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

General General

COVID-19 information fatigue? A case study of a German university website during two waves of the pandemic.

In Human behavior and emerging technologies

The COVID-19 pandemic has resulted in the ubiquity of health-related information, disseminated using digital technology. However, recent research suggests that this accessibility of (often negative) information can induce adverse psychological effects, including anxiety, panic-based hoarding, and other unhealthy behaviors. Some of these consequences have been explained with the idea of an information overload. Considering these current developments, it may become harder to effectively communicate COVID-19-related information in smaller, local contexts, such as universities. By analyzing the page views and searches on the website of a university of education in Germany, we derive recommendations for the delivery of information of local organizations. One conclusion is that the need for information during the pandemic decreases as time passes (at least at the local level of institutions such as universities), and even new emergencies such as the beginning of the second wave of COVID-19 only affect this behavioral pattern to a minor extent. As a result of this COVID-19 information fatigue, strategies to keep members of institutions informed are discussed. In addition, we suggest developing a mobile app for delivering individualized information right on hand using machine learning and natural language processing strategies. In sum, individual organizations interested in keeping their members informed concerning COVID-19 should consider the use of personalized information strategies that avoid inducing negative emotional states. Moreover, potentials for connecting people using digital technology could be harnessed in local organizations.

Skulmowski Alexander, Standl Bernhard


COVIDÔÇÉ19, design, emergency, information, information seeking, page views, pandemic, searches, university, website

General General

The future of simulation-based medical education: Adaptive simulation utilizing a deep multitask neural network.

In AEM education and training

Background : In resuscitation medicine, effectively managing cognitive load in high-stakes environments has important implications for education and expertise development. There exists the potential to tailor educational experiences to an individual's cognitive processes via real-time physiologic measurement of cognitive load in simulation environments.

Objective : The goal of this research was to test a novel simulation platform that utilized artificial intelligence to deliver a medical simulation that was adaptable to a participant's measured cognitive load.

Methods : The research was conducted in 2019. Two board-certified emergency physicians and two medical students participated in a 10-minute pilot trial of a novel simulation platform. The system utilized artificial intelligence algorithms to measure cognitive load in real time via electrocardiography and galvanic skin response. In turn, modulation of simulation difficulty, determined by a participant's cognitive load, was facilitated through symptom severity changes of an augmented reality (AR) patient. A postsimulation survey assessed the participants' experience.

Results : Participants completed a simulation that successfully measured cognitive load in real time through physiological signals. The simulation difficulty was adapted to the participant's cognitive load, which was reflected in changes in the AR patient's symptoms. Participants found the novel adaptive simulation platform to be valuable in supporting their learning.

Conclusion : Our research team created a simulation platform that adapts to a participant's cognitive load in real-time. The ability to customize a medical simulation to a participant's cognitive state has potential implications for the development of expertise in resuscitation medicine.

Ruberto Aaron J, Rodenburg Dirk, Ross Kyle, Sarkar Pritam, Hungler Paul C, Etemad Ali, Howes Daniel, Clarke Daniel, McLellan James, Wilson Daryl, Szulewski Adam


Public Health Public Health

Artificial intelligence-assisted colonic endocytoscopy for cancer recognition: a multicenter study.

In Endoscopy international open

Background and study aims  Large adenomas are sometimes misidentified as cancers during colonoscopy and are surgically removed. To address this overtreatment, we developed an artificial intelligence (AI) tool that identified cancerous pathology in vivo with high specificity. We evaluated our AI tool under the supervision of a government agency to obtain regulatory approval. Patients and methods  The AI tool outputted three pathological class predictions (cancer, adenoma, or non-neoplastic) for endocytoscopic images obtained at 520-fold magnification and previously trained on 68,082 images from six academic centers. A validation test was developed, employing 500 endocytoscopic images taken from various parts of randomly selected 50 large (≥ 20 mm) colorectal lesions (10 images per lesion). An expert board labelled each of the 500 images with a histopathological diagnosis, which was made using endoscopic and histopathological images. The validation test was performed using the AI tool under a controlled environment. The primary outcome measure was the specificity in identifying cancer. Results  The validation test consisted of 30 cancers, 15 adenomas, and five non-neoplastic lesions. The AI tool could analyze 83.6 % of the images (418/500): 231 cancers, 152 adenomas, and 35 non-neoplastic lesions. Among the analyzable images, the AI tool identified the three pathological classes with an overall accuracy of 91.9 % (384/418, 95 % confidence interval [CI]: 88.8 %-94.3 %). Its sensitivity and specificity for differentiating cancer was 91.8 % (212/231, 95 % CI: 87.5 %-95.0 %) and 97.3 % (182/187, 95 % CI: 93.9 %-99.1 %), respectively. Conclusions  The newly developed AI system designed for endocytoscopy showed excellent specificity in identifying colorectal cancer.

Mori Yuichi, Kudo Shin-Ei, Misawa Masashi, Hotta Kinichi, Kazuo Ohtsuka, Saito Shoichi, Ikematsu Hiroaki, Saito Yutaka, Matsuda Takahisa, Kenichi Takeda, Kudo Toyoki, Nemoto Tetsuo, Itoh Hayato, Mori Kensaku


General General

Identifying Key Drivers of Wildfires in the Contiguous US Using Machine Learning and Game Theory Interpretation.

In Earth's future

Understanding the complex interrelationships between wildfire and its environmental and anthropogenic controls is crucial for wildfire modeling and management. Although machine learning (ML) models have yielded significant improvements in wildfire predictions, their limited interpretability has been an obstacle for their use in advancing understanding of wildfires. This study builds an ML model incorporating predictors of local meteorology, land-surface characteristics, and socioeconomic variables to predict monthly burned area at grid cells of 0.25° × 0.25° resolution over the contiguous United States. Besides these predictors, we construct and include predictors representing the large-scale circulation patterns conducive to wildfires, which largely improves the temporal correlations in several regions by 14%-44%. The Shapley additive explanation is introduced to quantify the contributions of the predictors to burned area. Results show a key role of longitude and latitude in delineating fire regimes with different temporal patterns of burned area. The model captures the physical relationship between burned area and vapor pressure deficit, relative humidity (RH), and energy release component (ERC), in agreement with the prior findings. Aggregating the contribution of predictor variables of all the grids by region, analyses show that ERC is the major contributor accounting for 14%-27% to large burned areas in the western US. In contrast, there is no leading factor contributing to large burned areas in the eastern US, although large-scale circulation patterns featuring less active upper-level ridge-trough and low RH two months earlier in winter contribute relatively more to large burned areas in spring in the southeastern US.

Wang Sally S-C, Qian Yun, Leung L Ruby, Zhang Yang


machine learning, wildfire modeling

General General

Application of intelligent algorithms in Down syndrome screening during second trimester pregnancy.

In World journal of clinical cases

BACKGROUND : Down syndrome (DS) is one of the most common chromosomal aneuploidy diseases. Prenatal screening and diagnostic tests can aid the early diagnosis, appropriate management of these fetuses, and give parents an informed choice about whether or not to terminate a pregnancy. In recent years, investigations have been conducted to achieve a high detection rate (DR) and reduce the false positive rate (FPR). Hospitals have accumulated large numbers of screened cases. However, artificial intelligence methods are rarely used in the risk assessment of prenatal screening for DS.

AIM : To use a support vector machine algorithm, classification and regression tree algorithm, and AdaBoost algorithm in machine learning for modeling and analysis of prenatal DS screening.

METHODS : The dataset was from the Center for Prenatal Diagnosis at the First Hospital of Jilin University. We designed and developed intelligent algorithms based on the synthetic minority over-sampling technique (SMOTE)-Tomek and adaptive synthetic sampling over-sampling techniques to preprocess the dataset of prenatal screening information. The machine learning model was then established. Finally, the feasibility of artificial intelligence algorithms in DS screening evaluation is discussed.

RESULTS : The database contained 31 DS diagnosed cases, accounting for 0.03% of all patients. The dataset showed a large difference between the numbers of DS affected and non-affected cases. A combination of over-sampling and under-sampling techniques can greatly increase the performance of the algorithm at processing non-balanced datasets. As the number of iterations increases, the combination of the classification and regression tree algorithm and the SMOTE-Tomek over-sampling technique can obtain a high DR while keeping the FPR to a minimum.

CONCLUSION : The support vector machine algorithm and the classification and regression tree algorithm achieved good results on the DS screening dataset. When the T21 risk cutoff value was set to 270, machine learning methods had a higher DR and a lower FPR than statistical methods.

Zhang Hong-Guo, Jiang Yu-Ting, Dai Si-Da, Li Ling, Hu Xiao-Nan, Liu Rui-Zhi


Algorithms, Classification and regression tree, Down syndrome, Prenatal screening, Risk cutoff value, Support vector machine

Cardiology Cardiology

Coronary Plaque Characterization From Optical Coherence Tomography Imaging With a Two-Pathway Cascade Convolutional Neural Network Architecture.

In Frontiers in cardiovascular medicine

Background: The morphological structure and tissue composition of a coronary atherosclerotic plaque determine its stability, which can be assessed by intravascular optical coherence tomography (OCT) imaging. However, plaque characterization relies on the interpretation of large datasets by well-trained observers. This study aims to develop a convolutional neural network (CNN) method to automatically extract tissue features from OCT images to characterize the main components of a coronary atherosclerotic plaque (fibrous, lipid, and calcification). The method is based on a novel CNN architecture called TwopathCNN, which is utilized in a cascaded structure. According to the evaluation, this proposed method is effective and robust in the characterization of coronary plaque composition from in vivo OCT imaging. On average, the method achieves 0.86 in F1-score and 0.88 in accuracy. The TwopathCNN architecture and cascaded structure show significant improvement in performance (p < 0.05). CNN with cascaded structure can greatly improve the performance of characterization compared to the conventional CNN methods and machine learning methods. This method has a higher efficiency, which may be proven to be a promising diagnostic tool in the detection of coronary plaques.

Yin Yifan, He Chunliu, Xu Biao, Li Zhiyong


cascaded structure, convolutional neural network, optical coherence tomography, plaque characterization, two-pathway architecture