Harvard data science review最新文献

Assessing the prognostic utility of clinical and radiomic features for COVID-19 patients admitted to ICU: challenges and lessons learned. 评估入住重症监护室的 COVID-19 患者的临床和放射学特征的预后效用：挑战与经验教训。

Harvard data science review Pub Date : 2024-01-01 Epub Date: 2024-01-31 DOI: 10.1162/99608f92.9d86a749

Yuming Sun, Stephen Salerno, Ziyang Pan, Eileen Yang, Chinakorn Sujimongkol, Jiyeon Song, Xinan Wang, Peisong Han, Donglin Zeng, Jian Kang, David C Christiani, Yi Li

{"title":"Assessing the prognostic utility of clinical and radiomic features for COVID-19 patients admitted to ICU: challenges and lessons learned.","authors":"Yuming Sun, Stephen Salerno, Ziyang Pan, Eileen Yang, Chinakorn Sujimongkol, Jiyeon Song, Xinan Wang, Peisong Han, Donglin Zeng, Jian Kang, David C Christiani, Yi Li","doi":"10.1162/99608f92.9d86a749","DOIUrl":"10.1162/99608f92.9d86a749","url":null,"abstract":"<p><p>Severe cases of COVID-19 often necessitate escalation to the Intensive Care Unit (ICU), where patients may face grave outcomes, including mortality. Chest X-rays play a crucial role in the diagnostic process for evaluating COVID-19 patients. Our collaborative efforts with Michigan Medicine in monitoring patient outcomes within the ICU have motivated us to investigate the potential advantages of incorporating clinical information and chest X-ray images for predicting patient outcomes. We propose an analytical workflow to address challenges such as the absence of standardized approaches for image pre-processing and data utilization. We then propose an ensemble learning approach designed to maximize the information derived from multiple prediction algorithms. This entails optimizing the weights within the ensemble and considering the common variability present in individual risk scores. Our simulations demonstrate the superior performance of this weighted ensemble averaging approach across various scenarios. We apply this refined ensemble methodology to analyze post-ICU COVID-19 mortality, an occurrence observed in 21% of COVID-19 patients admitted to the ICU at Michigan Medicine. Our findings reveal substantial performance improvement when incorporating imaging data compared to models trained solely on clinical risk factors. Furthermore, the addition of radiomic features yields even larger enhancements, particularly among older and more medically compromised patients. These results may carry implications for enhancing patient outcomes in similar clinical contexts.</p>","PeriodicalId":73195,"journal":{"name":"Harvard data science review","volume":"6 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11225107/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141556055","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Rejoinder: Building a Paradigm That Allows for the Possibility of Non-Ignorable Nonresponse 反驳:建立一个允许不可忽略的非响应可能性的范式

Harvard data science review Pub Date : 2023-11-09 DOI: 10.1162/99608f92.4187b1b4

Michael A. Bailey

引用次数: 0

Close to Refuge: Integrating AI and Human Insights for Intervention and Prevention: A Conversation With Seema Iyer 接近避难所:整合人工智能和人类的干预和预防见解:与Seema Iyer的对话

Harvard data science review Pub Date : 2023-10-27 DOI: 10.1162/99608f92.1a58d824

Seema Iyer, Xiao-Li Meng, Liberty Vittert

引用次数: 0

The Intelligence and Rationality of AI and Humans: A Conversation With Steven Pinker 《人工智能与人类的智慧与理性:与史蒂芬·平克的对话

Harvard data science review Pub Date : 2023-10-27 DOI: 10.1162/99608f92.c37d3572

Steven Pinker, Xiao-Li Meng, Liberty Vittert

引用次数: 0

Crisis? What Crisis? Sociology’s Slow Progress Toward Scientific Transparency 危机?什么危机?社会学走向科学透明的缓慢进程

Harvard data science review Pub Date : 2023-10-27 DOI: 10.1162/99608f92.151c41e3

Kim A. Weeden

引用次数: 0

Demonstrations of the Potential of AI-based Political Issue Polling 基于人工智能的政治问题民意调查的潜力展示

Harvard data science review Pub Date : 2023-10-27 DOI: 10.1162/99608f92.1d3cf75d

Nathan E. Sanders, Alex Ulinich, Bruce Schneier

引用次数: 0

Understanding and Fostering Regional Artificial Intelligence Ecosystems: A Case Study in Maine 理解和促进区域人工智能生态系统:以缅因州为例

Harvard data science review Pub Date : 2023-10-27 DOI: 10.1162/99608f92.dc2a1d1b

Hamit Hamutcu, Usama Fayyad, Michael Pollastri

引用次数: 0

Resolving the Credibility Crisis: Recommendations for Improving Predictive Algorithms for Clinical Utility 解决信誉危机:改进临床应用预测算法的建议

Harvard data science review Pub Date : 2023-10-27 DOI: 10.1162/99608f92.c1292c54

Stephen Ruberg, Sandeep Menon, Charmaine Demanuele

引用次数: 0

Perils and Opportunities of ChatGPT: A High School Perspective 聊天的风险和机遇:高中视角

Harvard data science review Pub Date : 2023-10-27 DOI: 10.1162/99608f92.9f0adc39

Nicole Lazar, James Byrns, Danielle Crowe, Meghan McGinty, Angela Abraham, Mike Guo, Megan Mann, Prithvi Narayanan, Lydia Roberts, Benjamin Sidore, Maxwell Wager

引用次数: 0

The Birth of a New Discipline: Data Science Education 一个新学科的诞生:数据科学教育

Harvard data science review Pub Date : 2023-10-27 DOI: 10.1162/99608f92.280afe66

Koby Mike, Benny Kimelfeld, Orit Hazzan

引用次数: 0