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

oncology Oncology

Novel biomarkers and prediction model for the pathological complete response to neoadjuvant treatment of triple-negative breast cancer.

In Journal of Cancer

Objective: To develop and validate a prediction model for the pathological complete response (pCR) to neoadjuvant chemotherapy (NCT) of triple-negative breast cancer (TNBC). Methods: We systematically searched Gene Expression Omnibus, ArrayExpress, and PubMed for the gene expression profiles of operable TNBC accessible to NCT. Molecular heterogeneity was detected with hierarchical clustering method, and the biological profiles of differentially expressed genes were investigated by Gene Ontology, Kyoto Encyclopedia of Genes and Genomes analyses, and Gene Set Enrichment Analysis (GSEA). Next, machine-learning algorithms including random-forest analysis and least absolute shrinkage and selection operator (LASSO) analysis were synchronously performed and, then, the intersected proportion of significant genes was undergone binary logistic regression to fulfill variables selection. The predictive response score (pRS) system was built as the product of the gene expression and coefficient obtained from the logistic analysis. Last, the cohorts were randomly divided in a 7:3 ratio into training cohort and validation cohort for the introduction of a robust model, and a nomogram was constructed with the independent predictors for pCR rate. Results: A total of 217 individuals from four cohort datasets (GSE32646, GSE25065, GSE25055, GSE21974) with complete clinicopathological information were included. Based on the microarray data, a six-gene panel (ATP4B, FBXO22, FCN2, RRP8, SMERK2, TET3) was identified. A robust nomogram, adopting pRS and clinical tumor size stage, was established and the performance was successively validated by calibration curves and receiver operating characteristic curves with the area under curve 0.704 and 0.756, respectively. Results of GSEA revealed that the biological processes including apoptosis, hypoxia, mTORC1 signaling and myogenesis, and oncogenic features of EGFR and RAF were in proactivity to attribute to an inferior response. Conclusions: This study provided a robust prediction model for pCR rate and revealed potential mechanisms of distinct response to NCT in TNBC, which were promising and warranted to further validate in the perspective.

Han Yiqun, Wang Jiayu, Xu Binghe


molecular heterogeneity, neoadjuvant chemotherapy, nomogram, pathological complete response, triple-negative breast cancer

Radiology Radiology

A deep-learning-based prognostic nomogram integrating microscopic digital pathology and macroscopic magnetic resonance images in nasopharyngeal carcinoma: a multi-cohort study.

In Therapeutic advances in medical oncology

Background : To explore the prognostic value of radiomics-based and digital pathology-based imaging biomarkers from macroscopic magnetic resonance imaging (MRI) and microscopic whole-slide images for patients with nasopharyngeal carcinoma (NPC).

Methods : We recruited 220 NPC patients and divided them into training (n = 132), internal test (n = 44), and external test (n = 44) cohorts. The primary endpoint was failure-free survival (FFS). Radiomic features were extracted from pretreatment MRI and selected and integrated into a radiomic signature. The histopathological signature was extracted from whole-slide images of biopsy specimens using an end-to-end deep-learning method. Incorporating two signatures and independent clinical factors, a multi-scale nomogram was constructed. We also tested the correlation between the key imaging features and genetic alternations in an independent cohort of 16 patients (biological test cohort).

Results : Both radiomic and histopathologic signatures presented significant associations with treatment failure in the three cohorts (C-index: 0.689-0.779, all p < 0.050). The multi-scale nomogram showed a consistent significant improvement for predicting treatment failure compared with the clinical model in the training (C-index: 0.817 versus 0.730, p < 0.050), internal test (C-index: 0.828 versus 0.602, p < 0.050) and external test (C-index: 0.834 versus 0.679, p < 0.050) cohorts. Furthermore, patients were stratified successfully into two groups with distinguishable prognosis (log-rank p < 0.0010) using our nomogram. We also found that two texture features were related to the genetic alternations of chromatin remodeling pathways in another independent cohort.

Conclusion : The multi-scale imaging features showed a complementary value in prognostic prediction and may improve individualized treatment in NPC.

Zhang Fan, Zhong Lian-Zhen, Zhao Xun, Dong Di, Yao Ji-Jin, Wang Si-Yang, Liu Ye, Zhu Ding, Wang Yin, Wang Guo-Jie, Wang Yi-Ming, Li Dan, Wei Jiang, Tian Jie, Shan Hong


digital pathology, multi-scale features, nasopharyngeal carcinoma, radiomics, survival analysis

General General

The single-monitor trial: an embedded CADe system increased adenoma detection during colonoscopy: a prospective randomized study.

In Therapeutic advances in gastroenterology

Background : Computer-aided detection (CADe) of colon polyps has been demonstrated to improve colon polyp and adenoma detection during colonoscopy by indicating the location of a given polyp on a parallel monitor. The aim of this study was to investigate whether embedding the CADe system into the primary colonoscopy monitor may serve to increase polyp and adenoma detection, without increasing physician fatigue level.

Methods : Consecutive patients presenting for colonoscopies were prospectively randomized to undergo routine colonoscopy with or without the assistance of a real-time polyp detection CADe system. Fatigue level was evaluated from score 0 to 10 by the performing endoscopists after each colonoscopy procedure. The main outcome was adenoma detection rate (ADR).

Results : Out of 790 patients analyzed, 397 were randomized to routine colonoscopy (control group), and 393 to a colonoscopy with computer-aided diagnosis (CADe group). The ADRs were 20.91% and 29.01%, respectively (OR = 1.546, 95% CI 1.116-2.141, p = 0.009). The average number of adenomas per colonoscopy (APC) was 0.29 and 0.48, respectively (Change Folds = 1.64, 95% CI 1.299-2.063, p < 0.001). The improvement in polyp detection was mainly due to increased detection of non-advanced diminutive adenomas, serrated adenoma and hyperplastic polyps. The fatigue score for each procedure was 3.28 versus 3.40 for routine and CADe group, p = 0.357.

Conclusions : A real-time CADe system employed on the primary endoscopy monitor may lead to improvements in ADR and polyp detection rate without increasing fatigue level during colonoscopy. The integration of a low-latency and high-performance CADe systems may serve as an effective quality assurance tool during colonoscopy. number, ChiCTR1800018058.

Liu Peixi, Wang Pu, Glissen Brown Jeremy R, Berzin Tyler M, Zhou Guanyu, Liu Weihui, Xiao Xun, Chen Ziyang, Zhang Zhihong, Zhou Chao, Lei Lei, Xiong Fei, Li Liangping, Liu Xiaogang


artificial intelligence, colonoscopy, computer-aided diagnosis, polyp

Public Health Public Health

Second opinion needed: communicating uncertainty in medical machine learning.

In NPJ digital medicine

There is great excitement that medical artificial intelligence (AI) based on machine learning (ML) can be used to improve decision making at the patient level in a variety of healthcare settings. However, the quantification and communication of uncertainty for individual predictions is often neglected even though uncertainty estimates could lead to more principled decision-making and enable machine learning models to automatically or semi-automatically abstain on samples for which there is high uncertainty. In this article, we provide an overview of different approaches to uncertainty quantification and abstention for machine learning and highlight how these techniques could improve the safety and reliability of current ML systems being used in healthcare settings. Effective quantification and communication of uncertainty could help to engender trust with healthcare workers, while providing safeguards against known failure modes of current machine learning approaches. As machine learning becomes further integrated into healthcare environments, the ability to say "I'm not sure" or "I don't know" when uncertain is a necessary capability to enable safe clinical deployment.

Kompa Benjamin, Snoek Jasper, Beam Andrew L


General General

A new precision medicine initiative at the dawn of exascale computing.

In Signal transduction and targeted therapy

Which signaling pathway and protein to select to mitigate the patient's expected drug resistance? The number of possibilities facing the physician is massive, and the drug combination should fit the patient status. Here, we briefly review current approaches and data and map an innovative patient-specific strategy to forecast drug resistance targets that centers on parallel (or redundant) proliferation pathways in specialized cells. It considers the availability of each protein in each pathway in the specific cell, its activating mutations, and the chromatin accessibility of its encoding gene. The construction of the resulting Proliferation Pathway Network Atlas will harness the emerging exascale computing and advanced artificial intelligence (AI) methods for therapeutic development. Merging the resulting set of targets, pathways, and proteins, with current strategies will augment the choice for the attending physicians to thwart resistance.

Nussinov Ruth, Jang Hyunbum, Nir Guy, Tsai Chung-Jung, Cheng Feixiong


General General

Prediction of Long-term Cognitive Functions after Minor Stroke, Using Functional Connectivity.

In Neurology ; h5-index 107.0

OBJECTIVE : To determine whether functional MRI connectivity can predict the long-term cognitive functions 36 months after minor stroke.

METHODS : Seventy-two participants with first-ever stroke were included at baseline and followed up for 36 months. A ridge regression machine learning algorithm was developed and used to predict cognitive scores 36 months post-stroke on the basis of the functional networks measured using MRI at 6 months (referred to here as the post-stroke cognitive impairment (PSCI) network). The prediction accuracy was evaluated in four domains (memory, attention/executive, language and visuospatial functions) and compared with clinical data and other functional networks. The models' statistical significance was probed with permutation tests. The potential involvement of cortical atrophy was assessed 6 months post-stroke. A second, independent dataset (n=40) was used to validate the results and assess their generalizability.

RESULTS : Based on the PSCI network, a machine learning model was able to predict memory, attention, visuospatial functions and language functions 36 months post-stroke (r2: 0.67, 0.73, 0.55 and 0.48, respectively). The PSCI-based model was at least as accurate as models based on other functional networks or clinical data. Specific patterns were demonstrated for the four cognitive domains, with involvement of the left superior frontal cortex for memory, attention and visuospatial functions. The cortical thickness 6 months post-stroke was not correlated with cognitive function 36 months post-stroke. The independent validation dataset gave similar results.

CONCLUSIONS : A machine learning model based on the PSCI network can predict the long-term cognitive outcome after stroke.

Lopes Renaud, Bournonville Clément, Kuchcinski Grégory, Dondaine Thibaut, Mendyk Anne-Marie, Viard Romain, Pruvo Jean-Pierre, Hénon Hilde, Georgakis Marios K, Duering Marco, Dichgans Martin, Cordonnier Charlotte, Leclerc Xavier, Bordet Régis