A novel deep learning approach to extract Chinese clinical entities for lung cancer screening and staging

Abstract Background Computed tomography (CT) reports record a large volume of valuable information about patients’ conditions and the interpretations of radiology images from radiologists, which can be used for clinical decision-making and further academic study. However, the free-text nature of clinical reports is a critical barrier to use this data more effectively. In this study, we investigate a novel deep learning method to extract entities from Chinese CT reports for lung cancer screening and TNM staging. Methods The proposed approach presents a new named entity recognition algorithm, namely the BERT-based-BiLSTM-Transformer network (BERT-BTN) with pre-training, to extract clinical entities for lung cancer screening and staging. Specifically, instead of traditional word embedding methods, BERT is applied to learn the deep semantic representations of characters. Following the long short-term memory layer, a Transformer layer is added to capture the global dependencies between characters. Besides, pre-training technique is employed to alleviate the problem of insufficient labeled data. Results We verify the effectiveness of the proposed approach on a clinical dataset containing 359 CT reports collected from the Department of Thoracic Surgery II of Peking University Cancer Hospital. The experimental results show that the proposed approach achieves an 85.96% macro-F1 score under exact match scheme, which improves the performance by 1.38%, 1.84%, 3.81%,4.29%,5.12%,5.29% and 8.84% compared to BERT-BTN, BERT-LSTM, BERT-fine-tune, BERT-Transformer, FastText-BTN, FastText-BiLSTM and FastText-Transformer, respectively. Conclusions In this study, we developed a novel deep learning method, i.e., BERT-BTN with pre-training, to extract the clinical entities from Chinese CT reports. The experimental results indicate that the proposed approach can efficiently recognize various clinical entities about lung cancer screening and staging, which shows the potential for further clinical decision-making and academic research.

Download Full-text

Explaining deep neural networks for knowledge discovery in electrocardiogram analysis

Scientific Reports ◽

10.1038/s41598-021-90285-5 ◽

2021 ◽

Vol 11 (1) ◽

Author(s):

Steven A. Hicks ◽

Jonas L. Isaksen ◽

Vajira Thambawita ◽

Jonas Ghouse ◽

Gustav Ahlberg ◽

...

Keyword(s):

Decision Making ◽

Deep Learning ◽

Deep Neural Networks ◽

Clinical Decision Making ◽

Medical Knowledge ◽

Clinical Decision ◽

Medical Data ◽

Medical Doctors ◽

Medical Tests ◽

Deep Learning Model

AbstractDeep learning-based tools may annotate and interpret medical data more quickly, consistently, and accurately than medical doctors. However, as medical doctors are ultimately responsible for clinical decision-making, any deep learning-based prediction should be accompanied by an explanation that a human can understand. We present an approach called electrocardiogram gradient class activation map (ECGradCAM), which is used to generate attention maps and explain the reasoning behind deep learning-based decision-making in ECG analysis. Attention maps may be used in the clinic to aid diagnosis, discover new medical knowledge, and identify novel features and characteristics of medical tests. In this paper, we showcase how ECGradCAM attention maps can unmask how a novel deep learning model measures both amplitudes and intervals in 12-lead electrocardiograms, and we show an example of how attention maps may be used to develop novel ECG features.

Download Full-text

Implementation of Shared Decision Making for Lung Cancer Screening Among the Privately Insured Nonelderly

MDM Policy & Practice ◽

10.1177/2381468320984773 ◽

2021 ◽

Vol 6 (1) ◽

pp. 238146832098477

Author(s):

Ya-Chen Tina Shih ◽

Ying Xu ◽

Lisa M. Lowenstein ◽

Robert J. Volk

Keyword(s):

Lung Cancer ◽

Decision Making ◽

Cancer Screening ◽

Shared Decision Making ◽

Private Insurance ◽

Lung Cancer Screening ◽

Shared Decision ◽

Factors Associated ◽

Coverage Policy ◽

Privately Insured

Introduction. The Centers for Medicare & Medicaid Services requires a written order of shared decision making (SDM) visit in its coverage policy for low-dose computed tomography (LDCT) for lung cancer screening (LCS). With screening eligibility starting at age 55, private insurance plans will likely adopt this coverage policy. This study examined the implementation of SDM in the context of LCS among the privately insured. Methods. We constructed two study cohorts from MarketScan Commercial Claims and Encounters database 2016-2017: a LDCT cohort who received LDCT for LCS and an SDM cohort who had an LCS-related SDM visit. For the LDCT cohort, we examined the trend and factors associated with the receipt of SDM within 3 months prior to LDCT. For the SDM cohort, we studied the trend and factors associated with LDCT within 3 months after an SDM visit. Results. For privately insured adults aged <64, 93% (19,681/21,084) of the LDCT cohort did not have a billing claim indicating SDM, although the uptake of SDM increased from 3.1% in 1Q2016 to 8.2% in 4Q2017 ( P < 0.0001). For the SDM cohort, 46% (948/2048) did not have a claim for an LDCT for lung cancer screening in the 3 months after the SDM visit; this percentage increased from 29.5% in 1Q2016 to 61.8% in 3Q2017 ( P < 0.0001). Limitations. Findings cannot be generalized to other nonelderly adults without private insurance. Additionally, the rate of SDM identified from claims may be underreported. Conclusions. We found a growing but low uptake of SDM among privately insured individuals who underwent LDCT. The higher rate of LDCT in the SDM cohort than the rate reported in national studies emphasized the importance of patient awareness.

Download Full-text