功能
A.I. 和保健
教师创造的工具, student researchers designed to help medical team improve care for patients with rare diseases
![扎克·德布鲁因用记号笔清理黑板, 绘制图形和形状, 他穿着一件有钮扣的蓝色衬衫](./files/shorthand/GTOP4DQYIk/assets/QDaJf7M0J2/230915_zacharydebruine_ksm-3252-4096x2832.jpg)
michele coffill的故事/ kendra stanley-mills的照片
对于患有癫痫的人来说,它’s often a trial and error process through several of the 30-some antiepileptic drugs to get to a medication that works.
想象一下, 虽然, a situation where physicians and health care teams could explore a patient's dashboard — uploaded using artificial intelligence tools — and then prescribe personalized medication without trial and error. 如果同样的人工智能工具可以帮助患有罕见疾病的患者呢?
扎卡里·德布琳, 计算机助理教授, and a team of student researchers are exploring how to develop and deliver artificial intelligence tools to help clinicians at Corewell Health and Helen DeVos Children's Hospital who treat patients with rare diseases.
Dr. 迦勒Bupp, 谁是Corewell Health医学遗传学和基因组学部门的负责人, said 德布琳's research could be invaluable in a medical field where 1 in 10 Americans has a rare disease yet 95% of patients have no treatment.
”我们现在用煤气做饭,” Bupp说.
![](./files/shorthand/GTOP4DQYIk/assets/HkEyfaceJx/single-907x604.png)
人们普遍对罕见病进行了研究 单独
![](./files/shorthand/GTOP4DQYIk/assets/CLMRd7YXu3/collective-908x604.png)
人工智能可以提供对罕见疾病的见解 集体
![](./files/shorthand/GTOP4DQYIk/assets/MYQZOItFBw/istock-1500469862-frame-0ms-1280x720.jpg)
![](./files/shorthand/GTOP4DQYIk/assets/HkEyfaceJx/single-907x604.png)
人们普遍对罕见病进行了研究 单独
![](./files/shorthand/GTOP4DQYIk/assets/CLMRd7YXu3/collective-908x604.png)
人工智能可以提供对罕见疾病的见解 集体
![](./files/shorthand/GTOP4DQYIk/assets/MYQZOItFBw/istock-1500469862-frame-0ms-1280x720.jpg)
德布鲁因加入了格兰德山谷’2022年的美国教师, after working for nearly a decade at Van Andel Institute (VAI) as a post-doctoral fellow and adjunct faculty member. 德布琳’s work at VAI was groundbreaking in helping researchers store and analyze massive sets of biomedical data. It also provided a foundation for his work at 博天堂官方 centered around building generative AI tools for clinicians and researchers.
”We’我们正努力为临床实践开发基因组智能,” 德布琳说. ”This will put AI tools that understand not the English language like ChatGTP but the language of genetic regulation and genetic variation in the hands of clinicians so they can ask questions and get answers that help them improve patient care.”
Bupp说 one of the many challenges of working with rare disease patients is the lack of comparisons to other patients. 与德布琳’基因组智能工具, Bupp说 he and his team are uncovering layers of understanding with patients.
For example, Bupp explained one ultra-rare condition that affects only 16 people worldwide. ”我们可以通过改变我们知道有效的药物的用途来治疗少数人. 和扎克一起’S组,我们已经超越了化学反应 ’为什么这个方法有效??’” 他说.
布普说,遗传学作为一个领域过去是非常活跃的. 随着人工智能的发展, ”We are shifting to being more proactive and Zach and his team are helping us to do that. 他们’他们没有给我们路线图,但他们让我们坐在驾驶座上,” 他说.
扎克·德布鲁因
在GVSU达到更高
四月展销会.
![Zach 德布琳 in checked suit jacket with nametag on lanyard in the middle of a crowd at the Reach Higher Showcase](./files/shorthand/GTOP4DQYIk/assets/2vohsY7wmX/240412_reachhighershowcase_ksm-8668-4096x2663.jpg)
三个组织伙伴, 博天堂官方, Corewell Health和VAI, have provided support and funding to create AI models that can provide collective insight into rare diseases.
他们首先关注的是儿童癫痫,这是德布鲁因非常了解的一个课题. 他的儿子安德鲁在出生时就被诊断出患有这种疾病. 德布琳 explained to an audience during a Grand Rapids Tech Week event that 安德鲁 underwent three different drug therapies, 这对癫痫患者来说并不罕见. 德布鲁因说,安德鲁现在8岁,健康快乐.
在德布琳和他的学生正在构建的人工智能模型中, results from a simple blood draw would be uploaded to an app that generates an AI cell atlas that can be explored through a dashboard for physicians and clinicians to prescribe personalized medication to treat, 例如, 安德鲁’年代癫痫.
”如果我们能学习一个能理解遗传学语言的模型, that model would be applicable not only to pediatric epilepsy but also rare disease diagnosis,” 德布琳说.
德布鲁因的方法
个性化医疗保健
生成式AI:
![A circular graphic with 6 icons around the edges with arrows pointing counter-clockwise from one icons to the next in a full circle and one icon in the middle. Icons read along the edges from top and then to the left: rare disease patient; blood draw; genomics assay; upload data to web app; AI generated "cell atlas" of disease patient; dashboard of results. 中间的图标写着:临床医生.](./files/shorthand/GTOP4DQYIk/assets/cWdkQOA7O0/cycle_large-1875x1459.png)
![](./files/shorthand/GTOP4DQYIk/assets/5yYDWTfkR1/istock-1500469862-frame-0ms-1280x720.jpg)
德布琳的方法
对个性化
医疗保健
生成人工智能:
![A circular graphic with 6 icons around the edges with arrows pointing counter-clockwise from one icons to the next in a full circle and one icon in the middle. Icons read along the edges from top and then to the left: rare disease patient; blood draw; genomics assay; upload data to web app; AI generated "cell atlas" of disease patient; dashboard of results. 中间的图标写着:临床医生.](./files/shorthand/GTOP4DQYIk/assets/23uWHdzlg7/cycle_large-1875x1459.png)
![](./files/shorthand/GTOP4DQYIk/assets/5yYDWTfkR1/istock-1500469862-frame-0ms-1280x720.jpg)
与蓝点的连接
扎卡里·德布琳的研究, 计算机助理教授, 他实验室里的学生就是这种影响的一个例子 蓝点,大峡谷’年代倡议 to support emerging technology and connect education with industry and business, 将在西密歇根和其他地方.
德布琳说 the infrastructure of Blue Dot connects individual partners to solve problems for the greater good. 在这种情况下, 德布琳 and his research team are developing tools using artificial intelligence to create a working AI model for medical teams to use to personalize medicine for patients with rare diseases.
Dr. 迦勒Bupp, 处长, Medical Genetics and Genomics at Corewell Health and Helen DeVos Children's Hospital, said the leadership from top executives at 博天堂官方 and Corewell Health has opened the door to this partnership and more connections.
”This is among the priorities of President (Philomena) Mantella and Tina Freese Decker (president and CEO of Corewell Health),布普说。. ”Here we have two great leaders looking at their local organizations and seeing the connections. 大峡谷正在推动人工智能创新,所以这是一个自然的合作伙伴关系.”
去年年底, 政府. Gretchen Whitmer signed a $616 million supplemental funding bill during an event at 博天堂官方为该校的蓝点计划提供了3000万美元的资金支持.
![蓝点圆图:应用学习, applied research innovative campus; talent, 创新, 能力](./files/shorthand/GTOP4DQYIk/assets/T3it0uj6Jc/blue_dot_slide_01-3200x2000.jpg)