In JAMA network open

Importance : Axillary lymph node metastasis (ALNM) status, typically estimated using an invasive procedure with a high false-negative rate, strongly affects the prognosis of recurrence in breast cancer. However, preoperative noninvasive tools to accurately predict ALNM status and disease-free survival (DFS) are lacking.

Objective : To develop and validate dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) radiomic signatures for preoperative identification of ALNM and to assess individual DFS in patients with early-stage breast cancer.

Design, Setting, and Participants : This retrospective prognostic study included patients with histologically confirmed early-stage breast cancer diagnosed at 4 hospitals in China from July 3, 2007, to September 21, 2019, randomly divided (7:3) into development and vaidation cohorts. All patients underwent preoperative MRI scans, were treated with surgery and sentinel lymph node biopsy or ALN dissection, and were pathologically examined to determine the ALNM status. Data analysis was conducted from February 15, 2019, to March 20, 2020.

Exposure : Clinical and DCE-MRI radiomic signatures.

Main Outcomes and Measures : The primary end points were ALNM and DFS.

Results : This study included 1214 women (median [IQR] age, 47 [42-55] years), split into development (849 [69.9%]) and validation (365 [30.1%]) cohorts. The radiomic signature identified ALNM in the development and validation cohorts with areas under the curve (AUCs) of 0.88 and 0.85, respectively, and the clinical-radiomic nomogram accurately predicted ALNM in the development and validation cohorts (AUC, 0.92 and 0.90, respectively) based on a least absolute shrinkage and selection operator (LASSO)-logistic regression model. The radiomic signature predicted 3-year DFS in the development and validation cohorts (AUC, 0.81 and 0.73, respectively), and the clinical-radiomic nomogram could discriminate high-risk from low-risk patients in the development cohort (hazard ratio [HR], 0.04; 95% CI, 0.01-0.11; P < .001) and the validation cohort (HR, 0.04; 95% CI, 0.004-0.32; P < .001) based on a random forest-Cox regression model. The clinical-radiomic nomogram was associated with 3-year DFS in the development and validation cohorts (AUC, 0.89 and 0.90, respectively). The decision curve analysis demonstrated that the clinical-radiomic nomogram displayed better clinical predictive usefulness than the clinical or radiomic signature alone.

Conclusions and Relevance : This study described the application of MRI-based machine learning in patients with breast cancer, presenting novel individualized clinical decision nomograms that could be used to predict ALNM status and DFS. The clinical-radiomic nomograms were useful in clinical decision-making associated with personalized selection of surgical interventions and therapeutic regimens for patients with early-stage breast cancer.

Yu Yunfang, Tan Yujie, Xie Chuanmiao, Hu Qiugen, Ouyang Jie, Chen Yongjian, Gu Yang, Li Anlin, Lu Nian, He Zifan, Yang Yaping, Chen Kai, Ma Jiafan, Li Chenchen, Ma Mudi, Li Xiaohong, Zhang Rong, Zhong Haitao, Ou Qiyun, Zhang Yiwen, He Yufang, Li Gang, Wu Zhuo, Su Fengxi, Song Erwei, Yao Herui

2020-Dec-01

In Journal of behavioral addictions ; h5-index 36.0

Rumpf Hans-Jürgen, Browne Dillon, Brandt Dominique, Rehbein Florian

2020-Dec-08

In Journal of medical Internet research ; h5-index 88.0

BACKGROUND : Data sharing in multicenter medical research can improve the generalizability of research, accelerate progress, enhance collaborations among institutions, and lead to new discoveries from data pooled from multiple sources. Despite these benefits, many medical institutions are unwilling to share their data, as sharing may cause sensitive information to be leaked to researchers, other institutions, and unauthorized users. Great progress has been made in the development of secure machine learning frameworks based on homomorphic encryption in recent years; however, nearly all such frameworks use a single secret key and lack a description of how to securely evaluate the trained model, which makes them impractical for multicenter medical applications.

OBJECTIVE : The aim of this study is to provide a privacy-preserving machine learning protocol for multiple data providers and researchers (eg, logistic regression). This protocol allows researchers to train models and then evaluate them on medical data from multiple sources while providing privacy protection for both the sensitive data and the learned model.

METHODS : We adapted a novel threshold homomorphic encryption scheme to guarantee privacy requirements. We devised new relinearization key generation techniques for greater scalability and multiplicative depth and new model training strategies for simultaneously training multiple models through x-fold cross-validation.

RESULTS : Using a client-server architecture, we evaluated the performance of our protocol. The experimental results demonstrated that, with 10-fold cross-validation, our privacy-preserving logistic regression model training and evaluation over 10 attributes in a data set of 49,152 samples took approximately 7 minutes and 20 minutes, respectively.

CONCLUSIONS : We present the first privacy-preserving multiparty logistic regression model training and evaluation protocol based on threshold homomorphic encryption. Our protocol is practical for real-world use and may promote multicenter medical research to some extent.

Lu Yao, Zhou Tianshu, Tian Yu, Zhu Shiqiang, Li Jingsong

2020-Dec-08

confidentiality, logistic regression, machine learning, threshold homomorphic encryption

In eLife

Kane Gary A, Lopes Gonçalo, Sanders Jonny L, Mathis Alexander, Mathis Mackenzie

2020-Dec-08

computational biology, mouse, neuroscience, systems biology

In Radiology ; h5-index 91.0

Capaldi Dante P I, Guo Fumin, Xing Lei, Parraga Grace

2020-Dec-08

In The Journal of urology ; h5-index 80.0

PURPOSE : Continuous antibiotic prophylaxis (CAP) reduces the risk of recurrent urinary tract infection (rUTI) by 50% in vesicoureteral reflux (VUR) children. However, there may be subgroups in whom CAP could be used more selectively. We sought to develop a machine learning model to identify such subgroups.

MATERIALS AND METHODS : We used RIVUR data and randomly split it into train/test in 4:1 ratio. Two models were developed to predict rUTI risk in scenario with and without CAP. The test set was then used to validate rUTI events and the effectiveness of CAP. Predicted probabilities of rUTI were generated from each model. CAP was assigned at various cutoffs of rUTI risk reduction to evaluate CAP effectiveness.

RESULTS : 607 patients (558 female/49 male, median age 12 months) were included. Predictors included VUR grade, serum creatinine, race/sex, prior UTI symptoms (fever/dysuria), and weight percentiles. The AUC of the prediction model of rUTI (CAP/placebo) was 0.82 (95% CI: 0.74-0.87). Using 10% rUTI risk reduction cutoff, minimal rUTI on population-level can be achieved by giving CAP to 40% VUR patients instead of everyone. In test set (n=121), 51 patients had CAP randomization consistent with model recommendation (CAP if rUTI risk reduction >10%). rUTI incidence was significantly lower among this group compared to those whose CAP assignment differed from model suggestion (7.5% vs 19.4%, p=0.037).

CONCLUSIONS : Our predictive model identifies VUR patients who are more likely to benefit from CAP, which would allow more selective, personalized use of CAP with maximal benefit, while minimizing use in those with least need.

Wang Hsin-Hsiao Scott, Li Michael, Bertsimas Dimitri, Estrada Carlos, Caleb Nelson

2020-Dec-08

Prediction model, RIVUR, antibiotic prophylaxis, machine learning, urinary tract infection, vesico-ureteral reflux