DeepCertainty: Deep Learning for Contextual Diagnostic Uncertainty Measurement in Radiology Reports

DeepCertainty：放射学报告中上下文诊断不确定性测量的深度学习

• 批准号: 10593770
• 负责人: Feifan Liu
• 金额: $ 18.84万
• 依托单位: UNIV OF MASSACHUSETTS MED SCH WORCESTER
• 依托单位国家: 美国
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-09-01 至 2025-08-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10593770
• 关键词: Accident and Emergency department; Address; Adopted; Adoption; Agreement; American College of Radiology; Angiography; Awareness; Calibration; Cardiovascular system; Caring; Categories; Cessation of life; Clinical; Communication; Complex; Computing Methodologies; Data; Data Set; Decentralization; Diagnosis; Diagnostic; Diagnostic Errors; Diagnostic Imaging; Diagnostic tests; Disease; Effectiveness; Emergency Department Physician; Emergency Department patient; Emergency Situation; Emergency department visit; Ensure; Evaluation; Exclusion; Feedback; Foundations; Funding; Grain; Guidelines; Healthcare; Hospitalization; Image; Image Analysis; Individual; Inpatients; Institution; Intensive Care Units; Knowledge; Language; Learning; Lung; Magnetic Resonance Imaging; Manuals; Measurement; Measures; Medical; Modeling; Morbidity - disease rate; Natural Language Processing; Outpatients; Patient Care; Patients; Perception; Persons; Physicians; Process; Pulmonary Embolism; Quality of Care; Radiology Specialty; Reporting; Sampling; Semantics; Signs and Symptoms; Specific qualifier value; Standardization; Stress; Structure; System; Technology; Testing; Time; Uncertainty; United States; Variant; Workplace; X-Ray Computed Tomography; accurate diagnosis; accurate diagnostics; adverse outcome; clinical decision-making; computerized; cost outcomes; deep learning; design; future implementation; imaging modality; impression; improved; innovation; lexical; mortality; neural; prevent; radiologist; rapid diagnosis; statistics; unnecessary treatment; user-friendly

PE becomes the third leading cause of cardiovascular-related death, and more than 500,000 cases of PE occur in the United States (US) every year, resulting in approximately 200,000 deaths and hospitalization of over 250,000 patients. Rapid and accurate diagnosis of PE are of paramount importance to ensure the highest quality of care. Every year 1-2% of the 120 million emergency department (ED) patients in the US undergo computed tomographic pulmonary angiography (CTPA) for PE. The referring physicians rely heavily on CTPA reports diagnosing or excluding PEs. Clarity of the radiology report is one of the most critical qualities, and the American College of Radiology has emphasized a need for precision communication in radiological reports. Yet communicating uncertainty effectively in radiology reports is challenging. Referring physicians may interpret radiologists’ textual expressions that convey diagnostic confidence differently than intended. The gap between radiologists’ intended message and the referring physicians’ interpretation can not be completely resolved through structured reporting or standardized lexicon. Unnecessary hedging language in CTPA reports may further worsen the reporting ambiguity and may lead to inappropriate treatment of patients. Therefore, we aim to develop a deep learning-based approach for context-aware (un)certainty assessment (DeepCertainty), which is end-to-end trainable, calibratable, generalizable, scalable, and explainable. It would allow for fine- grained uncertainty measurement and standardization, facilitate consistent and accurate diagnostic certainty communication in CTPA reports and thus improve PE care. This study will build the foundation for future implementation and integration of DeepCertainty into clinical workflows to prompt real-time low-certainty alerts for improving PE diagnostic reporting quality and clarity, which will inform better treatment decisions for ED patients with suspected PE.

PE成为心血管相关死亡的第三大原因， 每年在美国（US）发生，导致约20万人死亡和住院治疗， 超过25万名患者PE的快速和准确诊断对于确保最高的 护理质量。每年美国1.2亿急诊科（艾德）患者中有1-2%接受 CT肺血管造影（CTPA）治疗PE。转诊医生严重依赖CTPA 报告诊断或排除PE。放射学报告的清晰度是最关键的质量之一， 美国放射学会强调了在放射学报告中精确沟通的必要性。 然而，在放射学报告中有效地传达不确定性是具有挑战性的。转诊医生可能 解释放射科医生的文本表达，其传达的诊断置信度不同于预期。差距 放射科医生的预期信息和转诊医生的解释之间不能完全 通过结构化报告或标准化词典解决。CTPA报告中不必要的对冲语言 可能会进一步加剧报告的不明确性，并可能导致对患者的不适当治疗。所以我们 旨在开发一种基于深度学习的方法，用于上下文感知（un）确定性评估（deepaware）， 其是端到端可训练的、可校准的、可推广的、可缩放的和可解释的。它会允许罚款- 粒度不确定性测量和标准化，促进一致和准确的诊断确定性 CTPA报告中的沟通，从而改善PE护理。本研究为今后的研究奠定了基础 将DeepMonitorty实施并集成到临床工作流程中，以提示实时低确定性警报 用于提高PE诊断报告的质量和清晰度，这将为艾德提供更好的治疗决策 疑似PE的患者。