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

General General

Classification of the Multiple Stages of Parkinson's Disease by a Deep Convolution Neural Network Based on 99mTc-TRODAT-1 SPECT Images.

In Molecules (Basel, Switzerland)

Single photon emission computed tomography (SPECT) has been employed to detect Parkinson's disease (PD). However, analysis of the SPECT PD images was mostly based on the region of interest (ROI) approach. Due to limited size of the ROI, especially in the multi-stage classification of PD, this study utilizes deep learning methods to establish a multiple stages classification model of PD. In the retrospective study, the 99mTc-TRODAT-1 was used for brain SPECT imaging. A total of 202 cases were collected, and five slices were selected for analysis from each subject. The total number of images was thus 1010. According to the Hoehn and Yahr Scale standards, all the cases were divided into healthy, early, middle, late four stages, and HYS I~V six stages. Deep learning is compared with five convolutional neural networks (CNNs). The input images included grayscale and pseudo color of two types. The training and validation sets were 70% and 30%. The accuracy, recall, precision, F-score, and Kappa values were used to evaluate the models' performance. The best accuracy of the models based on grayscale and color images in four and six stages were 0.83 (AlexNet), 0.85 (VGG), 0.78 (DenseNet) and 0.78 (DenseNet).

Hsu Shih-Yen, Yeh Li-Ren, Chen Tai-Been, Du Wei-Chang, Huang Yung-Hui, Twan Wen-Hung, Lin Ming-Chia, Hsu Yun-Hsuan, Wu Yi-Chen, Chen Huei-Yung


Parkinson’s disease, SPECT, convolution neural network, deep learning

oncology Oncology

Identification of A Methylation Panel Aid in Risk Stratification in Node-positive Penile Squamous Cell Carcinoma.

In International journal of cancer ; h5-index 82.0

Molecular prognostic factors for individualized treatment of Squamous Cell Carcinoma (SCC) are poorly defined. This study developed and validated a novel molecular tools aid in pre- and post- inguinal lymphadenectomy risk stratification in node-positive penile SCC. Patients with node-positive penile SCC who underwent inguinal or ilioinguinal lymphadenectomy were divided into three cohorts: a discovery set, a development set and a validation set. The local ethics committee approved the study. The primary endpoint was cancer-specific survival (CSS). At the discovery stage, 17 CpG sites were significantly associated with CSS. In the development set, we constructed a 3-CpG-based prognostic score for survival prediction. The hazard ratio (HR) of the panel (dichotomized using the optimal cutoff) was 5.8 in the multivariate analyses (p<0.001). The addition of the methylation score significantly improved the pN-stage C-index from 0.70 to 0.79 (incremental C=0.09, p<0.001). In the validation set, the methylation panel showed a HR of 9.9 in the multivariate analyses. The addition of the molecular marker improved the pN-stage C-index from 0.69 to 0.78 (incremental C=0.09, p<0.001). The methylation score remarkably separated survival curves in different pN stages, which indicate the tool can be applied to tailor the treatment in both pre- and post- inguinal lymphadenectomy settings. We developed and validated a prognostic methylation panel for node-positive penile SCC. The tool may aid in the risk stratification of the population with heterogeneous outcomes and needs prospective validation. Patients in high risk group may benefit from more aggressive therapy or clinical trials.

Gu Weijie, Wan Fangning, Chen Jun, Gan Hualei, Wang Beihe, Wei Yu, Zhang Guiming, Zhou Jiaquan, Ding Xuefei, Zhang Peipei, Jin Shengming, Xu Qinghua, Ye Dingwei, Zhu Yao


General General

The psychology of professional and student actors: Creativity, personality, and motivation.

In PloS one ; h5-index 176.0

As a profession, acting is marked by a high-level of economic and social riskiness concomitantly with the possibility for artistic satisfaction and/or public admiration. Current understanding of the psychological attributes that distinguish professional actors is incomplete. Here, we compare samples of professional actors (n = 104), undergraduate student actors (n = 100), and non-acting adults (n = 92) on 26 psychological dimensions and use machine-learning methods to classify participants based on these attributes. Nearly all of the attributes measured here displayed significant univariate mean differences across the three groups, with the strongest effect sizes being on Creative Activities, Openness, and Extraversion. A cross-validated Least Absolute Shrinkage and Selection Operator (LASSO) classification model was capable of identifying actors (either professional or student) from non-actors with a 92% accuracy and was able to sort professional from student actors with a 96% accuracy when age was included in the model, and a 68% accuracy with only psychological attributes included. In these LASSO models, actors in general were distinguished by high levels of Openness, Assertiveness, and Elaboration, but professional actors were specifically marked by high levels of Originality, Volatility, and Literary Activities.

Dumas Denis, Doherty Michael, Organisciak Peter


Public Health Public Health

Recent Practice Patterns and Variations in Children Hospitalized for Asthma Exacerbation in Japan.

In International archives of allergy and immunology

BACKGROUND : High antibiotic prescribing rates for adults with an asthma exacerbation have been reported in developed countries, but few studies have assessed the variation of antibiotic and adjunctive treatment in the routine care of children.

OBJECTIVE : We evaluated the trends in health resource utilization for children hospitalized for asthma exacerbation, ascertained the variations of practices across hospitals and geographic location, and classified these different patterns at hospital levels.

METHODS : Using data on Japanese children hospitalized for asthma exacerbation with no indication of bacterial infection during 2010-2018, we conducted a retrospective observational study to assess the trends in initial treatment patterns and their variations. Mixed-effect generalized linear models were used to investigate the treatment trends. Hierarchical cluster analyses were performed to classify the treatment variations across hospitals.

RESULTS : Overall, 54,981 children were eligible for the study. Proportions of antibiotic use decreased from 47.2% in 2010 to 26.9% in 2018. Similarly, utilization of antitussives, antihistamines, and methylxanthine showed decreasing trends over the period, whereas the use of mucolytics and ambroxol increased. These treatment variations were more considerable in hospital levels than in 47 prefecture levels. Hierarchical cluster analyses classified these patterns into 6 groups, mostly based on mediator release inhibitor, ambroxol, and antitussives.

CONCLUSIONS : Wide variations in antibiotics and adjunctive treatments were observed across hospital levels. Our findings support the improvement in reducing inappropriate antibiotic use and highlight the need for comparative effectiveness research of the adjunctive treatments among children hospitalized for asthma.

Okubo Yusuke, Horimukai Kenta, Michihata Nobuaki, Morita Kojiro, Matsui Hiroki, Fushimi Kiyohide, Yasunaga Hideo


Machine learning, Pediatric asthma, Treatment pattern

General General

A bioelectric neural interface towards intuitive prosthetic control for amputees.

In Journal of neural engineering ; h5-index 52.0

OBJECTIVE : While prosthetic hands with independently actuated digits have become commercially available, state-of-the-art human-machine interfaces (HMI) only permit control over a limited set of grasp patterns, which does not enable amputees to experience sufficient improvement in their daily activities to make an active prosthesis useful.

APPROACH : Here we present a technology platform combining fully-integrated bioelectronics, implantable intrafascicular microelectrodes and deep learning-based artificial intelligence (AI) to facilitate this missing bridge by tapping into the intricate motor control signals of peripheral nerves. The bioelectric neural interface includes an ultra-low-noise neural recording system to sense electroneurography (ENG) signals from microelectrode arrays implanted in the residual nerves, and AI models employing the recurrent neural network (RNN) architecture to decode the subject's motor intention.

MAIN RESULTS : A pilot human study has been carried out on a transradial amputee. We demonstrate that the information channel established by the proposed neural interface is sufficient to provide high accuracy control of a prosthetic hand up to 15 degrees of freedom (DOF). The interface is intuitive as it directly maps complex prosthesis movements to the patient's true intention.

SIGNIFICANCE : Our study layouts the foundation towards not only a robust and dexterous control strategy for modern neuroprostheses at a near-natural level approaching that of the able hand, but also an intuitive conduit for connecting human minds and machines through the peripheral neural pathways. (Clinical trial identifier: NCT02994160).

Nguyen Anh Tuan, Xu Jian, Jiang Ming, Luu Diu Khue, Wu Tong, Tam Wing-Kin, Zhao Wenfeng, Drealan Markus W, Overstreet Cynthia K, Zhao Qi, Cheng Jonathan, Keefer Edward, Yang Zhi


artificial intelligence, fully-integrated bioelectronics, human-machine interface, intrafascicular microelectrodes, intuitive control, neural decoder, peripheral neural pathways

Radiology Radiology

Automatic classification of scanned electronic health record documents.

In International journal of medical informatics ; h5-index 49.0

OBJECTIVES : Electronic Health Records (EHRs) contain scanned documents from a variety of sources such as identification cards, radiology reports, clinical correspondence, and many other document types. We describe the distribution of scanned documents at one health institution and describe the design and evaluation of a system to categorize documents into clinically relevant and non-clinically relevant categories as well as further sub-classifications. Our objective is to demonstrate that text classification systems can accurately classify scanned documents.

METHODS : We extracted text using Optical Character Recognition (OCR). We then created and evaluated multiple text classification machine learning models, including both "bag of words" and deep learning approaches. We evaluated the system on three different levels of classification using both the entire document as input, as well as the individual pages of the document. Finally, we compared the effects of different text processing methods.

RESULTS : A deep learning model using ClinicalBERT performed best. This model distinguished between clinically-relevant documents and not clinically-relevant documents with an accuracy of 0.973; between intermediate sub-classifications with an accuracy of 0.949; and between individual classes with an accuracy of 0.913.

DISCUSSION : Within the EHR, some document categories such as "external medical records" may contain hundreds of scanned pages without clear document boundaries. Without further sub-classification, clinicians must view every page or risk missing clinically-relevant information. Machine learning can automatically classify these scanned documents to reduce clinician burden.

CONCLUSION : Using machine learning applied to OCR-extracted text has the potential to accurately identify clinically-relevant scanned content within EHRs.

Goodrum Heath, Roberts Kirk, Bernstam Elmer V


Classification, Electronic health records, Machine learning, Optical character recognition, Patient safety, Scanned documents