Forward-looking providers made strides with AI in 2019

前瞻性供应商在2019年与 AI 取得了长足进展

2019-12-12 05:41:10 Healthcare IT News


Artificial intelligence has been near the top of many healthcare CIOs’ wish lists in 2019. It’s more than a bright, shiny object – it’s a set of technologies that can help healthcare provider organizations accomplish quite a bit on both the clinical and business sides of operations. But not many provider organizations have made much progress with AI yet. Still, 2019 has seen a lot of progress being made by some forward-looking providers dipping their toes into the AI waters. And some of these providers have results to brag about. Summa Health is a nonprofit health system in Northeast Ohio. The Greater Akron Chamber documents Summa Health as the largest employer in Summit County with more than 7,000 employees. Summa Health provides comprehensive emergency, acute, critical, outpatient and long-term/home care. The growing use of CT chest imaging has resulted in increased incidental lung nodule findings on imaging studies. These nodules have historically proved problematic for follow-up. According to the Journal of the American College of Radiology (February 2016), follow-up rates for incidental nodules range from 30-50%. “Patients seen in the emergency department are particularly vulnerable to being lost to follow-up on their incidental findings, something unrelated to their original emergency visit,” explained Sandy Kohut, lead lung navigator at Summa Health. “Additionally, arranging follow-up care and further diagnostic studies for asymptomatic conditions such as lung nodules presents a challenge to healthcare organizations.” However, earlier detection means earlier treatment, which means additional treatment options and increased rates of survival. “As a result, a team at Summa Health launched a multi-pronged quality improvement project to improve identification and appropriate follow-up of incidental lung nodules identified in emergency patients,” Kohut said. Summa Health turned to health IT vendor Nuance Communications for help with this challenge. “Nuance’s mPower Clinical Analytics solution would provide us with automated data mining and reporting tools to help identify emergency department patients with incidental lung nodules for follow-up,” said Laura Musarra, senior business performance analyst at Summa Health. “Summa leveraged both Nuance’s PowerScribe 360 reporting platform and Nuance’s mPower Clinical Analytics to enable the multidisciplinary team to improve follow-up around incidental findings, and in doing so, lead to improved care,” she explained. Specifically, PowerScribe 360 Reporting is a real-time radiology reporting system that helps radiologists generate high-quality reports quickly and efficiently to increase physician satisfaction and improve patient care, said Musarra. “mPower Clinical Analytics is a radiology-specific natural language processing-driven analytics platform,” she added, speaking of the AI technology NLP. “It enables users to easily query and analyze large amounts of unstructured or dictated notes and data in radiology reports, saving time and automating laborious data mining processes. It unlocks valuable data and provides insights, making it easier to monitor, understand and improve clinical and operational performance.” In the first six months, Summa Health’s quality improvement initiative helped realize a 662% increase in the number of patients identified each month for follow-up – from 8 per month to 61 per month. “For patients with actionable lung nodules (>8mm), consultations to pulmonologists were expedited by lung navigators, with approval from primary care physicians to lung nodule clinics,” Musarra explained. “The increased number of patients contributed to the opening of a new lung nodule clinic.” Most important, the multidisciplinary team established a best practice in dealing with incidental findings. “They conduct regular review of CT scans of incidental lung nodules to prevent the issue of overdiagnosis,” Musarra explained. “The team carefully weighs additional and potentially risky testing or procedures for conditions that may be benign and could cause harm for conditions that would not lead to morbidity or mortality if they were never detected.” Also in 2019 in the realm of healthcare AI, Sutter Health, a health system based in Sacramento, California, has made innovation a part of its mission. It’s made investments in many different technologies, research projects and medical advancements to improve the patient experience and patient outcomes. Among other things, Sutter Health created and launched its Virtual Symptom Checker, a new artificial intelligence program to check symptoms based on severity and medical history. It reveals potential causes and next steps. “Creating human connections is one of the most important things we can do as an integrated health system, being whenever our patients and their families need us the most,” said Dr. Albert Chan, chief of digital patient experience at Sutter Health. “Thus far, more than 50% of our symptom checker interactions happen after hours.” With AI, the health system can take something meaningful like answering patients’ questions in the wee hours of the morning and make that systematic, he added. “When you are concerned or sick, we aim to connect you to the care that you need – reducing friction one human interaction at a time,” he said. Elsewhere on the healthcare AI front in 2019, Israel’s Sheba Medical Center, Tel Hashomer, one of the top 10 hospitals in the world according to Newsweek, announced the results of a study that validates the clinical impact of health IT vendor MedAware’s machine learning-enabled patient safety platform designed to minimize medication-related risks. The findings were published August 7, 2019, in the Journal of American Medical Informatics Association (JAMIA) in a study entitled “Reducing drug prescription errors and adverse drug events by application of a probabilistic, machine-learning based clinical decision support system in an inpatient setting.” Preventable errors account for 1 out of 131 outpatient deaths and 1 out of 854 inpatients deaths in the U.S., with direct costs of more than $20 billion and liability costs of more than $13 billion annually, according to Sheba research authors. Often errors that take place are the result of failures in computerized health information systems, according to the research. Led by Dr. Gadi Segal, head of internal medicine, Sheba Medical Center researchers assessed the quality, accuracy and impact of MedAware’s medication safety platform. Physicians at Sheba analyzed results in a single medical ward, from a hospital-wide live implementation of MedAware, which had been integrated into the center’s existing EHR system. The platform monitored all medical prescriptions issued over 16 months, with the department’s staff assessing all alerts for accuracy, clinical validity and usefulness, recording all physicians’ real-time responses to alerts generated. The results of the study demonstrated a low overall alert burden, with MedAware-generated warnings for only 0.4% of all prescriptions. Additional findings included: There are other cases of healthcare provider organizations doing AI work with positive outcomes in 2019. And 2020 promises many more healthcare AI projects. Artificial intelligence is starting to mature in the healthcare industry, and healthcare CIOs, CMIOs and other leaders have a vast arena in which to experiment and prove that the complex technologies can improve healthcare delivery and operations. Twitter: @SiwickiHealthIT Email the writer: Healthcare IT News is a HIMSS Media publication.
人工智能已接近许多卫生保健首席信息官希望在2019年的名单。它不仅仅是一个明亮而闪亮的目标——它是一组能够帮助医疗保健提供者组织在临床和业务方面都取得相当大成就的技术。 但还没有多少供应商组织在人工智能方面取得了很大进展。然而,2019年,一些前瞻性的供应商在人工智能领域取得了很大进展。这些供应商中的一些有结果值得吹嘘。 Summa Health 是俄亥俄州东北部的一个非营利性卫生系统。大阿克伦商会记录 Summa Health 是 Summit 郡最大的雇主,拥有7000多名员工。Summa Health 提供全面的紧急、紧急、紧急、门诊和长期/家庭护理。 越来越多的 CT 胸腔成像的使用导致了附带肺结节的成像研究结果的增加。这些结节在历史上被证明是有问题的后续行动。根据美国放射学会杂志(2016年2月),偶然结节的随访率在30-50%之间。 Summa Health 肺导航仪负责人桑迪•科胡特( Sandy Kohut )解释说:“急诊科的病人特别容易因意外发现而失去后续行动,这与他们最初的紧急访问无关。”“此外,为肺结节等无症状的疾病安排后续护理和进一步的诊断研究,对医疗机构构成了挑战。” 然而,早期检测意味着更早的治疗,这意味着更多的治疗选择和更高的存活率。 “因此, Summa Health 的一个团队启动了一个多管质量改进项目,以改善急诊病人肺部附带结节的鉴别和适当的随访,” Kohut 说。 Summa Health 转向健康 IT 供应商 Nuance Communications 寻求帮助以应对这一挑战。Summa Health 高级业务绩效分析师 Laura Musarra 表示:“ Nuance 的 mPower 临床分析解决方案将为我们提供自动化的数据挖掘和报告工具,以帮助确定急诊部门患者附带肺结节的随访情况。” “ Summa 利用 Nuance 的 PowerScribe 360报告平台和 Nuance 的 mPower Clinical Analytics ,使多学科团队能够改进偶然发现的后续工作,并以此提高护理水平,”她解释道。 特别是, PowerScribe360 Reporting 是一个实时的放射报告系统,它帮助放射科医生快速高效地生成高质量的报告,以提高医生的满意度和改善病人护理, Musarra 说。 “ mPower Clinical Analytics 是一个特定于放射学的自然语言处理驱动的分析平台,”她在谈到人工智能技术 NLP 时补充道。“它使用户能够轻松地在放射学报告中查询和分析大量非结构化或指令的笔记和数据,节省时间,并自动化繁琐的数据挖掘过程。它可以释放有价值的数据并提供见解,从而更容易监控、理解和改善临床和操作性能。” 在前六个月, Summa Health 的质量改进计划帮助实现了每月确定的随访患者数量的662%,从每月8人增加到每月61人。 “对于可操作肺结节(>8mm )的患者,肺导航仪加快了对肺科医生的咨询,并获得了初级保健医生对肺结节诊所的批准,” Musarra 解释说。“越来越多的病人参与了一个新的肺结节诊所的开设。” 最重要的是,多学科小组在处理附带发现方面建立了最佳做法。 “他们定期检查附带肺结节的 CT 扫描,以防止过度诊断,” Musarra 解释说。“该团队仔细评估了可能是良性的、可能会导致不会导致发病率或死亡率的条件的附加和潜在风险的测试或程序。” 同样在2019年,位于加州萨克拉门托的卫生系统 Sutter Health 也将创新作为其使命的一部分。它投资于许多不同的技术、研究项目和医疗进步,以改善病人的经验和病人的结果。 除其他外, Sutter Health 创建并推出了虚拟症状检查程序,这是一个新的人工智能程序,用于根据严重程度和病史检查症状。它揭示了潜在的原因和接下来的步骤。 Sutter Health 的数字病人体验主管 Albert Chan 博士说:“建立人与人之间的联系是我们作为一个综合健康系统所能做的最重要的事情之一,在我们的病人和他们的家人最需要我们的时候。”“到目前为止,超过50%的症状检查器相互作用发生在数小时后。” 他补充说,通过人工智能,健康系统可以采取一些有意义的举措,比如在早上几个小时内回答患者的问题,并使之系统化。 “当你担心或生病时,我们的目标是让你得到你所需要的照顾——一次减少人与人之间的摩擦,”他说。 在2019年医疗人工智能领域的其他领域,以色列的 Sheba 医疗中心 Tel Hashomr 宣布了一项研究结果,该研究证实了医疗 IT 供应商 MedAwaree 的机器学习支持病人安全平台的临床影响,该平台旨在最大限度地降低与药物相关的风险。 该研究结果于2019年8月7日发表在《美国医学信息协会杂志》( JAMIA )上,发表在题为“通过在住院环境中应用基于机器学习的概率临床决策支持系统来减少药物处方错误和不良药物事件”的研究中。 Sheba 研究报告的作者说,在美国131例门诊死亡病例中,有1例是可预防的错误,854例住院死亡病例中有1例是可预防的,直接费用超过200亿美元,责任费用每年超过130亿美元。研究表明,经常发生的错误是计算机健康信息系统故障的结果。 在内部医学负责人 Gadi Segal 博士的带领下, Sheba 医学中心的研究人员评估了 MedAwarene 药物安全平台的质量、准确性和影响。 Sheba 的医生分析了一个单独的医疗病房的结果,该病房是 MedAwarene 在医院范围内的现场实施,已被纳入该中心现有的 EHR 系统。该平台监控了16个月内发布的所有医疗处方,部门员工评估所有警报的准确性、临床有效性和实用性,并记录所有医生对警报的实时响应。 研究结果表明,总体警戒负担较低, MedAwarene 只对所有处方的0.4%发出警告。其他调查结果包括: 还有其他一些医疗保健提供者组织在2019年开展 AI 工作,取得积极成果。2020年将会有更多的医疗人工智能项目。 人工智能在医疗保健行业开始成熟,而医疗 CIO 、 CMIOs 等领导者拥有一个广阔的舞台,在这个舞台上进行实验,证明复杂的技术可以改善医疗服务和运营。 Twitter :@ SiwickiHealthIT 给作者发邮件:账单。siwicki @ 医疗保健 IT 新闻是医疗卫生信息与管理系统协会(HIMSS)媒体出版物。