BLOG: Real-time Intelligence in Reporting and Communication
增强放射科医生解读诊断影像的专业技能的人工智能模型往往吸引了业界的大部分关注。这是可以理解的,因为它们在工作列表优先排序、完成耗时的测量以及患者诊断和治疗方面提供了好处。But a range of otherAI technologiesare quietly gaining widespread acceptance because they address in real-time many of the everyday challenges that radiologist face in reporting and communicating findings and recommendations to referring physicians.
AI-powered natural language understanding and other innovations now generate structured data from unstructured narrative text, deliver contextual clinical guidance when most helpful during the reporting workflow, provide quality and accuracy checks, connect disparate systems with synchronous data exchange and reduce workflow interruptions. Together, they are adding significant value to radiology reporting and integrating diagnostic imaging more closely into patient care.
“Real-time intelligence in the workflow is critical,” saidKaren Holzberger, senior vice president and general manager ofNuance Healthcare’s diagnostic solutions business. “Successful adoption of AI in radiology requires a combination of innovations and solutions that are intelligently integrated into workflows and that enable the full clinical value of radiology in improving patient care and outcomes.”
Beyond image analysis, using AI to improve the quality and flow of radiology reporting downstream and streamline its communication and consumption by care teams and patients is becoming a primary factor in integrating radiology into the care cycle and opening important new areas of clinical applications such as precision medicine.
“In the past, radiologists spent a lot of time searching for patient histories and other contextual clinical information to help them interpret and report findings,” Holzberger said. “With new capabilities and automation, radiologists can move beyond being reporters of narrative and numerical data to being expert curators of a central part of the overall patient story with more detailed findings and consistent, evidence-based recommendations.”
Minimizing Distraction
Recent analysissuggests radiologists are interrupted once every 4 to 12 minutes during regular business hours, generally with questions and consult requests. Each phone call or in-person interruption disrupts focus, takes time away from the current interpretation, and requires additional time to reorient to the active report. The impact is significant, from higher rates of exhaustion and burnout to lower productivity and increased risk of diagnostic or reporting errors. By integrating intelligent filtering and prioritization of communications into radiologists’ workflow in real time, they can manage interruptions more effectively and focus on current reporting tasks.
“Our collective goal in the industry is keeping the radiologists’ eyes on patient images and on delivering timely and actionable reports for patient-centered care,” Holzberger said.
Nuance PowerConnect Communicator简化沟通和优化信息传递,使放射科医生能够主动管理中断。这样做有助于放射小组成员之间的合作,以挖掘不同水平的专业知识在成像方式,熟悉医疗专业或特定提供者,患者的历史和其他领域。
Streamlining report creation
InPowerScribe One,上下文感知语言理解技术将非结构化听写转换为结构化数据,并支持公共数据元素。这有助于减少人工和重复的数据输入以及报告的可变性。产生的数据可以集成到EMR中,用于跟踪随访建议的依从性或应用于临床分析。
AI-powered integrations and speech recognition also enable radiologists to navigate reports, access patient histories and data from the EMR andPACSfor clinical decision support.
“You have AI driving advanced language understanding, image characterization, and non-pixel-based analysis to automate content generation and augment radiologists’ expertise. AI provides evidence-based clinical intelligence to support their findings and follow-up recommendations,” Holzberger said. “The combination of technologies helps the radiologist improve reporting accuracy and get to the correct diagnosis more quickly.
Facilitating Sharing with Disparate Systems
在不同的系统之间实时共享信息的能力是游戏规则的改变者。PowerScribe One可以与放射科医生使用的其他系统进行通信,如PACS、图像查看器和第三方AI解决方案,将必要的数据放在前面和中心。一旦在报告中捕获信息,下游系统就可以立即获得这些信息。霍尔兹伯格认为,随着卫生系统扩大采用新技术,这种整体、综合的数据处理方法是前进的方向。
“Radiologists have always embraced the adoption of new technology, from moving away from transcription to front-end speech recognition and self-editing, or the adoption of PACS systems,” Holzberger said. “What Nuance brings to the table is a combination of years of domain and technical expertise, proven product innovation and a truly patient-centered approach. In the end, it is about helping radiologists advance the state of the art of data-driven radiology reporting to improve care access, outcomes, and costs.”
Editor’s note:This blog is the third in a four-part series about real-time intelligence in the radiology workflow, to be published monthly. The first blog can be foundhere,and the second blog can be foundhere.To learn more, visitnuance.com/healthcare/diagnostics-solutions