Journal of the American Medical Informatics Association (J Am Med Informat Assoc)

Publications in this journal

• Article: From health search to healthcare: explorations of intention and utilization via query logs and user surveys.

  Ryen W White, Eric Horvitz
  [show abstract] [hide abstract]
  ABSTRACT: OBJECTIVE: To better understand the relationship between online health-seeking behaviors and in-world healthcare utilization (HU) by studies of online search and access activities before and after queries that pursue medical professionals and facilities. MATERIALS AND METHODS: We analyzed data collected from logs of online searches gathered from consenting users of a browser toolbar from Microsoft (N=9740). We employed a complementary survey (N=489) to seek a deeper understanding of information-gathering, reflection, and action on the pursuit of professional healthcare. RESULTS: We provide insights about HU through the survey, breaking out its findings by different respondent marginalizations as appropriate. Observations made from search logs may be explained by trends observed in our survey responses, even though the user populations differ. DISCUSSION: The results provide insights about how users decide if and when to utilize healthcare resources, and how online health information seeking transitions to in-world HU. The findings from both the survey and the logs reveal behavioral patterns and suggest a strong relationship between search behavior and HU. Although the diversity of our survey respondents is limited and we cannot be certain that users visited medical facilities, we demonstrate that it may be possible to infer HU from long-term search behavior by the apparent influence that health concerns and professional advice have on search activity. CONCLUSIONS: Our findings highlight different phases of online activities around queries pursuing professional healthcare facilities and services. We also show that it may be possible to infer HU from logs without tracking people's physical location, based on the effect of HU on pre- and post-HU search behavior. This allows search providers and others to develop more robust models of interests and preferences by modeling utilization rather than simply the intention to utilize that is expressed in search queries.
  Journal of the American Medical Informatics Association 05/2013;
• Article: Using statistical text classification to identify health information technology incidents.

  Kevin E K Chai, Stephen Anthony, Enrico Coiera, Farah Magrabi
  [show abstract] [hide abstract]
  ABSTRACT: OBJECTIVE: To examine the feasibility of using statistical text classification to automatically identify health information technology (HIT) incidents in the USA Food and Drug Administration (FDA) Manufacturer and User Facility Device Experience (MAUDE) database. DESIGN: We used a subset of 570 272 incidents including 1534 HIT incidents reported to MAUDE between 1 January 2008 and 1 July 2010. Text classifiers using regularized logistic regression were evaluated with both 'balanced' (50% HIT) and 'stratified' (0.297% HIT) datasets for training, validation, and testing. Dataset preparation, feature extraction, feature selection, cross-validation, classification, performance evaluation, and error analysis were performed iteratively to further improve the classifiers. Feature-selection techniques such as removing short words and stop words, stemming, lemmatization, and principal component analysis were examined. MEASUREMENTS: κ statistic, F1 score, precision and recall. RESULTS: Classification performance was similar on both the stratified (0.954 F1 score) and balanced (0.995 F1 score) datasets. Stemming was the most effective technique, reducing the feature set size to 79% while maintaining comparable performance. Training with balanced datasets improved recall (0.989) but reduced precision (0.165). CONCLUSIONS: Statistical text classification appears to be a feasible method for identifying HIT reports within large databases of incidents. Automated identification should enable more HIT problems to be detected, analyzed, and addressed in a timely manner. Semi-supervised learning may be necessary when applying machine learning to big data analysis of patient safety incidents and requires further investigation.
  Journal of the American Medical Informatics Association 05/2013;
• Article: Health information technologies in geriatrics and gerontology: a mixed systematic review.

  Isabelle Vedel, Saeed Akhlaghpour, Isaac Vaghefi, Howard Bergman, Liette Lapointe
  [show abstract] [hide abstract]
  ABSTRACT: OBJECTIVE: To review, categorize, and synthesize findings from the literature about the application of health information technologies in geriatrics and gerontology (GGHIT). MATERIALS AND METHODS: This mixed-method systematic review is based on a comprehensive search of Medline, Embase, PsychInfo and ABI/Inform Global. Study selection and coding were performed independently by two researchers and were followed by a narrative synthesis. To move beyond a simple description of the technologies, we employed and adapted the diffusion of innovation theory (DOI). RESULTS: 112 papers were included. Analysis revealed five main types of GGHIT: (1) telecare technologies (representing half of the studies); (2) electronic health records; (3) decision support systems; (4) web-based packages for patients and/or family caregivers; and (5) assistive information technologies. On aggregate, the most consistent finding proves to be the positive outcomes of GGHIT in terms of clinical processes. Although less frequently studied, positive impacts were found on patients' health, productivity, efficiency and costs, clinicians' satisfaction, patients' satisfaction and patients' empowerment. DISCUSSION: Further efforts should focus on improving the characteristics of such technologies in terms of compatibility and simplicity. Implementation strategies also should be improved as trialability and observability are insufficient. CONCLUSIONS: Our results will help organizations in making decisions regarding the choice, planning and diffusion of GGHIT implemented for the care of older adults.
  Journal of the American Medical Informatics Association 05/2013;
• Article: Identifying medical terms in patient-authored text: a crowdsourcing-based approach.

  Diana Lynn Maclean, Jeffrey Heer
  [show abstract] [hide abstract]
  ABSTRACT: BACKGROUND AND OBJECTIVE: As people increasingly engage in online health-seeking behavior and contribute to health-oriented websites, the volume of medical text authored by patients and other medical novices grows rapidly. However, we lack an effective method for automatically identifying medical terms in patient-authored text (PAT). We demonstrate that crowdsourcing PAT medical term identification tasks to non-experts is a viable method for creating large, accurately-labeled PAT datasets; moreover, such datasets can be used to train classifiers that outperform existing medical term identification tools. MATERIALS AND METHODS: To evaluate the viability of using non-expert crowds to label PAT, we compare expert (registered nurses) and non-expert (Amazon Mechanical Turk workers; Turkers) responses to a PAT medical term identification task. Next, we build a crowd-labeled dataset comprising 10 000 sentences from MedHelp. We train two models on this dataset and evaluate their performance, as well as that of MetaMap, Open Biomedical Annotator (OBA), and NaCTeM's TerMINE, against two gold standard datasets: one from MedHelp and the other from CureTogether. RESULTS: When aggregated according to a corroborative voting policy, Turker responses predict expert responses with an F1 score of 84%. A conditional random field (CRF) trained on 10 000 crowd-labeled MedHelp sentences achieves an F1 score of 78% against the CureTogether gold standard, widely outperforming OBA (47%), TerMINE (43%), and MetaMap (39%). A failure analysis of the CRF suggests that misclassified terms are likely to be either generic or rare. CONCLUSIONS: Our results show that combining statistical models sensitive to sentence-level context with crowd-labeled data is a scalable and effective technique for automatically identifying medical terms in PAT.
  Journal of the American Medical Informatics Association 05/2013;
• Article: Facility characteristics associated with the use of electronic health records in residential care facilities.

  Amanda A Holup, Debra Dobbs, Hongdao Meng, Kathryn Hyer
  [show abstract] [hide abstract]
  ABSTRACT: The integration of electronic health records (EHRs) across care settings including residential care facilities (RCFs) promises to reduce medical errors and improve coordination of services. Using data from the 2010 National Survey of Residential Care Facilities (n=2302), this study examines the association between facility structural characteristics and the use of EHRs in RCFs. Findings indicate that in 2010, only 3% of RCFs nationwide were using an EHR. However, 55% of RCFs reported using a computerized system for one or more (but not all) of the functionalities defined by a basic EHR. Ownership, chain membership, staffing levels, and facility size were significantly associated with the use of one or more core EHR functionalities. These findings suggest that facility characteristics may play an important role in the adoption of EHRs in RCFs.
  Journal of the American Medical Informatics Association 05/2013;
• Article: Health surveillance using the internet and other sources of information.

  Lucila Ohno-Machado
  Journal of the American Medical Informatics Association 05/2013; 20(3):403.
• Article: President's column: interoperability--the 30% solution: from dialog and rhetoric to reality.

  Kevin M Fickenscher
  Journal of the American Medical Informatics Association 05/2013; 20(3):593-4.
• Article: Implementation and management of a biomedical observation dictionary in a large healthcare information system.

  Pierre-Yves Vandenbussche, Sylvie Cormont, Christophe André, Christel Daniel, Jean Delahousse, Jean Charlet, Eric Lepage
  [show abstract] [hide abstract]
  ABSTRACT: OBJECTIVE: This study shows the evolution of a biomedical observation dictionary within the Assistance Publique Hôpitaux Paris (AP-HP), the largest European university hospital group. The different steps are detailed as follows: the dictionary creation, the mapping to logical observation identifier names and codes (LOINC), the integration into a multiterminological management platform and, finally, the implementation in the health information system. METHODS: AP-HP decided to create a biomedical observation dictionary named AnaBio, to map it to LOINC and to maintain the mapping. A management platform based on methods used for knowledge engineering has been put in place. It aims at integrating AnaBio within the health information system and improving both the quality and stability of the dictionary. RESULTS: This new management platform is now active in AP-HP. The AnaBio dictionary is shared by 120 laboratories and currently includes 50 000 codes. The mapping implementation to LOINC reaches 40% of the AnaBio entries and uses 26% of LOINC records. The results of our work validate the choice made to develop a local dictionary aligned with LOINC. DISCUSSION AND CONCLUSIONS: This work constitutes a first step towards a wider use of the platform. The next step will support the entire biomedical production chain, from the clinician prescription, through laboratory tests tracking in the laboratory information system to the communication of results and the use for decision support and biomedical research. In addition, the increase in the mapping implementation to LOINC ensures the interoperability allowing communication with other international health institutions.
  Journal of the American Medical Informatics Association 05/2013;
• Article: Electronic medical records and the transgender patient: recommendations from the World Professional Association for Transgender Health EMR Working Group.

  Madeline B Deutsch, Jamison Green, Joanne Keatley, Gal Mayer, Jennifer Hastings, Alexandra M Hall
  [show abstract] [hide abstract]
  ABSTRACT: Transgender patients have particular needs with respect to demographic information and health records; specifically, transgender patients may have a chosen name and gender identity that differs from their current legally designated name and sex. Additionally, sex-specific health information, for example, a man with a cervix or a woman with a prostate, requires special attention in electronic health record (EHR) systems. The World Professional Association for Transgender Health (WPATH) is an international multidisciplinary professional association that publishes recognized standards for the care of transgender and gender variant persons. In September 2011, the WPATH Executive Committee convened an Electronic Medical Records Working Group comprised of both expert clinicians and medical information technology specialists, to make recommendations for developers, vendors, and users of EHR systems with respect to transgender patients. These recommendations and supporting rationale are presented here.
  Journal of the American Medical Informatics Association 04/2013;
• Article: Machine learning for predicting the response of breast cancer to neoadjuvant chemotherapy.

  Subramani Mani, Yukun Chen, Xia Li, Lori Arlinghaus, A Bapsi Chakravarthy, Vandana Abramson, Sandeep R Bhave, Mia A Levy, Hua Xu, Thomas E Yankeelov
  [show abstract] [hide abstract]
  ABSTRACT: OBJECTIVE: To employ machine learning methods to predict the eventual therapeutic response of breast cancer patients after a single cycle of neoadjuvant chemotherapy (NAC). MATERIALS AND METHODS: Quantitative dynamic contrast-enhanced MRI and diffusion-weighted MRI data were acquired on 28 patients before and after one cycle of NAC. A total of 118 semiquantitative and quantitative parameters were derived from these data and combined with 11 clinical variables. We used Bayesian logistic regression in combination with feature selection using a machine learning framework for predictive model building. RESULTS: The best predictive models using feature selection obtained an area under the curve of 0.86 and an accuracy of 0.86, with a sensitivity of 0.88 and a specificity of 0.82. DISCUSSION: With the numerous options for NAC available, development of a method to predict response early in the course of therapy is needed. Unfortunately, by the time most patients are found not to be responding, their disease may no longer be surgically resectable, and this situation could be avoided by the development of techniques to assess response earlier in the treatment regimen. The method outlined here is one possible solution to this important clinical problem. CONCLUSIONS: Predictive modeling approaches based on machine learning using readily available clinical and quantitative MRI data show promise in distinguishing breast cancer responders from non-responders after the first cycle of NAC.
  Journal of the American Medical Informatics Association 04/2013;
• Article: Combining rules and machine learning for extraction of temporal expressions and events from clinical narratives.

  Aleksandar Kovacevic, Azad Dehghan, Michele Filannino, John A Keane, Goran Nenadic
  [show abstract] [hide abstract]
  ABSTRACT: OBJECTIVE: Identification of clinical events (eg, problems, tests, treatments) and associated temporal expressions (eg, dates and times) are key tasks in extracting and managing data from electronic health records. As part of the i2b2 2012 Natural Language Processing for Clinical Data challenge, we developed and evaluated a system to automatically extract temporal expressions and events from clinical narratives. The extracted temporal expressions were additionally normalized by assigning type, value, and modifier. MATERIALS AND METHODS: The system combines rule-based and machine learning approaches that rely on morphological, lexical, syntactic, semantic, and domain-specific features. Rule-based components were designed to handle the recognition and normalization of temporal expressions, while conditional random fields models were trained for event and temporal recognition. RESULTS: The system achieved micro F scores of 90% for the extraction of temporal expressions and 87% for clinical event extraction. The normalization component for temporal expressions achieved accuracies of 84.73% (expression's type), 70.44% (value), and 82.75% (modifier). DISCUSSION: Compared to the initial agreement between human annotators (87-89%), the system provided comparable performance for both event and temporal expression mining. While (lenient) identification of such mentions is achievable, finding the exact boundaries proved challenging. CONCLUSIONS: The system provides a state-of-the-art method that can be used to support automated identification of mentions of clinical events and temporal expressions in narratives either to support the manual review process or as a part of a large-scale processing of electronic health databases.
  Journal of the American Medical Informatics Association 04/2013;
• Article: Predicting complications of percutaneous coronary intervention using a novel support vector method.

  Gyemin Lee, Hitinder S Gurm, Zeeshan Syed
  [show abstract] [hide abstract]
  ABSTRACT: OBJECTIVE: To explore the feasibility of a novel approach using an augmented one-class learning algorithm to model in-laboratory complications of percutaneous coronary intervention (PCI). MATERIALS AND METHODS: Data from the Blue Cross Blue Shield of Michigan Cardiovascular Consortium (BMC2) multicenter registry for the years 2007 and 2008 (n=41 016) were used to train models to predict 13 different in-laboratory PCI complications using a novel one-plus-class support vector machine (OP-SVM) algorithm. The performance of these models in terms of discrimination and calibration was compared to the performance of models trained using the following classification algorithms on BMC2 data from 2009 (n=20 289): logistic regression (LR), one-class support vector machine classification (OC-SVM), and two-class support vector machine classification (TC-SVM). For the OP-SVM and TC-SVM approaches, variants of the algorithms with cost-sensitive weighting were also considered. RESULTS: The OP-SVM algorithm and its cost-sensitive variant achieved the highest area under the receiver operating characteristic curve for the majority of the PCI complications studied (eight cases). Similar improvements were observed for the Hosmer-Lemeshow χ(2) value (seven cases) and the mean cross-entropy error (eight cases). CONCLUSIONS: The OP-SVM algorithm based on an augmented one-class learning problem improved discrimination and calibration across different PCI complications relative to LR and traditional support vector machine classification. Such an approach may have value in a broader range of clinical domains.
  Journal of the American Medical Informatics Association 04/2013;
• Article: Relationship between medication event rates and the Leapfrog computerized physician order entry evaluation tool.

  Alexander A Leung, Carol Keohane, Stuart Lipsitz, Eyal Zimlichman, Mary Amato, Steven R Simon, Michael Coffey, Nathan Kaufman, Bismarck Cadet, Gordon Schiff, Diane L Seger, David W Bates
  [show abstract] [hide abstract]
  ABSTRACT: OBJECTIVE: The Leapfrog CPOE evaluation tool has been promoted as a means of monitoring computerized physician order entry (CPOE). We sought to determine the relationship between Leapfrog scores and the rates of preventable adverse drug events (ADE) and potential ADE. MATERIALS AND METHODS: A cross-sectional study of 1000 adult admissions in five community hospitals from October 1, 2008 to September 30, 2010 was performed. Observed rates of preventable ADE and potential ADE were compared with scores reported by the Leapfrog CPOE evaluation tool. The primary outcome was the rate of preventable ADE and the secondary outcome was the composite rate of preventable ADE and potential ADE. RESULTS: Leapfrog performance scores were highly related to the primary outcome. A 43% relative reduction in the rate of preventable ADE was predicted for every 5% increase in Leapfrog scores (rate ratio 0.57; 95% CI 0.37 to 0.88). In absolute terms, four fewer preventable ADE per 100 admissions were predicted for every 5% increase in overall Leapfrog scores (rate difference -4.2; 95% CI -7.4 to -1.1). A statistically significant relationship between Leapfrog scores and the secondary outcome, however, was not detected. DISCUSSION: Our findings support the use of the Leapfrog tool as a means of evaluating and monitoring CPOE performance after implementation, as addressed by current certification standards. CONCLUSIONS: Scores from the Leapfrog CPOE evaluation tool closely relate to actual rates of preventable ADE. Leapfrog testing may alert providers to potential vulnerabilities and highlight areas for further improvement.
  Journal of the American Medical Informatics Association 04/2013;
• Article: Extracting coordinated patterns of DNA methylation and gene expression in ovarian cancer.

  Je-Gun Joung, Dokyoon Kim, Kyung Hwa Kim, Ju Han Kim
  [show abstract] [hide abstract]
  ABSTRACT: OBJECTIVE: DNA methylation, a regulator of gene expression, plays an important role in diverse biological processes including developmental process, carcinogenesis and aging. In particular, aberrant DNA methylation has been largely observed in several types of cancers. Currently, it is important to extract disease-specific gene sets associated with the regulation of DNA methylation. MATERIALS AND METHODS: Here we propose a novel approach to find the minimum regulatory units of genes, co-methylated and co-expressed gene pairs (MEGP) that are highly correlated gene pairs between DNA methylation and gene expression showing the co-regulatory relationship. To evaluate whether our method is applicable to extract disease-associated genes, we applied our method to a large-scale dataset from the Cancer Genome Atlas extracting significantly associated MEGP and analyzed their functional correlation. RESULTS: We observed that many MEGP physically interacted with each other and showed high semantic similarity with gene ontology terms. Furthermore, we performed gene set enrichment tests to identify how they are correlated in a complex biological process. Our MEGP were highly enriched in the biological pathway associated with ovarian cancers. CONCLUSIONS: Our approach is useful for discovering coordinated epigenetic markers associated with specific diseases.
  Journal of the American Medical Informatics Association 04/2013;
• Article: Quality improvement in preoperative assessment by implementation of an electronic decision support tool.

  Maria Flamm, Gerhard Fritsch, Martin Hysek, Sabine Klausner, Karl Entacher, Sigrid Panisch, Andreas C Soennichsen
  [show abstract] [hide abstract]
  ABSTRACT: OBJECTIVES: To evaluate the impact of the electronic decision support (eDS) tool 'PReOPerative evaluation' (PROP) on guideline adherence in preoperative assessment in statutory health care in Salzburg, Austria. MATERIALS AND METHODS: The evaluation was designed as a non-randomized controlled trial with a historical control group (CG). In 2007, we consecutively recruited 1363 patients admitted for elective surgery, and evaluated the preoperative assessment. In 2008, PROP was implemented and available online. In 2009 we recruited 1148 patients preoperatively assessed using PROP (294 outpatients, 854 hospital sector). Our analysis includes full blood count, liver function tests, coagulation parameters, electrolytes, ECG, and chest x-ray. RESULTS: The number of tests/patient without indication was 3.39 in the CG vs 0.60 in the intervention group (IG) (p<0.001). 97.8% (CG) vs 31.5% (IG) received at least one unnecessary test. However, we also observed an increase in recommended tests not performed/patient (0.05±0.27 (CG) vs 0.55±1.00 (IG), p<0.001). 4.2% (CG) vs 30.1% (IG) missed at least one necessary test. The guideline adherence (correctly tested/not tested) improved distinctively for all tests (1.6% (CG) vs 49.3% (IG), p<0.001). DISCUSSION: PROP reduced the number of unnecessary tests/patient by 2.79 which implied a reduction of patients' burden, and a relevant cut in unnecessary costs. However, the advantage in specificity caused an increase in the number of patients incorrectly not tested. Further research is required regarding the impact of PROP on perioperative outcomes.
  Journal of the American Medical Informatics Association 04/2013;
• Article: Privacy policies for health social networking sites.

  Jingquan Li
  [show abstract] [hide abstract]
  ABSTRACT: Health social networking sites (HSNS), virtual communities where users connect with each other around common problems and share relevant health data, have been increasingly adopted by medical professionals and patients. The growing use of HSNS like Sermo and PatientsLikeMe has prompted public concerns about the risks that such online data-sharing platforms pose to the privacy and security of personal health data. This paper articulates a set of privacy risks introduced by social networking in health care and presents a practical example that demonstrates how the risks might be intrinsic to some HSNS. The aim of this study is to identify and sketch the policy implications of using HSNS and how policy makers and stakeholders should elaborate upon them to protect the privacy of online health data.
  Journal of the American Medical Informatics Association 04/2013;
• Article: Ten key considerations for the successful implementation and adoption of large-scale health information technology.

  Kathrin M Cresswell, David W Bates, Aziz Sheikh
  [show abstract] [hide abstract]
  ABSTRACT: The implementation of health information technology interventions is at the forefront of most policy agendas internationally. However, such undertakings are often far from straightforward as they require complex strategic planning accompanying the systemic organizational changes associated with such programs. Building on our experiences of designing and evaluating the implementation of large-scale health information technology interventions in the USA and the UK, we highlight key lessons learned in the hope of informing the on-going international efforts of policymakers, health directorates, healthcare management, and senior clinicians.
  Journal of the American Medical Informatics Association 04/2013;
• Article: Identifying survival associated morphological features of triple negative breast cancer using multiple datasets.

  Chao Wang, Thierry Pécot, Debra L Zynger, Raghu Machiraju, Charles L Shapiro, Kun Huang
  [show abstract] [hide abstract]
  ABSTRACT: BACKGROUND AND OBJECTIVE: Biomarkers for subtyping triple negative breast cancer (TNBC) are needed given the absence of responsive therapy and relatively poor prediction of survival. Morphology of cancer tissues is widely used in clinical practice for stratifying cancer patients, while genomic data are highly effective to classify cancer patients into subgroups. Thus integration of both morphological and genomic data is a promising approach in discovering new biomarkers for cancer outcome prediction. Here we propose a workflow for analyzing histopathological images and integrate them with genomic data for discovering biomarkers for TNBC. MATERIALS AND METHODS: We developed an image analysis workflow for extracting a large collection of morphological features and deployed the same on histological images from The Cancer Genome Atlas (TCGA) TNBC samples during the discovery phase (n=44). Strong correlations between salient morphological features and gene expression profiles from the same patients were identified. We then evaluated the same morphological features in predicting survival using a local TNBC cohort (n=143). We further tested the predictive power on patient prognosis of correlated gene clusters using two other public gene expression datasets. RESULTS AND CONCLUSION: Using TCGA data, we identified 48 pairs of significantly correlated morphological features and gene clusters; four morphological features were able to separate the local cohort with significantly different survival outcomes. Gene clusters correlated with these four morphological features further proved to be effective in predicting patient survival using multiple public gene expression datasets. These results suggest the efficacy of our workflow and demonstrate that integrative analysis holds promise for discovering biomarkers of complex diseases.
  Journal of the American Medical Informatics Association 04/2013;