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

Pathology Pathology

Application of Radiomics and Artificial Intelligence for Lung Cancer Precision Medicine.

In Cold Spring Harbor perspectives in medicine

Medical imaging is the standard-of-care for early detection, diagnosis, treatment planning, monitoring, and image-guided interventions of lung cancer patients. Most medical images are stored digitally in a standardized Digital Imaging and Communications in Medicine format that can be readily accessed and used for qualitative and quantitative analysis. Over the several last decades, medical images have been shown to contain complementary and interchangeable data orthogonal to other sources such as pathology, hematology, genomics, and/or proteomics. As such, "radiomics" has emerged as a field of research that involves the process of converting standard-of-care images into quantitative image-based data that can be merged with other data sources and subsequently analyzed using conventional biostatistics or artificial intelligence (AI) methods. As radiomic features capture biological and pathophysiological information, these quantitative radiomic features have shown to provide rapid and accurate noninvasive biomarkers for lung cancer risk prediction, diagnostics, prognosis, treatment response monitoring, and tumor biology. In this review, radiomics and emerging AI methods in lung cancer research are highlighted and discussed including advantages, challenges, and pitfalls.

Tunali Ilke, Gillies Robert J, Schabath Matthew B


Pathology Pathology

Analysis of multidrug resistance in Staphylococcus aureus with a machine learning generated antibiogram.

In Antimicrobial agents and chemotherapy ; h5-index 79.0

Multidrug resistance (MDR) surveillance consists of reporting MDR prevalence and MDR phenotypes. Detailed knowledge of the specific associations underlying MDR patterns can allow antimicrobial stewardship programs to accurately identify clinically relevant resistance patterns. We applied machine learning and graphical networks to quantify and visualize associations between resistance traits in a set of 1,091 Staphylococcus aureus isolates collected from one New York hospital between 2008 and 2018. Antimicrobial susceptibility testing was performed using reference broth microdilution. The isolates were analyzed by year, methicillin susceptibility, and infection site. Association mining was used to identify resistance patterns that consisted of two or more individual antimicrobial resistance (AMR) traits and quantify the association among the individual resistance traits in each pattern. The resistance patterns captured the majority of the most common MDR phenotypes and reflected previously identified pairwise relationships between AMR traits in S. aureus Associations between β-lactams and other antimicrobial classes (macrolides, lincosamides, and fluoroquinolones) were common, although the strength of the association among these antimicrobial classes varied by infection site and by methicillin susceptibility. Association mining identified associations between clinically important AMR traits, which could be further investigated for evidence of resistance co-selection. For example, in skin and skin structure infections, clindamycin and tetracycline resistance occurred together 1.5 times more often than expected if they were independent from one another. Association mining efficiently discovered and quantified associations among resistance traits; allowing these associations to be compared between relevant subsets of isolates to identify and track clinically relevant MDR.

Cazer Casey L, Westblade Lars F, Simon Matthew S, Magleby Reed, Castanheira Mariana, Booth James G, Jenkins Stephen G, Gröhn Yrjö T


Surgery Surgery

A machine learning approach yields a multiparameter prognostic marker in liver cancer.

In Cancer immunology research ; h5-index 78.0

A number of staging systems have been developed to predict clinical outcomes in hepatocellular carcinoma (HCC). However, no general consensus has been reached regarding the optimal model. New approaches such as machine learning (ML) strategies are powerful tools for incorporating risk factors from multiple platforms. We retrospectively reviewed the baseline information, including clinicopathologic characteristics, laboratory parameters, and peripheral immune features reflecting T-cell function, from three HCC cohorts. A gradient-boosting survival (GBS) classifier was trained with prognosis-related variables in the training dataset and validated in two independent cohorts. We constructed a 20-feature GBS model classifier incorporating 1 clinical feature, 14 laboratory parameters, and 5 T-cell function parameters obtained from peripheral blood mononuclear cells (PBMCs). The GBS model-derived risk scores demonstrated high concordance indexes (C-indexes) - 0.844, 0.827, and 0.806 in the training set and validation sets 1 and 2, respectively. The GBS classifier could separate patients into high-, medium- and low-risk subgroups with respect to death in all datasets (P<0.05 for all comparisons). A higher risk score was positively correlated with a higher clinical stage and the presence of portal vein tumor thrombus (PVTT). Subgroup analyses with respect to Child-Pugh class, Barcelona Clinic Liver Cancer (BCLC) stage, and PVTT status supported the prognostic relevance of the GBS-derived risk algorithm independent of the conventional tumor staging system. In summary, a multiparameter machine learning algorithm incorporating clinical characteristics, laboratory parameters, and peripheral immune signatures offers a different approach to identify patients with the greatest risk of HCC-related death.

Liu Xiaoli, Lu Jilin, Zhang Guanxiong, Han Junyan, Zhou Wei, Chen Huan, Zhang Henghui, Yang Zhiyun


Surgery Surgery

Patient characteristics and surgical variables associated with intraoperative reduced right ventricular function.

In The Journal of thoracic and cardiovascular surgery ; h5-index 63.0

OBJECTIVE : Perioperative right ventricular function is a significant predictor of patient outcomes after cardiac surgery. This prospective study aimed to identify perioperative factors associated with reduced intraoperative right ventricular function.

METHODS : Right ventricular function was assessed at the beginning and end of surgery by standardized transesophageal echocardiographic measurements, including tricuspid annular plane systolic excursion, peak systolic longitudinal right ventricular strain, and fractional area change, in 109 adult patients undergoing cardiac surgery at Cleveland Clinic. Associations between right ventricular function and 33 patient characteristics and perioperative factors were analyzed by random forest machine learning. The relative importance of each variable in predicting right ventricular function at the end of surgery was determined.

RESULTS : Longer aortic clamp duration and lower baseline right ventricular function were highly important variables for predicting worse right ventricular function measured by tricuspid annular plane systolic excursion, right ventricular strain, and fractional area change at the end of surgery. For example, right ventricular function after longer aortic clamp times of 100-120 minutes was worse (median [Q1, Q3] tricuspid annular plane systolic excursion 1.0 [0.9, 1.1] cm) compared with right ventricular function after shorter aortic clamp times of 50 to 70 minutes (tricuspid annular plane systolic excursion 1.5 [1.3, 1.7]; P = .001). Right ventricular strain at the end of surgery was reduced in patients with worse baseline right ventricular function compared with those with higher baseline right ventricular function (end of surgery right ventricular strain in lowest quartile -13.7 [-16.6, -12.4]% vs highest quartile -17.7 [-18.6, -15.3]% of baseline right ventricular function; P = .043).

CONCLUSIONS : Intraoperative decline in right ventricular function is associated with longer aortic clamp time and worse baseline right ventricular function. Efforts to optimize these factors, including better myocardial protection strategies, may improve perioperative right ventricular function.

Lang Angela L, Huang Xiaojie, Alfirevic Andrej, Blackstone Eugene, Pettersson Gosta B, Singh Asha, Duncan Andra E


cardiac surgery, myocardial protection, right ventricular dysfunction, transesophageal echocardiography

General General

Deep learning for Koopman Operator Optimal Control.

In ISA transactions

Nonlinear dynamics are ubiquitous in complex systems. Their applications range from robotics to computational neuroscience. In this work, the Koopman framework for globally linearizing nonlinear dynamics is introduced. Under this framework, the nonlinear observable states are lifted into a higher dimensional, linear regime. The challenge is to identify functions that facilitate the coordinate transformation to this raised linear space. This point is tackled using deep learning, where nonlinear dynamics are learned in a model-free manner, i.e., the underlying dynamics are uncovered using data rather than the nonlinear state-space equations. The main contributions include an implementation of the Linearly Recurrent Encoder Network (LREN) that is faster than the existing implementation and is significantly faster than the state-of-the-art deep learning-based approach. Also, a novel architecture termed Deep Encoder with Initial State Parameterization (DENIS) is proposed. By deriving an energy-budget control performance evaluation method, we demonstrate that DENIS also outperforms LREN in control performance. It is also on-par with and sometimes better than the iterative linear quadratic regulator (iLQR), which requires access to the state-space equations. Extensive experiments are done on DENIS to validate its performance. Also, another novel architecture termed Double Encoder for Input Nonaffine systems (DEINA) is described. Additionally, DEINA's potential ability to outperform existing Koopman frameworks for controlling nonaffine input systems is shown. We attribute this to using an auxiliary network to nonlinearly transform the inputs, thereby lifting the strong linear constraints imposed by the traditional Koopman approximation approach. Koopman model predictive control (KMPC) is implemented to verify that our models can also be successfully controlled under this popular approach. Overall, we demonstrate the deep learning-based Koopman framework shows promise for optimally controlling nonlinear dynamics.

Al-Gabalawy Mostafa


Deep Encoder with Initial State Parameterization (DENIS), Deep learning, Double Encoder for Input Nonaffine Systems (DEINA), Iterative linear quadratic regulator, Koopman model predictive control (KMPC), Linearly Recurrent Encoder Network (LREN), Optimal control

General General

Compressed graph representation for scalable molecular graph generation.

In Journal of cheminformatics

Recently, deep learning has been successfully applied to molecular graph generation. Nevertheless, mitigating the computational complexity, which increases with the number of nodes in a graph, has been a major challenge. This has hindered the application of deep learning-based molecular graph generation to large molecules with many heavy atoms. In this study, we present a molecular graph compression method to alleviate the complexity while maintaining the capability of generating chemically valid and diverse molecular graphs. We designate six small substructural patterns that are prevalent between two atoms in real-world molecules. These relevant substructures in a molecular graph are then converted to edges by regarding them as additional edge features along with the bond types. This reduces the number of nodes significantly without any information loss. Consequently, a generative model can be constructed in a more efficient and scalable manner with large molecules on a compressed graph representation. We demonstrate the effectiveness of the proposed method for molecules with up to 88 heavy atoms using the GuacaMol benchmark.

Kwon Youngchun, Lee Dongseon, Choi Youn-Suk, Shin Kyoham, Kang Seokho


Compressed graph representation, Deep learning, Graph variational autoencoder, Molecular graph generation