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

Surgery Surgery

Reinforcement learning in surgery.

In Surgery ; h5-index 54.0

Patients and physicians make essential decisions regarding diagnostic and therapeutic interventions. These actions should be performed or deferred under time constraints and uncertainty regarding patients' diagnoses and predicted response to treatment. This may lead to cognitive and judgment errors. Reinforcement learning is a subfield of machine learning that identifies a sequence of actions to increase the probability of achieving a predetermined goal. Reinforcement learning has the potential to assist in surgical decision making by recommending actions at predefined intervals and its ability to utilize complex input data, including text, image, and temporal data, in the decision-making process. The algorithm mimics a human trial-and-error learning process to calculate optimum recommendation policies. The article provides insight regarding challenges in the development and application of reinforcement learning in the medical field, with an emphasis on surgical decision making. The review focuses on challenges in formulating reward function describing the ultimate goal and determination of patient states derived from electronic health records, along with the lack of resources to simulate the potential benefits of suggested actions in response to changing physiological states during and after surgery. Although clinical implementation would require secure, interoperable, livestreaming electronic health record data for use by virtual model, development and validation of personalized reinforcement learning models in surgery can contribute to improving care by helping patients and clinicians make better decisions.

Datta Shounak, Li Yanjun, Ruppert Matthew M, Ren Yuanfang, Shickel Benjamin, Ozrazgat-Baslanti Tezcan, Rashidi Parisa, Bihorac Azra


General General

Machine-Learning-Driven Simulations on Microstructure and Thermophysical Properties of MgCl2-KCl Eutectic.

In ACS applied materials & interfaces ; h5-index 147.0

Theoretical studies on the MgCl2-KCl eutectic heavily rely on ab initio calculations based on density functional theory (DFT). However, neither large-scale nor long-time calculations are feasible in the framework of the ab initio method, which makes it challenging to accurately predict some properties. To address this issue, a scheme based on ab initio calculation, deep neural networks, and machine learning is introduced. By training on high-quality data sets generated by ab initio calculations, a deep potential (DP) is constructed to describe the interaction between atoms. This work shows that the DP enables higher efficiency and similar accuracy relative to DFT. By performing molecular dynamics simulations with DP, the microstructure and thermophysical properties of the MgCl2-KCl eutectic (32:68 mol %) are investigated. The structural evolution with temperature is analyzed through partial radial distribution functions, coordination numbers, angular distribution functions, and structural factors. Meanwhile, the estimated thermophysical properties are discussed, including density, thermal expansion coefficient, shear viscosity, self-diffusion coefficient, and specific heat capacity. It reveals that the Mg2+ ions in this system have a distorted tetrahedral geometry rather than an octahedral one (with vacancies). The microstructure of the MgCl2-KCl eutectic shows the feature of medium-range order, and this feature will be enhanced at a higher temperature. All predicted thermophysical properties are in good agreement with the experimental results. The hydrodynamic radius determined from the shear viscosity and self-diffusion coefficient shows that the Mg2+ ions have a strong local structure and diffuse as if with an intact coordination shell. Overall, this work provides a thorough understanding of the microstructure and enriches the data of the thermophysical properties of the MgCl2-KCl eutectic.

Liang Wenshuo, Lu Guimin, Yu Jianguo


MgCl2−KCl eutectic, deep potential, machine learning, microstructure, thermophysical properties

Radiology Radiology

Artificial intelligence in breast ultrasonography.

In Ultrasonography (Seoul, Korea)

Although breast ultrasonography is the mainstay modality for differentiating between benign and malignant breast masses, it has intrinsic problems with false positives and substantial interobserver variability. Artificial intelligence (AI), particularly with deep learning models, is expected to improve workflow efficiency and serve as a second opinion. AI is highly useful for performing three main clinical tasks in breast ultrasonography: detection (localization/ segmentation), differential diagnosis (classification), and prognostication (prediction). This article provides a current overview of AI applications in breast ultrasonography, with a discussion of methodological considerations in the development of AI models and an up-to-date literature review of potential clinical applications.

Kim Jaeil, Kim Hye Jung, Kim Chanho, Kim Won Hwa


Artificial intelligence, Breast diseases, Breast neoplasm, Convolutional neural network, Ultrasonography

General General

Artificial Intelligence in Lower Gastrointestinal Endoscopy: The Current Status and Future Perspective.

In Clinical endoscopy

The present manuscript aims to review the history, recent advances, evidence, and challenges of artificial intelligence (AI) in colonoscopy. Although it is mainly focused on polyp detection and characterization, it also considers other potential applications (i.e., inflammatory bowel disease) and future perspectives. Some of the most recent algorithms show promising results that are similar to human expert performance. The integration of AI in routine clinical practice will be challenging, with significant issues to overcome (i.e., regulatory, reimbursement). Medico-legal issues will also need to be addressed. With the exception of an AI system that is already available in selected countries (GI Genius; Medtronic, Minneapolis, MN, USA), the majority of the technology is still in its infancy and has not yet been proven to reach a sufficient diagnostic performance to be adopted in the clinical practice. However, larger players will enter the arena of AI in the next few months.

Milluzzo Sebastian Manuel, Cesaro Paola, Grazioli Leonardo Minelli, Olivari Nicola, Spada Cristiano


Artificial intelligence, Colon capsule endoscopy, Colonoscopy, Endoscopy

Radiology Radiology

Accurate automated diagnosis of carpal tunnel syndrome using radiomics features with ultrasound images: A comparison with radiologists' assessment.

In European journal of radiology ; h5-index 47.0

PURPOSE : Ultrasonography is the most common imaging modality used to diagnose carpal tunnel syndrome (CTS). Recently artificial intelligence algorithms have been used to diagnose musculoskeletal diseases accurately without human errors using medical images. In this work, a computer-aided diagnosis (CAD) system is developed using radiomics features extracted from median nerves (MN) to diagnose CTS accurately.

METHOD : This study is performed on 228 wrists from 65 patients and 57 controls, with an equal number of control and CTS wrists. Nerve conduction study (NCS) is considered as the gold standard in this study. Two radiologists used two guides to evaluate and categorize the pattern and echogenicity of MNs. Radiomics features are extracted from B-mode ultrasound images (Ultrasomics), and the robust features are fed into support vector machine classifier for automated classification. The diagnostic performances of two radiologists and the CAD system are evaluated using ROC analysis.

RESULTS : The agreement of two radiologists was excellent for both guide 1 and 2. The honey-comb pattern clearly appeared in control wrists (based on guide 1). In addition, CTS wrists indicated significantly lower number of fascicles in MNs (based on guide 2). The area under ROC curve (AUC) of the radiologist 1 and 2 are 0.658 and 0.667 based on guide 1 and 0.736 and 0.721 based on guide 2, respectively. The CAD system indicated higher performance than two radiologists with AUC of 0.926.

CONCLUSION : The proposed CAD system shows the benefit of using ultrasomics features and can assist radiologists to diagnose CTS accurately.

Faeghi Fariborz, Ardakani Ali Abbasian, Acharya U Rajendra, Mirza-Aghazadeh-Attari Mohammad, Abolghasemi Jamileh, Ejtehadifar Sajjad, Mohammadi Afshin


Artificial intelligence, Carpal tunnel syndrome, Machine learning, Median nerve, Ultrasonography

Public Health Public Health

An interpretable self-adaptive deep neural network for estimating daily spatially-continuous PM2.5 concentrations across China.

In The Science of the total environment

Accurate estimation of daily spatially-continuous PM2.5 (fine particulate matter) concentration is a prerequisite to address environmental public health issues, and satellite-based aerosol optical depth (AOD) products have been widely used to estimate PM2.5 concentrations using statistical-based or machine learning-based models. However, statistical-based models oversimplify the AOD-PM2.5 relationships, whereas complex machine learning technologies ignore the spatiotemporal heterogeneity of the predictors and demonstrate shortage in interpretation. Besides, large AOD data gaps resulting in PM2.5 estimation biases have been seldom imputed in previous studies, especially at national scales. To fill the above research gaps, this study attempts to present a feasible methodology to estimate daily spatially-continuous PM2.5 concentrations in China. The AOD data gaps across China were first imputed via a random forest (RF) model. Then, an interpretable self-adaptive deep neural network (SADNN) model, incorporating AOD, meteorological and other auxiliary predictors, was developed to estimate daily spatially-continuous PM2.5 concentrations from 2017 to 2018. Five-fold sample (site)-based cross-validation results showed a high accuracy of the SADNN model, with coefficient of determination and root mean square error values equal to 0.86 (0.84) and 13.07 (14.30) μg/m3, respectively, outperforming the standard DNN and the RF model. Furthermore, the SADNN model identified the spatiotemporal patterns of predictor importance, and demonstrated that the boundary layer height, elevation and AOD were the most important predictors both spatially and temporally. And the predictor importance in the Qinghai-Tibet Plateau was different from that in the rest of China. These results enhance our understanding of AOD-PM2.5 relationships and elucidate the estimated PM2.5 datasets with complete coverage are applicable for related air pollution studies and epidemiological cohort studies. Moreover, considering the effective nonlinear model capability and interpretability, the SADNN model is beneficial for not only PM2.5 estimation but also other earth data and scenarios.

Chen Binjie, You Shixue, Ye Yang, Fu Yongyong, Ye Ziran, Deng Jinsong, Wang Ke, Hong Yang


Aerosol optical depth (AOD), Attention module, Deep learning, Gap-filling, Particulate matter, Predictor importance