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

General General

Diagnostic performance of artificial intelligence-based computer-aided diagnosis system in longitudinal and transverse ultrasonic views for differentiating thyroid nodules.

In Frontiers in endocrinology ; h5-index 55.0

OBJECTIVE : To evaluate the diagnostic performance of different ultrasound sections of thyroid nodule (TN) using computer-aided diagnosis system based on artificial intelligence (AI-CADS) in predicting thyroid malignancy.

MATERIALS AND METHODS : This is a retrospective study. From January 2019 to July 2019, patients with preoperative thyroid ultrasound data and postoperative pathological results were enrolled, which were divided into two groups: lower risk group (ACR TI-RADS 1, 2 and 3) and higher risk group (ACR TI-RADS 4 and 5). The malignant risk scores (MRS) of TNs were obtained from longitudinal and transverse sections using AI-CADS. The diagnostic performance of AI-CADS and the consistency of each US characteristic were evaluated between these sections. The receiver operating characteristic (ROC) curve and the Cohen κ-statistic were performed.

RESULTS : A total of 203 patients (45.61 ± 11.59 years, 163 female) with 221 TNs were enrolled. The area under the ROC curve (AUC) of criterion 3 [0.86 (95%CI: 0.80~0.91)] was lower than criterion 1 [0.94 (95%CI: 0.90~ 0.99)], 2 [0.93 (95%CI: 0.89~0.97)] and 4 [0.94 (95%CI: 0.90, 0.99)] significantly (P<0.001, P=0.01, P<0.001, respectively). In the higher risk group, the MRS of transverse section was higher than longitudinal section (P<0.001), and the agreement of extrathyroidal extension and shape was moderate and fair (κ =0.48, 0.31 respectively). The diagnostic agreement of other ultrasonic features was substantial or almost perfect (κ >0.60).

CONCLUSION : The diagnostic performance of computer-aided diagnosis system based on artificial intelligence (AI-CADS) in longitudinal and transverse ultrasonic views for differentiating thyroid nodules (TN) was different, which was higher in the transverse section. It was more dependent on the section for the AI-CADS diagnosis of suspected malignant TNs.

Zheng Lin-Lin, Ma Su-Ya, Zhou Ling, Yu Cong, Xu Hai-Shan, Xu Li-Long, Li Shi-Yan

2023

artificial intelligence (AI), computer-aided diagnosis system (CAD), thyroid nodule, transverse, ultrasound

General General

The voice of COVID-19: Breath and cough recording classification with temporal decision trees and random forests.

In Artificial intelligence in medicine ; h5-index 34.0

Symbolic learning is the logic-based approach to machine learning, and its mission is to provide algorithms and methodologies to extract logical information from data and express it in an interpretable way. Interval temporal logic has been recently proposed as a suitable tool for symbolic learning, specifically via the design of an interval temporal logic decision tree extraction algorithm. In order to improve their performances, interval temporal decision trees can be embedded into interval temporal random forests, mimicking the corresponding schema at the propositional level. In this article we consider a dataset of cough and breath sample recordings of volunteer subjects, labeled with their COVID-19 status, originally collected by the University of Cambridge. By interpreting such recordings as multivariate time series, we study the problem of their automated classification using interval temporal decision trees and forests. While this problem has been approached with the same dataset as well as with other datasets, in all cases, non-symbolic learning methods (usually, deep learning-based) have been applied to solve it; in this article we apply a symbolic approach, and show that it does not only outperform the state-of-the-art obtained with the same dataset, but its results are also superior to those of most non-symbolic techniques applied on other datasets. As an added bonus, thanks to the symbolic nature of our approach, we are also able to extract explicit knowledge to help physicians characterize typical COVID-positive cough and breath.

Manzella F, Pagliarini G, Sciavicco G, Stan I E

2023-Mar

COVID-19, Interval temporal decision trees and forests, Symbolic models

General General

Measuring cognitive load of digital interface combining event-related potential and BubbleView.

In Brain informatics

Helmet mounted display systems (HMDs) are high-performance display devices for modern aircraft. We propose a novel method combining event-related potentials (ERPs) and BubbleView to measure cognitive load under different HMD interfaces. The distribution of the subjects' attention resources is reflected by analyzing the BubbleView, and the input of the subjects' attention resources on the interface is reflected by analyzing the ERP's P3b and P2 components. The results showed that the HMD interface with more symmetry and a simple layout had less cognitive load, and subjects paid more attention to the upper portion of the interface. Combining the experimental data of ERP and BubbleView, we can obtain a more comprehensive, objective, and reliable HMD interface evaluation result. This approach has significant implications for the design of digital interfaces and can be utilized for the iterative evaluation of HMD interfaces.

Wei Shaoyu, Zheng Ruiling, Li Rui, Shi Minghui, Zhang Junsong

2023-Mar-03

Cognitive load, Event-related potential, Eye tracking, Graphical user interface, Helmet mounted display systems

Public Health Public Health

Results of the COVID-19 mental health international for the health professionals (COMET-HP) study: depression, suicidal tendencies and conspiracism.

In Social psychiatry and psychiatric epidemiology

INTRODUCTION : The current study aimed to investigate the rates of anxiety, clinical depression, and suicidality and their changes in health professionals during the COVID-19 outbreak.

MATERIALS AND METHODS : The data came from the larger COMET-G study. The study sample includes 12,792 health professionals from 40 countries (62.40% women aged 39.76 ± 11.70; 36.81% men aged 35.91 ± 11.00 and 0.78% non-binary gender aged 35.15 ± 13.03). Distress and clinical depression were identified with the use of a previously developed cut-off and algorithm, respectively.

STATISTICAL ANALYSIS : Descriptive statistics were calculated. Chi-square tests, multiple forward stepwise linear regression analyses, and Factorial Analysis of Variance (ANOVA) tested relations among variables.

RESULTS : Clinical depression was detected in 13.16% with male doctors and 'non-binary genders' having the lowest rates (7.89 and 5.88% respectively) and 'non-binary gender' nurses and administrative staff had the highest (37.50%); distress was present in 15.19%. A significant percentage reported a deterioration in mental state, family dynamics, and everyday lifestyle. Persons with a history of mental disorders had higher rates of current depression (24.64% vs. 9.62%; p < 0.0001). Suicidal tendencies were at least doubled in terms of RASS scores. Approximately one-third of participants were accepting (at least to a moderate degree) a non-bizarre conspiracy. The highest Relative Risk (RR) to develop clinical depression was associated with a history of Bipolar disorder (RR = 4.23).

CONCLUSIONS : The current study reported findings in health care professionals similar in magnitude and quality to those reported earlier in the general population although rates of clinical depression, suicidal tendencies, and adherence to conspiracy theories were much lower. However, the general model of factors interplay seems to be the same and this could be of practical utility since many of these factors are modifiable.

N Fountoulakis Konstantinos, N Karakatsoulis Grigorios, Abraham Seri, Adorjan Kristina, Ahmed Helal Uddin, Alarcón Renato D, Arai Kiyomi, Auwal Sani Salihu, Bobes Julio, Bobes-Bascaran Teresa, Bourgin-Duchesnay Julie, Bredicean Cristina Ana, Bukelskis Laurynas, Burkadze Akaki, Cabrera Abud Indira Indiana, Castilla-Puentes Ruby, Cetkovich Marcelo, Colon-Rivera Hector, Corral Ricardo, Cortez-Vergara Carla, Crepin Piirika, de Berardis Domenico, Zamora Delgado Sergio, de Lucena David, de Sousa Avinash, di Stefano Ramona, Dodd Seetal, Elek Livia Priyanka, Elissa Anna, Erdelyi-Hamza Berta, Erzin Gamze, Etchevers Martin J, Falkai Peter, Farcas Adriana, Fedotov Ilya, Filatova Viktoriia, Fountoulakis Nikolaos K, Frankova Iryna, Franza Francesco, Frias Pedro, Galako Tatiana, Garay Cristian J, Garcia-Álvarez Leticia, García-Portilla Paz, Gonda Xenia, Gondek Tomasz M, Morera González Daniela, Gould Hilary, Grandinetti Paolo, Grau Arturo, Groudeva Violeta, Hagin Michal, Harada Takayuki, Hasan Tasdik M, Azreen Hashim Nurul, Hilbig Jan, Hossain Sahadat, Iakimova Rossitza, Ibrahim Mona, Iftene Felicia, Ignatenko Yulia, Irarrazaval Matias, Ismail Zaliha, Ismayilova Jamila, Jacobs Asaf, Jakovljević Miro, Jakšić Nenad, Javed Afzal, Yilmaz Kafali Helin, Karia Sagar, Kazakova Olga, Khalifa Doaa, Khaustova Olena, Koh Steve, Kopishinskaia Svetlana, Kosenko Korneliia, Koupidis Sotirios A, Kovacs Illes, Kulig Barbara, Lalljee Alisha, Liewig Justine, Majid Abdul, Malashonkova Evgeniia, Malik Khamelia, Iqbal Malik Najma, Mammadzada Gulay, Mandalia Bilvesh, Marazziti Donatella, Marčinko Darko, Martinez Stephanie, Matiekus Eimantas, Mejia Gabriela, Memon Roha Saeed, Meza Martínez Xarah Elenne, Mickevičiūtė Dalia, Milev Roumen, Mohammed Muftau, Molina-López Alejandro, Morozov Petr, Muhammad Nuru Suleiman, Mustač Filip, Naor Mika S, Nassieb Amira, Navickas Alvydas, Okasha Tarek, Pandova Milena, Panfil Anca-Livia, Panteleeva Liliya, Papava Ion, Patsali Mikaella E, Pavlichenko Alexey, Pejuskovic Bojana, Pinto da Costa Mariana, Popkov Mikhail, Popovic Dina, Raduan Nor Jannah Nasution, Vargas Ramírez Francisca, Rancans Elmars, Razali Salmi, Rebok Federico, Rewekant Anna, Reyes Flores Elena Ninoska, Rivera-Encinas María Teresa, Saiz Pilar A, Sánchez de Carmona Manuel, Saucedo Martínez David, Saw Jo Anne, Saygili Görkem, Schneidereit Patricia, Shah Bhumika, Shirasaka Tomohiro, Silagadze Ketevan, Sitanggang Satti, Skugarevsky Oleg, Spikina Anna, Mahalingappa Sridevi Sira, Stoyanova Maria, Szczegielniak Anna, Tamasan Simona Claudia, Tavormina Giuseppe, Tavormina Maurilio Giuseppe Maria, Theodorakis Pavlos N, Tohen Mauricio, Tsapakis Eva-Maria, Tukhvatullina Dina, Ullah Irfan, Vaidya Ratnaraj, Vega-Dienstmaier Johann M, Vrublevska Jelena, Vukovic Olivera, Vysotska Olga, Widiasih Natalia, Yashikhina Anna, Prezerakos Panagiotis E, Berk Michael, Levaj Sarah, Smirnova Daria

2023-Mar-03

Anxiety, COVID-19, Conspiracy theories, Depression, Health professionals, Mental disorders, Mental health, Psychiatry, Suicidality

General General

Flexible Organic-Inorganic Halide Perovskite-Based Diffusive Memristor for Artificial Nociceptors.

In ACS applied materials & interfaces ; h5-index 147.0

With the current evolution in the artificial intelligence technology, more biomimetic functions are essential to execute increasingly complicated tasks and respond to challenging work environments. Therefore, an artificial nociceptor plays a significant role in the advancement of humanoid robots. Organic-inorganic halide perovskites (OHPs) have the potential to mimic the biological neurons due to their inherent ion migration. Herein, a versatile and reliable diffusive memristor built on an OHP is reported as an artificial nociceptor. This OHP diffusive memristor showed threshold switching properties with excellent uniformity, forming-free behavior, a high ION/IOFF ratio (104), and bending endurance over >102 cycles. To emulate the biological nociceptor functionalities, four significant characteristics of the artificial nociceptor, such as threshold, no adaptation, relaxation, and sensitization, are demonstrated. Further, the feasibility of OHP nociceptors in artificial intelligence is being investigated by fabricating a thermoreceptor system. These findings suggest a prospective application of an OHP-based diffusive memristor in the future neuromorphic intelligence platform.

Patil Harshada, Kim Honggyun, Kadam Kalyani D, Rehman Shania, Patil Supriya A, Aziz Jamal, Dongale Tukaram D, Ali Sheikh Zulfqar, Khalid Rahmani Mehr, Khan Muhammad Farooq, Kim Deok-Kee

2023-Mar-03

artificial nociceptors, flexible diffusive memristor, organic−inorganic perovskite (OHP), thermoreceptors, threshold switching

General General

Molecular template growth of organic heterojunctions to tailor visual neuroplasticity for high performance phototransistors with ultralow energy consumption.

In Nanoscale horizons

The optical and charge transport properties of organic semiconductors are strongly influenced by their morphology and molecular structures. Here we report the influence of a molecular template strategy on anisotropic control via weak epitaxial growth of a semiconducting channel for a dinaphtho[2,3-b:2',3'-f]thieno[3,2-b]thiophene (DNTT)/para-sexiphenyl (p-6P) heterojunction. The aim is to improve charge transport and trapping, to enable tailoring of visual neuroplasticity. The proposed phototransistor devices, comprising a molecular heterojunction with optimized molecular template thickness, exhibited an excellent memory ratio (ION/IOFF) and retention characteristics in response to light stimulation, owing to the enhanced orientation/packing of DNTT molecules and a favorable match between the LUMO/HOMO levels of p-6P and DNTT. The best performing heterojunction exhibits visual synaptic functionalities, including an extremely high pair-pulse facilitation index of ∼206%, ultralow energy consumption of 0.54 fJ, and zero-gate operation, under ultrashort pulse light stimulation to mimic human-like sensing, computing, and memory functions. An array of heterojunction photosynapses possess a high degree of visual pattern recognition and learning, to mimic the neuroplasticity of human brain activities through a rehearsal learning process. This study provides a guide to the design of molecular heterojunctions for tailoring high-performance photonic memory and synapses for neuromorphic computing and artificial intelligence systems.

Ercan Ender, Hung Chih-Chien, Li Guan-Syuan, Yang Yun-Fang, Lin Yan-Cheng, Chen Wen-Chang

2023-Mar-03