Receive a weekly summary and discussion of the top papers of the week by leading researchers in the field.

Public Health Public Health

Extended Arm of Precision in Prosthodontics: Artificial Intelligence.

In Cureus

Dentistry based on artificial intelligence (AI) is not a myth but turning into a reality. AI has revolutionized medicine and dentistry in various ways. AI is a technology that uses machines to imitate intelligent human behavior. AI is gaining popularity worldwide because of its significant impact and breakthrough in the field of intelligence innovation. It is a lifesaver in dentistry, particularly in the field of prosthodontics, because it aids in the design of prostheses and the fabrication of functional maxillofacial appliances. It also helps in the processes of patient documentation, diagnosis, treatment planning, and patient management, allowing oral healthcare professionals to work smarter rather than harder. While it cannot replace the work of a dentist because dentistry is not about disease diagnosis, it does involve correlation with other clinical findings and provides treatment to the patient. The integration of AI and digitization has brought a new paradigm in dentistry, with extremely promising prospects. The availability of insufficient and inaccurate data is now the only barrier to the deployment of AI. Therefore, dentists and clinicians must focus on collecting and entering authentic data into their database, which will be completely utilized for AI in dentistry shortly. This study focuses on various applications of AI in prosthodontics along with its limitations and future scope.

Singi Shriya R, Sathe Seema, Reche Amit R, Sibal Akash, Mantri Namrata


artificial intelligence, cad/cam, implantology, maxillofacial prostheses, prosthodontics

Public Health Public Health

A four-generation family transmission chain of COVID-19 along the China-Myanmar border in October to November 2021.

In Frontiers in public health

BACKGROUND : Foreign imported patients and within-household transmission have been the focus and difficulty of coronavirus disease 2019 (COVID-19) prevention and control, which has also posed challenges to border areas' management. However, household transmission caused by foreign imported cases has not been reported in China's border areas. This study aimed to reveal a clear family clustering transmission chain of COVID-19 caused by contact with Myanmar refugees along the China-Myanmar border during an outbreak in October to November 2021.

METHODS : During the outbreak, detailed epidemiological investigations were conducted on confirmed patients with COVID-19 and their close contacts in daily activities. Patients were immediately transported to a designated hospital for treatment and quarantine, and their close contacts were quarantined at designated sites. Regular nucleic acid testing and SARS-CoV-2 antibody testing were provided to them.

RESULTS : A clear four-generation family clustering transmission involving five patients with COVID-19 was found along the China-Myanmar border. The index case (Patient A) was infected by brief conversations with Myanmar refugees across border fences during work. His wife (Patient B) and 9-month-old daughter (Patient C) were second-generation cases infected by daily contact with him. His 2-year-old daughter (Patient D) was the third-generation case infected by her mother and sister during quarantine in the same room and then transmitted the virus to her grandmother (Patient E, the fourth-generation case) who looked after her after Patients B and C were diagnosed and transported to the hospital. The household secondary attack rate was 80.0%, the average latent period was 4 days, and the generation time was 3 days. Ten of 942 close contacts (1.1%) of this family had positive IgM antibody during the medical observation period. In total 73.9% (696/942) of them were positive for IgG antibody and 8.3% (58/696) had IgG levels over 20 S/CO (optical density of the sample/cut-off value of the reagent).

CONCLUSION : This typical transmission chain indicated that it is essential to strengthen COVID-19 prevention and control in border areas, and explore more effective children care approaches in quarantine sites.

Yan Xiangyu, Xiao Wei, Zhou Saipeng, Wang Xuechun, Wang ZeKun, Zhao Mingchen, Li Tao, Jia Zhongwei, Zhang Bo, Shui Tiejun


COVID-19, China-Myanmar border, outbreak, refugees, transmission chain

Pathology Pathology

A deep learning and natural language processing-based system for automatic identification and surveillance of high-risk patients undergoing upper endoscopy: A multicenter study.

In EClinicalMedicine

BACKGROUND : Timely identification and regular surveillance of patients at high risk are crucial for early diagnosis of upper gastrointestinal cancer. However, traditional manual surveillance method is time-consuming, and current surveillance rate is below 50%. Here, we aimed to develop a surveillance system named ENDOANGEL-AS (automatic surveillance) for automatic identification and surveillance of high-risk patients.

METHODS : 7874 patients from Renmin Hospital of Wuhan University between May 1 and July 31, 2021 were used as the training set, 6762 patients between August 1 and October 31, 2021 as the internal test set, and 7570 patients from two other hospitals between August 1 and October 31, 2021 as the external test sets. We first extracted descriptions of abnormalities from endoscopic and pathological reports based on natural language processing techniques to identify individuals. Then patients were classified at nine risk levels according to endoscopic and pathological findings, and a deep learning model was trained to identify demarcation line (DL) in gastric low-grade intraepithelial neoplasia (LGIN) using 1561 white-light still images for risk stratification of gastric LGIN. Finally, patients undergoing upper endoscopy were classified and assigned one of ten surveillance intervals according to guidelines. The performance of ENDOANGEL-AS was evaluated and compared with physicians.

FINDINGS : Patient identification module achieved an accuracy of 100% and 99.91% in internal and external test sets, respectively. Risk level classification module achieved an accuracy of 100% and 99.85% in the internal and external test sets, respectively. DL identification module achieved an accuracy of 87.88%. ENDOANGEL-AS on surveillance interval assignment achieved an accuracy of 99.23% and 99.67% in internal and external test sets, respectively. ENDOANGEL-AS had significantly higher accuracy compared with physicians (99.00% vs 38.87%, p < 0.001). The accuracy (63.67%, p < 0.001) of endoscopists with the assistance of ENDOANGEL-AS was significantly improved.

INTERPRETATION : We established a surveillance system that can automatically identify patients and assign surveillance intervals with high accuracy and good transferability.

FUNDING : This work was partly supported by a grant from the Hubei Province Major Science and Technology Innovation Project (2018-916-000-008) and the Fundamental Research Funds for the Central Universities (2042021kf0084).

Li Jia, Hu Shan, Shi Conghui, Dong Zehua, Pan Jie, Ai Yaowei, Liu Jun, Zhou Wei, Deng Yunchao, Li Yanxia, Yuan Jingping, Zeng Zhi, Wu Lianlian, Yu Honggang


Deep learning, Endoscopy, Natural language processing, Surveillance, Upper gastrointestinal cancer

General General

Detection of Diabetic Retinopathy using Convolutional Neural Networks for Feature Extraction and Classification (DRFEC).

In Multimedia tools and applications

Diabetic Retinopathy (DR) is caused as a result of Diabetes Mellitus which causes development of various retinal abrasions in the human retina. These lesions cause hindrance in vision and in severe cases, DR can lead to blindness. DR is observed amongst 80% of patients who have been diagnosed from prolonged diabetes for a period of 10-15 years. The manual process of periodic DR diagnosis and detection for necessary treatment, is time consuming and unreliable due to unavailability of resources and expert opinion. Therefore, computerized diagnostic systems which use Deep Learning (DL) Convolutional Neural Network (CNN) architectures, are proposed to learn DR patterns from fundus images and identify the severity of the disease. This paper proposes a comprehensive model using 26 state-of-the-art DL networks to assess and evaluate their performance, and which contribute for deep feature extraction and image classification of DR fundus images. In the proposed model, ResNet50 has shown highest overfitting in comparison to Inception V3, which has shown lowest overfitting when trained using the Kaggle's EyePACS fundus image dataset. EfficientNetB4 is the most optimal, efficient and reliable DL algorithm in detection of DR, followed by InceptionResNetV2, NasNetLarge and DenseNet169. EfficientNetB4 has achieved a training accuracy of 99.37% and the highest validation accuracy of 79.11%. DenseNet201 has achieved the highest training accuracy of 99.58% and a validation accuracy of 76.80% which is less than the top-4 best performing models.

Das Dolly, Biswas Saroj Kumar, Bandyopadhyay Sivaji


Convolutional Neural Network, Deep Learning, Diabetic Retinopathy, Fundus image, Image classification

General General

An efficient hybrid stock trend prediction system during COVID-19 pandemic based on stacked-LSTM and news sentiment analysis.

In Multimedia tools and applications

The coronavirus is an irresistible virus that generally influences the respiratory framework. It has an effective impact on the global economy specifically, on the financial movement of stock markets. Recently, an accurate stock market prediction has been of great interest to investors. A sudden change in the stock movement due to COVID -19 appearance causes some problems for investors. From this point, we propose an efficient system that applies sentiment analysis of COVID-19 news and articles to extract the final impact of COVID-19 on the financial stock market. In this paper, we propose a stock market prediction system that extracts the stock movement with the COVID spread. It is important to predict the effect of these diseases on the economy to be ready for any disease change and protect our economy. In this paper, we apply sentimental analysis to stock news headlines to predict the daily future trend of stock in the COVID-19 period. Also, we use machine learning classifiers to predict the final impact of COVID-19 on some stocks such as TSLA, AMZ, and GOOG stock. For improving the performance and quality of future trend predictions, feature selection and spam tweet reduction are performed on the data sets. Finally, our proposed system is a hybrid system that applies text mining on social media data mining on the historical stock dataset to improve the whole prediction performance. The proposed system predicts stock movement for TSLA, AMZ, and GOOG with average prediction accuracy of 90%, 91.6%, and 92.3% respectively.

Sharaf Marwa, Hemdan Ezz El-Din, El-Sayed Ayman, El-Bahnasawy Nirmeen A


COVID-19 pandemic, Machine learning, Prediction, Sentimental analysis, Stacked-LSTM, Stock market

General General

COVID-19 risk reduce based YOLOv4-P6-FaceMask detector and DeepSORT tracker.

In Multimedia tools and applications

Wearing masks in public areas is one of the effective protection methods for people. Although it is essential to wear the facemask correctly, there are few research studies about facemask detection and tracking based on image processing. In this work, we propose a new high performance two stage facemask detector and tracker with a monocular camera and a deep learning based framework for automating the task of facemask detection and tracking using video sequences. Furthermore, we propose a novel facemask detection dataset consisting of 18,000 images with more than 30,000 tight bounding boxes and annotations for three different class labels namely respectively: face masked/incorrectly masked/no masked. We based on Scaled-You Only Look Once (Scaled-YOLOv4) object detection model to train the YOLOv4-P6-FaceMask detector and Simple Online and Real-time Tracking with a deep association metric (DeepSORT) approach to tracking faces. We suggest using DeepSORT to track faces by ID assignment to save faces only once and create a database of no masked faces. YOLOv4-P6-FaceMask is a model with high accuracy that achieves 93% mean average precision, 92% mean average recall and the real-time speed of 35 fps on single GPU Tesla-T4 graphic card on our proposed dataset. To demonstrate the performance of the proposed model, we compare the detection and tracking results with other popular state-of-the-art models of facemask detection and tracking.

Mokeddem Mohammed Lakhdar, Belahcene Mebarka, Bourennane Salah


Deep learning, Detection, Localization, Scaled-YOLOv4, Tracking