美国哈佛大学Eliezer M. Van Allen团队比较了前列腺癌和黑色素瘤患者种系基因检测与标准方法检测的准确性。2020年11月17日，该研究发表在《美国医学会杂志》上。

不到10%的癌症患者可检测到致病性种系改变，这可能部分是由于不完整的致病性变异检测所致。

为了评估深度学习方法是否能在癌症患者中发现更多种系致病性变异，2010-2017年，研究组在美国和欧洲进行了一项标准种系检测方法和深度学习方法的横断面研究，选择了两个前列腺癌和黑色素瘤患者队列。主要结局包括118个癌症易感基因的致病性变异检测表现，评估为敏感性、特异性、阳性预测值（PPV）和阴性预测值（NPV）。

前列腺癌队列包括1072名男性，确诊时的平均年龄为63.7岁，其中79.9%具有欧洲血统；黑色素瘤队列包括1295名患者，确诊时的平均年龄为59.8岁，其中37.7%为女性，81.9%具有欧洲血统。深度学习法比标准方法相比，可识别出更多癌症易感基因的致病性突变患者，其中前列腺癌队列分别识别198例和182例，黑色素瘤队列分别识别93例和74例；敏感性（前列腺癌：94.7%对87.1%；黑色素瘤：74.4%对59.2%），特异性（前列腺癌：64.0%对36.0%；黑色素瘤：63.4%对36.6%），PPV（前列腺癌：95.7%对91.9%；黑色素瘤：54.4%对35.4%），NPV（前列腺癌：59.3%对25.0%；黑色素瘤：80.8%对60.5%）。

对于美国医学遗传学和基因组学学会（ACMG）认定的致病性变异基因，在前列腺癌队列中，深度学习法的敏感性为94.9%，标准方法为90.6%，差异不显著；但在黑色素瘤队列中，深度学习法的敏感性为71.6%，显著高于标准方法（53.7%）。与标准方法相比，深度学习法对孟德尔基因有较高的敏感性（前列腺癌：99.7%对95.1%；黑色素瘤：91.7%对86.2%）。

研究结果表明，对于两个独立的前列腺癌和黑色素瘤患者队列，使用深度学习的种系基因检测与现行标准的基因检测方法相比，在检测致病性变异方面具有更高的敏感性和特异性。

附：英文原文

Title: Detection of Pathogenic Variants With Germline Genetic Testing Using Deep Learning vs Standard Methods in Patients With Prostate Cancer and Melanoma

Author: Saud H. AlDubayan, Jake R. Conway, Sabrina Y. Camp, Leora Witkowski, Eric Kofman, Brendan Reardon, Seunghun Han, Nicholas Moore, Haitham Elmarakeby, Keyan Salari, Hani Choudhry, Abdullah M. Al-Rubaish, Abdulsalam A. Al-Sulaiman, Amein K. Al-Ali, Amaro Taylor-Weiner, Eliezer M. Van Allen

Issue&Volume: 2020/11/17

Abstract:

Importance  Less than 10% of patients with cancer have detectable pathogenic germline alterations, which may be partially due to incomplete pathogenic variant detection.

Objective  To evaluate if deep learning approaches identify more germline pathogenic variants in patients with cancer.

Design, Setting, and Participants  A cross-sectional study of a standard germline detection method and a deep learning method in 2 convenience cohorts with prostate cancer and melanoma enrolled in the US and Europe between 2010 and 2017. The final date of clinical data collection was December 2017.

Exposures  Germline variant detection using standard or deep learning methods.

Main Outcomes and Measures  The primary outcomes included pathogenic variant detection performance in 118 cancer-predisposition genes estimated as sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). The secondary outcomes were pathogenic variant detection performance in 59 genes deemed actionable by the American College of Medical Genetics and Genomics (ACMG) and 5197 clinically relevant mendelian genes. True sensitivity and true specificity could not be calculated due to lack of a criterion reference standard, but were estimated as the proportion of true-positive variants and true-negative variants, respectively, identified by each method in a reference variant set that consisted of all variants judged to be valid from either approach.

Results  The prostate cancer cohort included 1072 men (mean [SD] age at diagnosis, 63.7 [7.9] years; 857 [79.9%] with European ancestry) and the melanoma cohort included 1295 patients (mean [SD] age at diagnosis, 59.8 [15.6] years; 488 [37.7%] women; 1060 [81.9%] with European ancestry). The deep learning method identified more patients with pathogenic variants in cancer-predisposition genes than the standard method (prostate cancer: 198 vs 182; melanoma: 93 vs 74); sensitivity (prostate cancer: 94.7% vs 87.1% [difference, 7.6%; 95% CI, 2.2% to 13.1%]; melanoma: 74.4% vs 59.2% [difference, 15.2%; 95% CI, 3.7% to 26.7%]), specificity (prostate cancer: 64.0% vs 36.0% [difference, 28.0%; 95% CI, 1.4% to 54.6%]; melanoma: 63.4% vs 36.6% [difference, 26.8%; 95% CI, 17.6% to 35.9%]), PPV (prostate cancer: 95.7% vs 91.9% [difference, 3.8%; 95% CI, –1.0% to 8.4%]; melanoma: 54.4% vs 35.4% [difference, 19.0%; 95% CI, 9.1% to 28.9%]), and NPV (prostate cancer: 59.3% vs 25.0% [difference, 34.3%; 95% CI, 10.9% to 57.6%]; melanoma: 80.8% vs 60.5% [difference, 20.3%; 95% CI, 10.0% to 30.7%]). For the ACMG genes, the sensitivity of the 2 methods was not significantly different in the prostate cancer cohort (94.9% vs 90.6% [difference, 4.3%; 95% CI, –2.3% to 10.9%]), but the deep learning method had a higher sensitivity in the melanoma cohort (71.6% vs 53.7% [difference, 17.9%; 95% CI, 1.82% to 34.0%]). The deep learning method had higher sensitivity in the mendelian genes (prostate cancer: 99.7% vs 95.1% [difference, 4.6%; 95% CI, 3.0% to 6.3%]; melanoma: 91.7% vs 86.2% [difference, 5.5%; 95% CI, 2.2% to 8.8%]).

Conclusions and Relevance  Among a convenience sample of 2 independent cohorts of patients with prostate cancer and melanoma, germline genetic testing using deep learning, compared with the current standard genetic testing method, was associated with higher sensitivity and specificity for detection of pathogenic variants. Further research is needed to understand the relevance of these findings with regard to clinical outcomes.

DOI: 10.1001/jama.2020.20457

Source: https://jamanetwork.com/journals/jama/article-abstract/2772962