2017 IEEE International Conference on Healthcare Informatics (ICHI)最新文献_第5页

A Process-Oriented Approach for Supporting Clinical Decisions for Infection Management 一种支持感染管理临床决策的过程导向方法

2017 IEEE International Conference on Healthcare Informatics (ICHI) Pub Date : 2017-08-01 DOI: 10.1109/ICHI.2017.73

B. Cánovas-Segura, Francesca Zerbato, Barbara Oliboni, Combi Carlo, M. Campos, Antonio Morales Nicolás, J. Juarez, R. Marín, Francisco Palacios Ortega

{"title":"A Process-Oriented Approach for Supporting Clinical Decisions for Infection Management","authors":"B. Cánovas-Segura, Francesca Zerbato, Barbara Oliboni, Combi Carlo, M. Campos, Antonio Morales Nicolás, J. Juarez, R. Marín, Francisco Palacios Ortega","doi":"10.1109/ICHI.2017.73","DOIUrl":"https://doi.org/10.1109/ICHI.2017.73","url":null,"abstract":"Clinical practice guidelines have proven to be a powerful means for improving and standardizing healthcare assistance and patient outcome. Despite the recent increase in their diffusion and the advances made towards their automation, most clinicians do not use guidelines at the point of care in their daily practice. Indeed, clinical decision support systems are often retrospective and complicated to use. To promote the extraction and use of the process-oriented knowledge encoded in clinical guidelines, we propose to seamlessly integrate different techniques in order to incorporate procedural and medical knowledge into an existing clinical decision support system. In detail, we employ the BPMN and DMN process and decision modeling standards to model certain critical parts of selected guidelines. The obtained diagrams are combined with production rules to measure the current progress of clinical practice with respect to the steps outlined in the guideline and to provide contextualized clinical decision support. Moreover, we introduce a timeline view of medical activities to foster both the planning of future care steps and the adaptation of the guideline to the needs of an individual patient. In this paper, we describe the novelties introduced in a clinical decision support system capable of visualizing guideline progress and of supporting clinical decisions in the context of antimicrobial stewardship programs.","PeriodicalId":263611,"journal":{"name":"2017 IEEE International Conference on Healthcare Informatics (ICHI)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126520990","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}

引用次数: 13

Supervised Machine Learning to Predict Follow-Up Among Adjuvant Endocrine Therapy Patients 监督机器学习预测辅助内分泌治疗患者的随访

2017 IEEE International Conference on Healthcare Informatics (ICHI) Pub Date : 2017-08-01 DOI: 10.1109/ICHI.2017.46

Morgan Harrell, M. Levy, D. Fabbri

{"title":"Supervised Machine Learning to Predict Follow-Up Among Adjuvant Endocrine Therapy Patients","authors":"Morgan Harrell, M. Levy, D. Fabbri","doi":"10.1109/ICHI.2017.46","DOIUrl":"https://doi.org/10.1109/ICHI.2017.46","url":null,"abstract":"Long-term adjuvant endocrine therapy patients often fail to follow-up with their care providers for the recommended duration of time. We used electronic health record data, tumor registry records, and appointment logs to predict follow-up for an adjuvant endocrine therapy patient cohort. Learning predictors for follow-up may facilitate interventions that improve follow-up rates, and ultimately improve patient care in the adjuvant endocrine therapy patient population.We selected 1455 adjuvant endocrine therapy patients at Vanderbilt University Medical Center, and modeled them as a matrix of medical-related, appointment-related, and demographic related features derived from EHR data. We built and optimized a random forest classifier and neural network to differentiate between patients that follow-up, or fail to follow-up, with their care provider for at least five years. We measured follow-up three different ways: thought appointments with any care providers, appointments with an oncologist, and adjuvant endocrine therapy medication records. Classifiers make predictions at the start of adjuvant endocrine therapy, and additionally use temporal subsets of data to learn the change in accuracy as patient data accrues.Our best model is a random forest classifier combining medical-related, appointment-related, and demographic-related features to achieve an AUC of 0.74. The most predictive features for follow-up in our random forest model are total medication counts, patient age, and median income for zip code. We suggest that reliable prediction for follow-up may be correlated with amount of care received at VUMC (i.e., VUMC primary care).This study achieved moderately accurate prediction for followup in adjuvant endocrine therapy patients from electronic health record data. Predicting follow-up can facilitate interventions for improving follow-up rates and improve patient care for adjuvant endocrine therapy cohorts. This study demonstrates the ability to find opportunities for patient care improvement from EHR data.","PeriodicalId":263611,"journal":{"name":"2017 IEEE International Conference on Healthcare Informatics (ICHI)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126658236","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}

引用次数: 1

MyHealthToday: Helping Patients with their Healthschedule Using a 24-Hour Clock Visualization MyHealthToday:使用24小时时钟可视化帮助患者制定健康计划

2017 IEEE International Conference on Healthcare Informatics (ICHI) Pub Date : 2017-08-01 DOI: 10.1109/ICHI.2017.32

Robin De Croon, Bruno Cardoso, K. Verbert

引用次数: 0

Provider-Consumer Anomaly Detection for Healthcare Systems 医疗保健系统的提供者-消费者异常检测

2017 IEEE International Conference on Healthcare Informatics (ICHI) Pub Date : 2017-08-01 DOI: 10.1109/ICHI.2017.75

Luiz F. M. Carvalho, Carlos H. C. Teixeira, Wagner Meira Jr, M. Ester, O. Carvalho, Maria Helena Brandao

{"title":"Provider-Consumer Anomaly Detection for Healthcare Systems","authors":"Luiz F. M. Carvalho, Carlos H. C. Teixeira, Wagner Meira Jr, M. Ester, O. Carvalho, Maria Helena Brandao","doi":"10.1109/ICHI.2017.75","DOIUrl":"https://doi.org/10.1109/ICHI.2017.75","url":null,"abstract":"Anomaly detection is an important task that has been widely applied to different scenarios. In particular, its application in public healthcare is a crucial management task that can improve the quality of the health services and avoid loss of huge amounts of money. In this work we propose and evaluate, in a real scenario, a method for anomaly detection in healthcare based on a provider-consumer model. Our method is divided into two phases. In the first phase it assigns anomaly scores to the cities (consumers) as a function of their demand, then, in the second phase, it transfers the scores from cities to hospitals (providers). We applied the method to a real database from the Brazilian public healthcare that records medical procedures which cost more than $8.5 billion from 2008 to 2012, and demonstrated our method's ability to find potentially fraudulent hospitals. The method is being adopted by the Brazilian government for selecting anomalous hospitals to be investigated. Our main contributions are (i) a simple and effective method for anomaly detection in healthcare; (ii) our method does not require information about the providers nor medical rules; (iii) the analysis from the consumer perspective allows the detection of anomalies that could not be detected with traditional methods; and (iv) we applied the method to a real database and performed a detailed validation.","PeriodicalId":263611,"journal":{"name":"2017 IEEE International Conference on Healthcare Informatics (ICHI)","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124630826","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}

引用次数: 12

Code2Vec: Embedding and Clustering Medical Diagnosis Data 医学诊断数据的嵌入和聚类

2017 IEEE International Conference on Healthcare Informatics (ICHI) Pub Date : 2017-08-01 DOI: 10.1109/ICHI.2017.94

David Kartchner, Tanner Christensen, J. Humpherys, Sean Wade

引用次数: 12

Trend Displays to Support Critical Care: A Systematic Review 支持重症监护的趋势显示:系统回顾

2017 IEEE International Conference on Healthcare Informatics (ICHI) Pub Date : 2017-08-01 DOI: 10.1109/ICHI.2017.85

Noa Segall, D. Borbolla, G. Fiol, Rosalie G. Waller, Thomas J. Reese, Paige Nesbitt, M. Wright

{"title":"Trend Displays to Support Critical Care: A Systematic Review","authors":"Noa Segall, D. Borbolla, G. Fiol, Rosalie G. Waller, Thomas J. Reese, Paige Nesbitt, M. Wright","doi":"10.1109/ICHI.2017.85","DOIUrl":"https://doi.org/10.1109/ICHI.2017.85","url":null,"abstract":"An important aspect of designing information displays to support monitoring and decision-making in critical care is the representation of change of patient data over time. We systematically reviewed articles to identify novel alternatives to tabular and single variable plots of values over time to convey information about change in multiple related variables. Following screening of 5,119 articles, 28 met our inclusion criteria. They described 26 unique displays evaluated in 31 experiments. Methods for representing change varied widely. We classified these methods as enhanced graphical displays (enhanced plots of quantitative data over time), other displays (novel object and metaphoric displays), small multiples displays (multiple co-presented small graphic displays), and simple change indicator displays. Overall, findings support the value of an explicit display of trend information using many different approaches. Few studies directly compared different methods for displaying trend information in ways that would support broader conclusions about which approaches may be preferred for specific applications. The studies suggest that, for displaying patient data trends, it is feasible to develop electronic displays that will outperform both historical paper-based flowcharts and current electronic health record (EHR)-based tabular approaches. There is evidence to suggest that even minor improvements to current approaches such as the automatic presentation of simple line plots of trends on EHRs or the addition of simple graphical indicators of trend direction on patient monitors could lead to clinically meaningful improvements in diagnostic accuracy and efficiency.","PeriodicalId":263611,"journal":{"name":"2017 IEEE International Conference on Healthcare Informatics (ICHI)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122738096","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}

引用次数: 5

Signal Analysis for Voice Evaluation in Parkinson’s Disease 帕金森病语音评价的信号分析

2017 IEEE International Conference on Healthcare Informatics (ICHI) Pub Date : 2017-08-01 DOI: 10.1109/ICHI.2017.72

D. Mirarchi, P. Vizza, G. Tradigo, N. Lombardo, G. Arabia, P. Veltri

引用次数: 16

Disease Comorbidity Linkages between MEDLINE and Patient Data MEDLINE和患者数据之间的疾病合并症联系

2017 IEEE International Conference on Healthcare Informatics (ICHI) Pub Date : 2017-08-01 DOI: 10.1109/ICHI.2017.48

Tejaswi Rohit Anupindi, P. Srinivasan

{"title":"Disease Comorbidity Linkages between MEDLINE and Patient Data","authors":"Tejaswi Rohit Anupindi, P. Srinivasan","doi":"10.1109/ICHI.2017.48","DOIUrl":"https://doi.org/10.1109/ICHI.2017.48","url":null,"abstract":"This paper presents an analysis of a class of inferred links between MEDLINE and patient data. Records in the two datasets are linked via pairs of disease associations with a view to emphasizing disease comorbidities. In MEDLINE disease pairs are extracted by mining specific patterns such as MeSH disease term 1/etiology and MeSH disease term 2/complications. 701,780 pairs are extracted by our pattern set from a 2017 download of MEDLINE with close to 27 million records. The patient data, obtained from another study, has 6,088,553 disease cooccurrence pairs. Our methodology to infer connections involves mapping ICD9 codes and MeSH terms to UMLS concept ids followed by both exact and approximate matching strategies. The approximate matching strategy involves semantic relations present in the UMLS. We are able to connect 2,478,366 patient disease pairs encoded using 5 digit ICD9 codes to MEDLINE pairs (and therefore to the corresponding documents) and 536,685 MEDLINE disease pairs onto the patient disease pairs (and therefore implicitly to the corresponding patient records). While these numbers are large the percentages are between 43% and 77%. This indicates that other approaches for linking the two datasets would be of interest. Moreover, comorbidity is a particular viewpoint among many options. We suggest that the study of inferred links between biomedical datasets - especially between core datasets - is of great value in terms of enriching the biomedical web of knowledge.","PeriodicalId":263611,"journal":{"name":"2017 IEEE International Conference on Healthcare Informatics (ICHI)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131589671","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}

引用次数: 2

Managing Environments for Healthcare Information Systems Using Enterprise Application Integration 使用企业应用程序集成管理医疗保健信息系统的环境

2017 IEEE International Conference on Healthcare Informatics (ICHI) Pub Date : 2017-08-01 DOI: 10.1109/ICHI.2017.70

Changjin Kim

{"title":"Managing Environments for Healthcare Information Systems Using Enterprise Application Integration","authors":"Changjin Kim","doi":"10.1109/ICHI.2017.70","DOIUrl":"https://doi.org/10.1109/ICHI.2017.70","url":null,"abstract":"Systems integration (SI) in healthcare uses an enterprise application integration (EAI) or middleware layer to allow disjoint systems on various platforms to exchange information. Health Level 7 (HL7) is the communication exchange standard used in healthcare for this purpose. The message structure and usage of HL7 is standardized but the implementation of HL7 is widely customized to fit specific system, application, and site. Therefore, EAI is used to accomplish seamless integration by transforming and filtering messages, translating and mapping coded values, and distributing and gathering messages to and from different systems. Within healthcare IT, the number of integrated information systems (IS) has been increasing and multiple environments are being set up to support different types of testing, such as regression testing, upgrade testing, compliance testing, etc. The ability to support multiple independent test cycles simultaneously is critical to patient care because each integration testing is designed to replicate real scenarios and mitigate any changes that can potentially be introduced to a live environment. The role of a systems integrator has evolved from primarily developing interfaces to also managing interfaces in multiple environments. This paper introduces a more efficient way of managing various test environments in SI using an EAI.","PeriodicalId":263611,"journal":{"name":"2017 IEEE International Conference on Healthcare Informatics (ICHI)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116030137","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}

引用次数: 1

The Impact of Online Social Capital on Twitter Users At-Risk for Suicide 网络社会资本对推特用户自杀风险的影响

2017 IEEE International Conference on Healthcare Informatics (ICHI) Pub Date : 2017-08-01 DOI: 10.1109/ICHI.2017.87

C. Hanson, K. Meek, Emma Hunt, M. Searles, M. Barnes, C. Giraud-Carrier

引用次数: 2