Pub Date : 2023-12-17DOI: 10.1142/9789811286421_0016
V. Rogovchenko, Austin Sibu, Yang Ni
Digital health technologies such as wearable devices have transformed health data analytics, providing continuous, high-resolution functional data on various health metrics, thereby opening new avenues for innovative research. In this work, we introduce a new approach for generating causal hypotheses for a pair of a continuous functional variable (e.g., physical activities recorded over time) and a binary scalar variable (e.g., mobility condition indicator). Our method goes beyond traditional association-focused approaches and has the potential to reveal the underlying causal mechanism. We theoretically show that the proposed scalar-function causal model is identifiable with observational data alone. Our identifiability theory justifies the use of a simple yet principled algorithm to discern the causal relationship by comparing the likelihood functions of competing causal hypotheses. The robustness and applicability of our method are demonstrated through simulation studies and a real-world application using wearable device data from the National Health and Nutrition Examination Survey.
{"title":"Scalar-Function Causal Discovery for Generating Causal Hypotheses with Observational Wearable Device Data","authors":"V. Rogovchenko, Austin Sibu, Yang Ni","doi":"10.1142/9789811286421_0016","DOIUrl":"https://doi.org/10.1142/9789811286421_0016","url":null,"abstract":"Digital health technologies such as wearable devices have transformed health data analytics, providing continuous, high-resolution functional data on various health metrics, thereby opening new avenues for innovative research. In this work, we introduce a new approach for generating causal hypotheses for a pair of a continuous functional variable (e.g., physical activities recorded over time) and a binary scalar variable (e.g., mobility condition indicator). Our method goes beyond traditional association-focused approaches and has the potential to reveal the underlying causal mechanism. We theoretically show that the proposed scalar-function causal model is identifiable with observational data alone. Our identifiability theory justifies the use of a simple yet principled algorithm to discern the causal relationship by comparing the likelihood functions of competing causal hypotheses. The robustness and applicability of our method are demonstrated through simulation studies and a real-world application using wearable device data from the National Health and Nutrition Examination Survey.","PeriodicalId":34954,"journal":{"name":"Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing","volume":"451 ","pages":"201 - 213"},"PeriodicalIF":0.0,"publicationDate":"2023-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139176499","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-12-17DOI: 10.1142/9789811286421_0032
Inyoung Jun, Sara Ser, Scott A. Cohen, Jie Xu, Robert J. Lucero, Jiang Bian, M. Prosperi
This study quantifies health outcome disparities in invasive Methicillin-Resistant Staphylococcus aureus (MRSA) infections by leveraging a novel artificial intelligence (AI) fairness algorithm, the Fairness-Aware Causal paThs (FACTS) decomposition, and applying it to real-world electronic health record (EHR) data. We spatiotemporally linked 9 years of EHRs from a large healthcare provider in Florida, USA, with contextual social determinants of health (SDoH). We first created a causal structure graph connecting SDoH with individual clinical measurements before/upon diagnosis of invasive MRSA infection, treatments, side effects, and outcomes; then, we applied FACTS to quantify outcome potential disparities of different causal pathways including SDoH, clinical and demographic variables. We found moderate disparity with respect to demographics and SDoH, and all the top ranked pathways that led to outcome disparities in age, gender, race, and income, included comorbidity. Prior kidney impairment, vancomycin use, and timing were associated with racial disparity, while income, rurality, and available healthcare facilities contributed to gender disparity. From an intervention standpoint, our results highlight the necessity of devising policies that consider both clinical factors and SDoH. In conclusion, this work demonstrates a practical utility of fairness AI methods in public health settings.
{"title":"Quantifying Health Outcome Disparity in Invasive Methicillin-Resistant Staphylococcus aureus Infection using Fairness Algorithms on Real-World Data.","authors":"Inyoung Jun, Sara Ser, Scott A. Cohen, Jie Xu, Robert J. Lucero, Jiang Bian, M. Prosperi","doi":"10.1142/9789811286421_0032","DOIUrl":"https://doi.org/10.1142/9789811286421_0032","url":null,"abstract":"This study quantifies health outcome disparities in invasive Methicillin-Resistant Staphylococcus aureus (MRSA) infections by leveraging a novel artificial intelligence (AI) fairness algorithm, the Fairness-Aware Causal paThs (FACTS) decomposition, and applying it to real-world electronic health record (EHR) data. We spatiotemporally linked 9 years of EHRs from a large healthcare provider in Florida, USA, with contextual social determinants of health (SDoH). We first created a causal structure graph connecting SDoH with individual clinical measurements before/upon diagnosis of invasive MRSA infection, treatments, side effects, and outcomes; then, we applied FACTS to quantify outcome potential disparities of different causal pathways including SDoH, clinical and demographic variables. We found moderate disparity with respect to demographics and SDoH, and all the top ranked pathways that led to outcome disparities in age, gender, race, and income, included comorbidity. Prior kidney impairment, vancomycin use, and timing were associated with racial disparity, while income, rurality, and available healthcare facilities contributed to gender disparity. From an intervention standpoint, our results highlight the necessity of devising policies that consider both clinical factors and SDoH. In conclusion, this work demonstrates a practical utility of fairness AI methods in public health settings.","PeriodicalId":34954,"journal":{"name":"Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing","volume":"67 ","pages":"419-432"},"PeriodicalIF":0.0,"publicationDate":"2023-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139176332","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-12-17DOI: 10.1142/9789811286421_0040
Zhihan Zhang, Christiana Wang, Ziyin Zhao, Ziyue Yi, Arda Durmaz, Jennifer S. Yu, G. Bebek
Advances in molecular characterization have reshaped our understanding of low-grade glioma (LGG) subtypes, emphasizing the need for comprehensive classification beyond histology. Lever-aging this, we present a novel approach, network-based Subnetwork Enumeration, and Analysis (nSEA), to identify distinct LGG patient groups based on dysregulated molecular pathways. Using gene expression profiles from 516 patients and a protein-protein interaction network we generated 25 million sub-networks. Through our unsupervised bottom-up approach, we selected 92 subnetworks that categorized LGG patients into five groups. Notably, a new LGG patient group with a lack of mutations in EGFR, NF1, and PTEN emerged as a previously unidentified patient subgroup with unique clinical features and subnetwork states. Validation of the patient groups on an independent dataset demonstrated the robustness of our approach and revealed consistent survival traits across different patient populations. This study offers a comprehensive molecular classification of LGG, providing insights beyond traditional genetic markers. By integrating network analysis with patient clustering, we unveil a previously overlooked patient subgroup with potential implications for prognosis and treatment strategies. Our approach sheds light on the synergistic nature of driver genes and highlights the biological relevance of the identified subnetworks. With broad implications for glioma research, our findings pave the way for further investigations into the mechanistic underpinnings of LGG subtypes and their clinical relevance.Availability: Source code and supplementary data are available at https://github.com/bebeklab/nSEA.
{"title":"nSEA: n-Node Subnetwork Enumeration Algorithm Identifies Lower Grade Glioma Subtypes with Altered Subnetworks and Distinct Prognostics.","authors":"Zhihan Zhang, Christiana Wang, Ziyin Zhao, Ziyue Yi, Arda Durmaz, Jennifer S. Yu, G. Bebek","doi":"10.1142/9789811286421_0040","DOIUrl":"https://doi.org/10.1142/9789811286421_0040","url":null,"abstract":"Advances in molecular characterization have reshaped our understanding of low-grade glioma (LGG) subtypes, emphasizing the need for comprehensive classification beyond histology. Lever-aging this, we present a novel approach, network-based Subnetwork Enumeration, and Analysis (nSEA), to identify distinct LGG patient groups based on dysregulated molecular pathways. Using gene expression profiles from 516 patients and a protein-protein interaction network we generated 25 million sub-networks. Through our unsupervised bottom-up approach, we selected 92 subnetworks that categorized LGG patients into five groups. Notably, a new LGG patient group with a lack of mutations in EGFR, NF1, and PTEN emerged as a previously unidentified patient subgroup with unique clinical features and subnetwork states. Validation of the patient groups on an independent dataset demonstrated the robustness of our approach and revealed consistent survival traits across different patient populations. This study offers a comprehensive molecular classification of LGG, providing insights beyond traditional genetic markers. By integrating network analysis with patient clustering, we unveil a previously overlooked patient subgroup with potential implications for prognosis and treatment strategies. Our approach sheds light on the synergistic nature of driver genes and highlights the biological relevance of the identified subnetworks. With broad implications for glioma research, our findings pave the way for further investigations into the mechanistic underpinnings of LGG subtypes and their clinical relevance.Availability: Source code and supplementary data are available at https://github.com/bebeklab/nSEA.","PeriodicalId":34954,"journal":{"name":"Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing","volume":"43 10","pages":"521-533"},"PeriodicalIF":0.0,"publicationDate":"2023-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139176415","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-12-17DOI: 10.1142/9789811286421_0008
Jason H. Moore, Xi Li, Jui-Hsuan Chang, Nicholas P. Tatonetti, Dan Theodorescu, Yong Chen, F. Asselbergs, Mythreye Venkatesan, Zhiping Wang
The concept of a digital twin came from the engineering, industrial, and manufacturing domains to create virtual objects or machines that could inform the design and development of real objects. This idea is appealing for precision medicine where digital twins of patients could help inform healthcare decisions. We have developed a methodology for generating and using digital twins for clinical outcome prediction. We introduce a new approach that combines synthetic data and network science to create digital twins (i.e. SynTwin) for precision medicine. First, our approach starts by estimating the distance between all subjects based on their available features. Second, the distances are used to construct a network with subjects as nodes and edges defining distance less than the percolation threshold. Third, communities or cliques of subjects are defined. Fourth, a large population of synthetic patients are generated using a synthetic data generation algorithm that models the correlation structure of the data to generate new patients. Fifth, digital twins are selected from the synthetic patient population that are within a given distance defining a subject community in the network. Finally, we compare and contrast community-based prediction of clinical endpoints using real subjects, digital twins, or both within and outside of the community. Key to this approach are the digital twins defined using patient similarity that represent hypothetical unobserved patients with patterns similar to nearby real patients as defined by network distance and community structure. We apply our SynTwin approach to predicting mortality in a population-based cancer registry (n=87,674) from the Surveillance, Epidemiology, and End Results (SEER) program from the National Cancer Institute (USA). Our results demonstrate that nearest network neighbor prediction of mortality in this study is significantly improved with digital twins (AUROC=0.864, 95% CI=0.857-0.872) over just using real data alone (AUROC=0.791, 95% CI=0.781-0.800). These results suggest a network-based digital twin strategy using synthetic patients may add value to precision medicine efforts.
数字孪生的概念来自工程、工业和制造领域，旨在创建虚拟物体或机器，为真实物体的设计和开发提供参考。这一想法对精准医疗很有吸引力，患者的数字孪生可以帮助医疗决策提供依据。我们开发了一种生成和使用数字双胞胎进行临床结果预测的方法。我们介绍了一种结合合成数据和网络科学的新方法，为精准医疗创建数字孪生（即 SynTwin）。首先，我们的方法是根据所有受试者的可用特征来估计他们之间的距离。其次，利用这些距离构建一个网络，以受试者为节点，边缘定义的距离小于渗透阈值。第三，定义受试者的群落或小群。第四，使用合成数据生成算法生成大量合成患者，该算法可模拟数据的相关结构，生成新的患者。第五，从合成患者群体中挑选出一定距离内的数字双胞胎，定义网络中的主体群落。最后，我们使用真实受试者、数字双胞胎或社区内外的受试者对基于社区的临床终点预测进行比较和对比。这种方法的关键在于使用患者相似性定义的数字孪生，它代表了假设的未观察到的患者，其模式与网络距离和社区结构定义的附近真实患者相似。我们将 SynTwin 方法应用于预测美国国家癌症研究所（National Cancer Institute，USA）监测、流行病学和最终结果（Surveillance，Epidemiology，and End Results，SEER）项目中基于人群的癌症登记（n=87,674）中的死亡率。我们的研究结果表明，在这项研究中，使用数字孪生预测死亡率的最近网络邻居（AUROC=0.864，95% CI=0.857-0.872）明显优于仅使用真实数据（AUROC=0.791，95% CI=0.781-0.800）。这些结果表明，使用合成患者的基于网络的数字孪生策略可能会为精准医疗工作增添价值。
{"title":"SynTwin: A graph-based approach for predicting clinical outcomes using digital twins derived from synthetic patients.","authors":"Jason H. Moore, Xi Li, Jui-Hsuan Chang, Nicholas P. Tatonetti, Dan Theodorescu, Yong Chen, F. Asselbergs, Mythreye Venkatesan, Zhiping Wang","doi":"10.1142/9789811286421_0008","DOIUrl":"https://doi.org/10.1142/9789811286421_0008","url":null,"abstract":"The concept of a digital twin came from the engineering, industrial, and manufacturing domains to create virtual objects or machines that could inform the design and development of real objects. This idea is appealing for precision medicine where digital twins of patients could help inform healthcare decisions. We have developed a methodology for generating and using digital twins for clinical outcome prediction. We introduce a new approach that combines synthetic data and network science to create digital twins (i.e. SynTwin) for precision medicine. First, our approach starts by estimating the distance between all subjects based on their available features. Second, the distances are used to construct a network with subjects as nodes and edges defining distance less than the percolation threshold. Third, communities or cliques of subjects are defined. Fourth, a large population of synthetic patients are generated using a synthetic data generation algorithm that models the correlation structure of the data to generate new patients. Fifth, digital twins are selected from the synthetic patient population that are within a given distance defining a subject community in the network. Finally, we compare and contrast community-based prediction of clinical endpoints using real subjects, digital twins, or both within and outside of the community. Key to this approach are the digital twins defined using patient similarity that represent hypothetical unobserved patients with patterns similar to nearby real patients as defined by network distance and community structure. We apply our SynTwin approach to predicting mortality in a population-based cancer registry (n=87,674) from the Surveillance, Epidemiology, and End Results (SEER) program from the National Cancer Institute (USA). Our results demonstrate that nearest network neighbor prediction of mortality in this study is significantly improved with digital twins (AUROC=0.864, 95% CI=0.857-0.872) over just using real data alone (AUROC=0.791, 95% CI=0.781-0.800). These results suggest a network-based digital twin strategy using synthetic patients may add value to precision medicine efforts.","PeriodicalId":34954,"journal":{"name":"Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing","volume":"40 15","pages":"96-107"},"PeriodicalIF":0.0,"publicationDate":"2023-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139176416","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-12-17DOI: 10.1142/9789811286421_0028
Alena Orlenko, P. Freda, Attri Ghosh, Hyunjun Choi, Nicholas Matsumoto, T. Bright, Corey T. Walker, Tayo Obafemi-Ajayi, Jason H. Moore
This work demonstrates the use of cluster analysis in detecting fair and unbiased novel discoveries. Given a sample population of elective spinal fusion patients, we identify two overarching subgroups driven by insurance type. The Medicare group, associated with lower socioeconomic status, exhibited an over-representation of negative risk factors. The findings provide a compelling depiction of the interwoven socioeconomic and racial disparities present within the healthcare system, highlighting their consequential effects on health inequalities. The results are intended to guide design of fair and precise machine learning models based on intentional integration of population stratification.
{"title":"Cluster Analysis reveals Socioeconomic Disparities among Elective Spine Surgery Patients.","authors":"Alena Orlenko, P. Freda, Attri Ghosh, Hyunjun Choi, Nicholas Matsumoto, T. Bright, Corey T. Walker, Tayo Obafemi-Ajayi, Jason H. Moore","doi":"10.1142/9789811286421_0028","DOIUrl":"https://doi.org/10.1142/9789811286421_0028","url":null,"abstract":"This work demonstrates the use of cluster analysis in detecting fair and unbiased novel discoveries. Given a sample population of elective spinal fusion patients, we identify two overarching subgroups driven by insurance type. The Medicare group, associated with lower socioeconomic status, exhibited an over-representation of negative risk factors. The findings provide a compelling depiction of the interwoven socioeconomic and racial disparities present within the healthcare system, highlighting their consequential effects on health inequalities. The results are intended to guide design of fair and precise machine learning models based on intentional integration of population stratification.","PeriodicalId":34954,"journal":{"name":"Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing","volume":"280 1","pages":"359-373"},"PeriodicalIF":0.0,"publicationDate":"2023-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139176512","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-12-17DOI: 10.1142/9789811286421_0003
Serguei V. S. Pakhomov, Jacob Solinsky, Martin Michalowski, Veronika Bachanova
We present a fully automated AI-based system for intensive monitoring of cognitive symptoms of neurotoxicity that frequently appear as a result of immunotherapy of hematologic malignancies. Early manifestations of these symptoms are evident in the patient's speech in the form of mild aphasia and confusion and can be detected and effectively treated prior to onset of more serious and potentially life-threatening impairment. We have developed the Automated Neural Nursing Assistant (ANNA) system designed to conduct a brief cognitive assessment several times per day over the telephone for 5-14 days following infusion of the immunotherapy medication. ANNA uses a conversational agent based on a large language model to elicit spontaneous speech in a semi-structured dialogue, followed by a series of brief language-based neurocognitive tests. In this paper we share ANNA's design and implementation, results of a pilot functional evaluation study, and discuss technical and logistic challenges facing the introduction of this type of technology in clinical practice. A large-scale clinical evaluation of ANNA will be conducted in an observational study of patients undergoing immunotherapy at the University of Minnesota Masonic Cancer Center starting in the Fall 2023.
我们介绍了一种基于人工智能的全自动系统，用于密集监测血液恶性肿瘤免疫治疗过程中经常出现的神经毒性认知症状。这些症状的早期表现以轻微失语和意识模糊的形式在患者的言语中显现，可以在出现更严重和可能危及生命的损害之前检测出来并进行有效治疗。我们开发了自动神经护理助手（ANNA）系统，旨在通过电话在输注免疫疗法药物后的 5-14 天内每天多次进行简短的认知评估。ANNA 使用基于大型语言模型的对话代理，在半结构化对话中诱导自发言语，然后进行一系列基于语言的简短神经认知测试。在本文中，我们分享了 ANNA 的设计和实施、试点功能评估研究的结果，并讨论了在临床实践中引入此类技术所面临的技术和后勤挑战。从 2023 年秋季开始，明尼苏达大学松下癌症中心将对接受免疫疗法的患者进行观察研究，对 ANNA 进行大规模临床评估。
{"title":"A Conversational Agent for Early Detection of Neurotoxic Effects of Medications through Automated Intensive Observation.","authors":"Serguei V. S. Pakhomov, Jacob Solinsky, Martin Michalowski, Veronika Bachanova","doi":"10.1142/9789811286421_0003","DOIUrl":"https://doi.org/10.1142/9789811286421_0003","url":null,"abstract":"We present a fully automated AI-based system for intensive monitoring of cognitive symptoms of neurotoxicity that frequently appear as a result of immunotherapy of hematologic malignancies. Early manifestations of these symptoms are evident in the patient's speech in the form of mild aphasia and confusion and can be detected and effectively treated prior to onset of more serious and potentially life-threatening impairment. We have developed the Automated Neural Nursing Assistant (ANNA) system designed to conduct a brief cognitive assessment several times per day over the telephone for 5-14 days following infusion of the immunotherapy medication. ANNA uses a conversational agent based on a large language model to elicit spontaneous speech in a semi-structured dialogue, followed by a series of brief language-based neurocognitive tests. In this paper we share ANNA's design and implementation, results of a pilot functional evaluation study, and discuss technical and logistic challenges facing the introduction of this type of technology in clinical practice. A large-scale clinical evaluation of ANNA will be conducted in an observational study of patients undergoing immunotherapy at the University of Minnesota Masonic Cancer Center starting in the Fall 2023.","PeriodicalId":34954,"journal":{"name":"Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing","volume":"31 4","pages":"24-38"},"PeriodicalIF":0.0,"publicationDate":"2023-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139176553","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-12-17DOI: 10.1142/9789811286421_0004
Grant Duffy, Kai Christensen, David Ouyang
Advancements in medical imaging and artificial intelligence (AI) have revolutionized the field of cardiac diagnostics, providing accurate and efficient tools for assessing cardiac function. AI diagnostics claims to improve upon the human-to-human variation that is known to be significant. However, when put in practice, for cardiac ultrasound, AI models are being run on images acquired by human sonographers whose quality and consistency may vary. With more variation than other medical imaging modalities, variation in image acquisition may lead to out-of-distribution (OOD) data and unpredictable performance of the AI tools. Recent advances in ultrasound technology has allowed the acquisition of both 3D as well as 2D data, however 3D has more limited temporal and spatial resolution and is still not routinely acquired. Because the training datasets used when developing AI algorithms are mostly developed using 2D images, it is difficult to determine the impact of human variation on the performance of AI tools in the real world. The objective of this project is to leverage 3D echos to simulate realistic human variation of image acquisition and better understand the OOD performance of a previously validated AI model. In doing so, we develop tools for interpreting 3D echo data and quantifiably recreating common variation in image acquisition between sonographers. We also developed a technique for finding good standard 2D views in 3D echo volumes. We found the performance of the AI model we evaluated to be as expected when the view is good, but variations in acquisition position degraded AI model performance. Performance on far from ideal views was poor, but still better than random, suggesting that there is some information being used that permeates the whole volume, not just a quality view. Additionally, we found that variations in foreshortening didn't result in the same errors that a human would make.
{"title":"Leveraging 3D Echocardiograms to Evaluate AI Model Performance in Predicting Cardiac Function on Out-of-Distribution Data.","authors":"Grant Duffy, Kai Christensen, David Ouyang","doi":"10.1142/9789811286421_0004","DOIUrl":"https://doi.org/10.1142/9789811286421_0004","url":null,"abstract":"Advancements in medical imaging and artificial intelligence (AI) have revolutionized the field of cardiac diagnostics, providing accurate and efficient tools for assessing cardiac function. AI diagnostics claims to improve upon the human-to-human variation that is known to be significant. However, when put in practice, for cardiac ultrasound, AI models are being run on images acquired by human sonographers whose quality and consistency may vary. With more variation than other medical imaging modalities, variation in image acquisition may lead to out-of-distribution (OOD) data and unpredictable performance of the AI tools. Recent advances in ultrasound technology has allowed the acquisition of both 3D as well as 2D data, however 3D has more limited temporal and spatial resolution and is still not routinely acquired. Because the training datasets used when developing AI algorithms are mostly developed using 2D images, it is difficult to determine the impact of human variation on the performance of AI tools in the real world. The objective of this project is to leverage 3D echos to simulate realistic human variation of image acquisition and better understand the OOD performance of a previously validated AI model. In doing so, we develop tools for interpreting 3D echo data and quantifiably recreating common variation in image acquisition between sonographers. We also developed a technique for finding good standard 2D views in 3D echo volumes. We found the performance of the AI model we evaluated to be as expected when the view is good, but variations in acquisition position degraded AI model performance. Performance on far from ideal views was poor, but still better than random, suggesting that there is some information being used that permeates the whole volume, not just a quality view. Additionally, we found that variations in foreshortening didn't result in the same errors that a human would make.","PeriodicalId":34954,"journal":{"name":"Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing","volume":"34 9","pages":"39-52"},"PeriodicalIF":0.0,"publicationDate":"2023-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139176569","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-12-17DOI: 10.1142/9789811286421_0048
Cecilia Arighi, Steven E. Brenner, Zhiyong Lu
Large Language Models (LLMs) are a type of artificial intelligence that has been revolutionizing various fields, including biomedicine. They have the capability to process and analyze large amounts of data, understand natural language, and generate new content, making them highly desirable in many biomedical applications and beyond. In this workshop, we aim to introduce the attendees to an in-depth understanding of the rise of LLMs in biomedicine, and how they are being used to drive innovation and improve outcomes in the field, along with associated challenges and pitfalls.
{"title":"LARGE LANGUAGE MODELS (LLMS) AND CHATGPT FOR BIOMEDICINE.","authors":"Cecilia Arighi, Steven E. Brenner, Zhiyong Lu","doi":"10.1142/9789811286421_0048","DOIUrl":"https://doi.org/10.1142/9789811286421_0048","url":null,"abstract":"Large Language Models (LLMs) are a type of artificial intelligence that has been revolutionizing various fields, including biomedicine. They have the capability to process and analyze large amounts of data, understand natural language, and generate new content, making them highly desirable in many biomedical applications and beyond. In this workshop, we aim to introduce the attendees to an in-depth understanding of the rise of LLMs in biomedicine, and how they are being used to drive innovation and improve outcomes in the field, along with associated challenges and pitfalls.","PeriodicalId":34954,"journal":{"name":"Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing","volume":"34 4","pages":"641-644"},"PeriodicalIF":0.0,"publicationDate":"2023-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139176571","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-12-17DOI: 10.1142/9789811286421_0027
Mrinal Mishra, Layan Nahlawi, Yizhen Zhong, T. De, Guang Yang, Cristina Alarcon, M. Perera
Gene imputation and TWAS have become a staple in the genomics medicine discovery space; helping to identify genes whose regulation effects may contribute to disease susceptibility. However, the cohorts on which these methods are built are overwhelmingly of European Ancestry. This means that the unique regulatory variation that exist in non-European populations, specifically African Ancestry populations, may not be included in the current models. Moreover, African Americans are an admixed population, with a mix of European and African segments within their genome. No gene imputation model thus far has incorporated the effect of local ancestry (LA) on gene expression imputation. As such, we created LA-GEM which was trained and tested on a cohort of 60 African American hepatocyte primary cultures. Uniquely, LA-GEM include local ancestry inference in its prediction of gene expression. We compared the performance of LA-GEM to PrediXcan trained the same dataset (with no inclusion of local ancestry) We were able to reliably predict the expression of 2559 genes (1326 in LA-GEM and 1236 in PrediXcan). Of these, 546 genes were unique to LA-GEM, including the CYP3A5 gene which is critical to drug metabolism. We conducted TWAS analysis on two African American clinical cohorts with pharmacogenomics phenotypic information to identity novel gene associations. In our IWPC warfarin cohort, we identified 17 transcriptome-wide significant hits. No gene reached are prespecified significance level in the clopidogrel cohort. We did see suggestive association with RAS3A to P2RY12 Reactivity Units (PRU), a clinical measure of response to anti-platelet therapy. This method demonstrated the need for the incorporation of LA into study in admixed populations.
{"title":"LA-GEM: imputation of gene expression with incorporation of Local Ancestry","authors":"Mrinal Mishra, Layan Nahlawi, Yizhen Zhong, T. De, Guang Yang, Cristina Alarcon, M. Perera","doi":"10.1142/9789811286421_0027","DOIUrl":"https://doi.org/10.1142/9789811286421_0027","url":null,"abstract":"Gene imputation and TWAS have become a staple in the genomics medicine discovery space; helping to identify genes whose regulation effects may contribute to disease susceptibility. However, the cohorts on which these methods are built are overwhelmingly of European Ancestry. This means that the unique regulatory variation that exist in non-European populations, specifically African Ancestry populations, may not be included in the current models. Moreover, African Americans are an admixed population, with a mix of European and African segments within their genome. No gene imputation model thus far has incorporated the effect of local ancestry (LA) on gene expression imputation. As such, we created LA-GEM which was trained and tested on a cohort of 60 African American hepatocyte primary cultures. Uniquely, LA-GEM include local ancestry inference in its prediction of gene expression. We compared the performance of LA-GEM to PrediXcan trained the same dataset (with no inclusion of local ancestry) We were able to reliably predict the expression of 2559 genes (1326 in LA-GEM and 1236 in PrediXcan). Of these, 546 genes were unique to LA-GEM, including the CYP3A5 gene which is critical to drug metabolism. We conducted TWAS analysis on two African American clinical cohorts with pharmacogenomics phenotypic information to identity novel gene associations. In our IWPC warfarin cohort, we identified 17 transcriptome-wide significant hits. No gene reached are prespecified significance level in the clopidogrel cohort. We did see suggestive association with RAS3A to P2RY12 Reactivity Units (PRU), a clinical measure of response to anti-platelet therapy. This method demonstrated the need for the incorporation of LA into study in admixed populations.","PeriodicalId":34954,"journal":{"name":"Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing","volume":"23 6","pages":"341 - 358"},"PeriodicalIF":0.0,"publicationDate":"2023-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139176679","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In the intricate landscape of healthcare analytics, effective feature selection is a prerequisite for generating robust predictive models, especially given the common challenges of sample sizes and potential biases. Zoish uniquely addresses these issues by employing Shapley additive values—an idea rooted in cooperative game theory—to enable both transparent and automated feature selection. Unlike existing tools, Zoish is versatile, designed to seamlessly integrate with an array of machine learning libraries including scikit-learn, XGBoost, CatBoost, and imbalanced-learn. The distinct advantage of Zoish lies in its dual algorithmic approach for calculating Shapley values, allowing it to efficiently manage both large and small datasets. This adaptability renders it exceptionally suitable for a wide spectrum of healthcare-related tasks. The tool also places a strong emphasis on interpretability, providing comprehensive visualizations for analyzed features. Its customizable settings offer users fine-grained control over feature selection, thus optimizing for specific predictive objectives. This manuscript elucidates the mathematical framework underpinning Zoish and how it uniquely combines local and global feature selection into a single, streamlined process. To validate Zoish’s efficiency and adaptability, we present case studies in breast cancer prediction and Montreal Cognitive Assessment (MoCA) prediction in Parkinson’s disease, along with evaluations on 300 synthetic datasets. These applications underscore Zoish’s unparalleled performance in diverse healthcare contexts and against its counterparts.
{"title":"Zoish: A Novel Feature Selection Approach Leveraging Shapley Additive Values for Machine Learning Applications in Healthcare","authors":"Hossein Javedani Sadaei, Salvatore Loguercio, Mahdi Shafiei Neyestanak, Ali Torkamani, Daria Prilutsky","doi":"10.1142/9789811286421_0007","DOIUrl":"https://doi.org/10.1142/9789811286421_0007","url":null,"abstract":"In the intricate landscape of healthcare analytics, effective feature selection is a prerequisite for generating robust predictive models, especially given the common challenges of sample sizes and potential biases. Zoish uniquely addresses these issues by employing Shapley additive values—an idea rooted in cooperative game theory—to enable both transparent and automated feature selection. Unlike existing tools, Zoish is versatile, designed to seamlessly integrate with an array of machine learning libraries including scikit-learn, XGBoost, CatBoost, and imbalanced-learn. The distinct advantage of Zoish lies in its dual algorithmic approach for calculating Shapley values, allowing it to efficiently manage both large and small datasets. This adaptability renders it exceptionally suitable for a wide spectrum of healthcare-related tasks. The tool also places a strong emphasis on interpretability, providing comprehensive visualizations for analyzed features. Its customizable settings offer users fine-grained control over feature selection, thus optimizing for specific predictive objectives. This manuscript elucidates the mathematical framework underpinning Zoish and how it uniquely combines local and global feature selection into a single, streamlined process. To validate Zoish’s efficiency and adaptability, we present case studies in breast cancer prediction and Montreal Cognitive Assessment (MoCA) prediction in Parkinson’s disease, along with evaluations on 300 synthetic datasets. These applications underscore Zoish’s unparalleled performance in diverse healthcare contexts and against its counterparts.","PeriodicalId":34954,"journal":{"name":"Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing","volume":"768 ","pages":"81 - 95"},"PeriodicalIF":0.0,"publicationDate":"2023-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139176701","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：