Convolutional neural network (CNN) model for the feature extraction of the images and discovers the most similar patients. The input queries patients from the hospital database with similar chest X-ray images. It uses a similarity metric for the similarity computation of the images. Results: This methodology recommends the doctors, medicines, and resources associated with similar patients to a COVID-19 patients being admitted to the hospital. The performance of the proposed RS is verified with five different feature extraction CNN models and four similarity measures. The proposed RS with a ResNet-50 CNN feature extraction model and Maxwell–Boltzmann similarity is found to be a proper framework for treatment recommendation with a mean average precision of more than 0.90 for threshold similarities in the range of 0.7 to 0.9 and an average highest cosine similarity of more than 0.95. Conclusions: Overall, an RS with a CNN model and image similarity is proven as an efficient tool for the proper management of resources during the peak period of pandemics and can be adopted in clinical settings.

UltraAIGenomics: Artificial Intelligence-Based Cardiovascular Disease Risk Assessment by Fusion of Ultrasound-Based Radiomics and Genomics Features for Preventive, Personalized and Precision Medicine: A Narrative Review

“…The RNN model cannot work to learn long-term dependencies, which results in a bridge problem when connecting old and new data [ 195 , 196 ]. This seldom causes the vanishing gradient problem, in which error signals vanish after backpropagation, leading to challenges in the model design [ 179 ].…”

A comprehensive review of machine learning algorithms and their application in geriatric medicine: present and future

“…In healthcare, examples of recommender models include recommending food items to diabetic patients [ 158 ], decision support for therapy [ 159 ], mental health apps [ 160 ], health-behaviour change [ 161 ], clinical order entry [ 161 ], treating COVID-19 [ 162 ] and cancer treatment [ 163 ]. In precision medicine, recommender systems can be used to predict the preferred treatment for a disease based on multiple patient measurements [ 164 ].…”

Survival-Based Treatment Planning Using Stage-Specific Machine Learning Models

“…The underlying justification for this observation is rooted in the substantial heterogeneity exhibited by these diseases, manifesting in diverse attributes across various disease stages and among different patients [6]. Hence, it is crucial for artificial intelligence (AI) models to adequately integrate this extensive array of diversity, while considering individual variances, in order to provide substantial prognostications and tailored therapeutic strategies [7], [8]. Moreover, it is important to acknowledge that intricate ailments like cancer often exhibit a wide range of therapeutic interventions, including surgical procedures, chemotherapy regimens, radiation therapy protocols, immunotherapeutic approaches, and targeted treatment modalities.…”