JMIR Publications

Recent Articles:

• 

  Clinical Informatics in Low-Resource...

  Aug 22, 2019

  Development of an eHealth Readiness Assessment Framework for Botswana and Other Developing Countries: Interview Study

  View Authors View Abstract

  Authors List:

  • Kabelo Leonard Mauco  
  • Richard Ernest Scott  
  • Maurice Mars  

  Abstract:

  Background: Electronic health (eHealth) readiness has been defined as the preparedness of health care institutions or communities for the anticipated change brought about by programs related to information and communication technology use. To ascertain the degree of such preparedness, an eHealth readiness assessment (eHRA) is needed. Literature on the existing eHRA frameworks and tools shows high inconsistency in content, definitions, and recommendations, and none have been found to be entirely suitable for assessing eHealth readiness in the context of developing countries. To develop an informed eHRA framework and tools with applicability to Botswana and similar developing countries, insight was sought from a broad spectrum of eHealth key informants in Botswana to identify and inform relevant issues, including those not specifically addressed in available eHRA tools. Objective: The aim of this study was to evaluate key informant (local expert) opinions on aspects that need to be considered when developing an eHRA framework suitable for use in developing countries. Methods: Interviews with 18 purposively selected key informants were recorded and transcribed. Thematic analysis of transcripts involved the use of an iterative approach and NVivo 11 software. The major themes, as well as subthemes, emerging from the thematic analysis were then discussed and agreed upon by the authors through consensus. Results: Analysis of interviews identified four eHealth readiness themes (governance, stakeholder issues, resources, and access), with 33 subthemes and 9 sub-subthemes. A major finding was that these results did not directly correspond in content or order to those previously identified in the literature. The results highlighted the need to perform exploratory research before developing an eHRA to ensure that those topics of relevance and importance to the local setting are first identified and then explored in any subsequent eHRA using a locally relevant framework and stakeholder-specific tools. In addition, seven sectors in Botswana were found to play a role in ensuring successful implementation of eHealth projects and might be targets for assessment. Conclusions: Insight obtained from this study will be used to inform the development of an evidence-based eHealth readiness assessment framework suitable for use in developing countries such as Botswana.

  • JMIR Med Inform 2019;7(3):e12949

  • Choose one of the following formats:

  • Share this article:

    Or, copy the article link to your clipboard:

    Article URL

  • Citation

    • END

      for: Endnote

    • BibTeX

      for: BibDesk and LaTeX

    • RIS

      for: RefMan, Procite, Endnote, RefWorks

    Add this article to your Mendeley library Copy Citation to Clipboard

  • Metrics

    Discover Social Media mentions by hovering over the donut. Click the 'details' link for a full report.

• 

  Decision Support for Health...

  Aug 16, 2019

  Artificial Intelligence Versus Clinicians in Disease Diagnosis: Systematic Review

  View Authors View Abstract

  Authors List:

  • Jiayi Shen  
  • Casper J P Zhang  
  • Bangsheng Jiang  
  • Jiebin Chen  
  • Jian Song  
  • Zherui Liu  
  • Zonglin He  
  • Sum Yi Wong  
  • Po-Han Fang  
  • Wai-Kit Ming  

  Abstract:

  Background: Artificial intelligence (AI) has been extensively used in a range of medical fields to promote therapeutic development. The development of diverse AI techniques has also contributed to early detections, disease diagnoses, and referral management. However, concerns about the value of advanced AI in disease diagnosis have been raised by health care professionals, medical service providers, and health policy decision makers. Methods: We systematically searched articles published between January 2000 and March 2019 following the Preferred Reporting Items for Systematic reviews and Meta-Analysis in the following databases: Scopus, PubMed, CINAHL, Web of Science, and the Cochrane Library. According to the preset inclusion and exclusion criteria, only articles comparing the medical performance between advanced AI and human experts were considered. Results: A total of 9 articles were identified. A convolutional neural network was the commonly applied advanced AI technology. Owing to the variation in medical fields, there is a distinction between individual studies in terms of classification, labeling, training process, dataset size, and algorithm validation of AI. Performance indices reported in articles included diagnostic accuracy, weighted errors, false-positive rate, sensitivity, specificity, and the area under the receiver operating characteristic curve. The results showed that the performance of AI was at par with that of clinicians and exceeded that of clinicians with less experience. Conclusions: Current AI development has a diagnostic performance that is comparable with medical experts, especially in image recognition-related fields. Further studies can be extended to other types of medical imaging such as magnetic resonance imaging and other medical practices unrelated to images. With the continued development of AI-assisted technologies, the clinical implications underpinned by clinicians’ experience and guided by patient-centered health care principle should be constantly considered in future AI-related and other technology-based medical research.

  • JMIR Med Inform 2019;7(3):e10010

  • Choose one of the following formats:

  • Share this article:

    Or, copy the article link to your clipboard:

    Article URL

  • Citation

    • END

      for: Endnote

    • BibTeX

      for: BibDesk and LaTeX

    • RIS

      for: RefMan, Procite, Endnote, RefWorks

    Add this article to your Mendeley library Add this article to your CiteULike library Copy Citation to Clipboard

  • Metrics

    Discover Social Media mentions by hovering over the donut. Click the 'details' link for a full report.

• 

  Machine Learning

  Aug 15, 2019

  A Machine Learning Method for Identifying Lung Cancer Based on Routine Blood Indices: Qualitative Feasibility Study

  View Authors View Abstract

  Authors List:

  • Jiangpeng Wu  
  • Xiangyi Zan  
  • Liping Gao  
  • Jianhong Zhao  
  • Jing Fan  
  • Hengxue Shi  
  • Yixin Wan  
  • E Yu  
  • Shuyan Li  
  • Xiaodong Xie  

  Abstract:

  Background: Liquid biopsies based on blood samples have been widely accepted as a diagnostic and monitoring tool for cancers, but extremely high sensitivity is frequently needed due to the very low levels of the specially selected DNA, RNA, or protein biomarkers that are released into blood. However, routine blood indices tests are frequently ordered by physicians, as they are easy to perform and are cost effective. In addition, machine learning is broadly accepted for its ability to decipher complicated connections between multiple sets of test data and diseases. Objective: The aim of this study is to discover the potential association between lung cancer and routine blood indices and thereby help clinicians and patients to identify lung cancer based on these routine tests. Methods: The machine learning method known as Random Forest was adopted to build an identification model between routine blood indices and lung cancer that would determine if they were potentially linked. Ten-fold cross-validation and further tests were utilized to evaluate the reliability of the identification model. Results: In total, 277 patients with 49 types of routine blood indices were included in this study, including 183 patients with lung cancer and 94 patients without lung cancer. Throughout the course of the study, there was correlation found between the combination of 19 types of routine blood indices and lung cancer. Lung cancer patients could be identified from other patients, especially those with tuberculosis (which usually has similar clinical symptoms to lung cancer), with a sensitivity, specificity and total accuracy of 96.3%, 94.97% and 95.7% for the cross-validation results, respectively. This identification method is called the routine blood indices model for lung cancer, and it promises to be of help as a tool for both clinicians and patients for the identification of lung cancer based on routine blood indices. Conclusions: Lung cancer can be identified based on the combination of 19 types of routine blood indices, which implies that artificial intelligence can find the connections between a disease and the fundamental indices of blood, which could reduce the necessity of costly, elaborate blood test techniques for this purpose. It may also be possible that the combination of multiple indices obtained from routine blood tests may be connected to other diseases as well.

  • JMIR Med Inform 2019;7(3):e13476

  • Choose one of the following formats:

  • Share this article:

    Or, copy the article link to your clipboard:

    Article URL

  • Citation

    • END

      for: Endnote

    • BibTeX

      for: BibDesk and LaTeX

    • RIS

      for: RefMan, Procite, Endnote, RefWorks

    Add this article to your Mendeley library Add this article to your CiteULike library Copy Citation to Clipboard

  • Metrics

    Discover Social Media mentions by hovering over the donut. Click the 'details' link for a full report.

• 

  Ontologies, Classifications, and Coding

  Aug 12, 2019

  Core Data Elements in Acute Myeloid Leukemia: A Unified Medical Language System–Based Semantic Analysis and Experts’ Review

  View Authors View Abstract

  Authors List:

  • Christian Holz  
  • Torsten Kessler  
  • Martin Dugas  
  • Julian Varghese  

  Abstract:

  Background: For cancer domains such as acute myeloid leukemia (AML), a large set of data elements is obtained from different institutions with heterogeneous data definitions within one patient course. The lack of clinical data harmonization impedes cross-institutional electronic data exchange and future meta-analyses. Objective: This study aimed to identify and harmonize a semantic core of common data elements (CDEs) in clinical routine and research documentation, based on a systematic metadata analysis of existing documentation models. Methods: Lists of relevant data items were collected and reviewed by hematologists from two university hospitals regarding routine documentation and several case report forms of clinical trials for AML. In addition, existing registries and international recommendations were included. Data items were coded to medical concepts via the Unified Medical Language System (UMLS) by a physician and reviewed by another physician. On the basis of the coded concepts, the data sources were analyzed for concept overlaps and identification of most frequent concepts. The most frequent concepts were then implemented as data elements in the standardized format of the Operational Data Model by the Clinical Data Interchange Standards Consortium. Results: A total of 3265 medical concepts were identified, of which 1414 were unique. Among the 1414 unique medical concepts, the 50 most frequent ones cover 26.98% of all concept occurrences within the collected AML documentation. The top 100 concepts represent 39.48% of all concepts’ occurrences. Implementation of CDEs is available on a European research infrastructure and can be downloaded in different formats for reuse in different electronic data capture systems. Conclusions: Information management is a complex process for research-intense disease entities as AML that is associated with a large set of lab-based diagnostics and different treatment options. Our systematic UMLS-based analysis revealed the existence of a core data set and an exemplary reusable implementation for harmonized data capture is available on an established metadata repository.

  • JMIR Med Inform 2019;7(3):e13554

  • Choose one of the following formats:

  • Share this article:

    Or, copy the article link to your clipboard:

    Article URL

  • Citation

    • END

      for: Endnote

    • BibTeX

      for: BibDesk and LaTeX

    • RIS

      for: RefMan, Procite, Endnote, RefWorks

    Add this article to your Mendeley library Add this article to your CiteULike library Copy Citation to Clipboard

  • Metrics

    Discover Social Media mentions by hovering over the donut. Click the 'details' link for a full report.

• 

  New Technologies

  Aug 5, 2019

  The Value of Radio Frequency Identification in Quality Management of the Blood Transfusion Chain in an Academic Hospital Setting

  View Authors View Abstract

  Authors List:

  • Linda W Dusseljee-Peute  
  • Remko Van der Togt  
  • Bas Jansen  
  • Monique W Jaspers  

  Abstract:

  Background: A complex process like the blood transfusion chain could benefit from modern technologies such as radio frequency identification (RFID). RFID could, for example, play an important role in generating logistic and temperature data of blood products, which are important in assessing the quality of the logistic process of blood transfusions and the product itself. Objective: This study aimed to evaluate whether location, time stamp, and temperature data generated in real time by an active RFID system containing temperature sensors attached to red blood cell (RBC) products can be used to assess the compliance of the management of RBCs to 4 intrahospital European and Dutch guidelines prescribing logistic and temperature constraints in an academic hospital setting. Methods: An RFID infrastructure supported the tracking and tracing of 243 tagged RBCs in a clinical setting inside the hospital at the blood transfusion laboratory, the operating room complex, and the intensive care unit within the Academic Medical Center, a large academic hospital in Amsterdam, the Netherlands. The compliance of the management of 182 out of the 243 tagged RBCs could be assessed on their adherence to the following guidelines on intrahospital storage, transport, and distribution: (1) RBCs must be preserved within an environment with a temperature between 2°C and 6°C; (2) RBCs have to be transfused within 1 hour after they have left a validated cooling system; (3) RBCs that have reached a temperature above 10°C must not be restored or must be transfused within 24 hours or else be destroyed; (4) unused RBCs are to be returned to the BTL within 24 hours after they left the transfusion laboratory. Results: In total, 4 blood products (4/182 compliant; 2.2%) complied to all applicable guidelines. Moreover, 15 blood products (15/182 not compliant to 1 out of several guidelines; 8.2%) were not compliant to one of the guidelines of either 2 or 3 relevant guidelines. Finally, 148 blood products (148/182 not compliant to 2 guidelines; 81.3%) were not compliant to 2 out of the 3 relevant guidelines. Conclusions: The results point out the possibilities of using RFID technology to assess the quality of the blood transfusion chain itself inside a hospital setting in reference to intrahospital guidelines concerning the storage, transport, and distribution conditions of RBCs. This study shows the potentials of RFID in identifying potential bottlenecks in hospital organizations’ processes by use of objective data, which are to be tackled in process redesign efforts. The effect of these efforts can subsequently be evaluated by the use of RFID again. As such, RFID can play a significant role in optimization of the quality of the blood transfusion chain.

  • JMIR Med Inform 2019;7(3):e9510

  • Choose one of the following formats:

  • Share this article:

    Or, copy the article link to your clipboard:

    Article URL

  • Citation

    • END

      for: Endnote

    • BibTeX

      for: BibDesk and LaTeX

    • RIS

      for: RefMan, Procite, Endnote, RefWorks

    Add this article to your Mendeley library Add this article to your CiteULike library Copy Citation to Clipboard

  • Metrics

    Discover Social Media mentions by hovering over the donut. Click the 'details' link for a full report.

• 

  Electronic Health Records

  Aug 2, 2019

  Assessing the Availability of Data on Social and Behavioral Determinants in Structured and Unstructured Electronic Health Records: A Retrospective Analysis...

  View Authors View Abstract

  Authors List:

  • Elham Hatef  
  • Masoud Rouhizadeh  
  • Iddrisu Tia  
  • Elyse Lasser  
  • Felicia Hill-Briggs  
  • Jill Marsteller  
  • Hadi Kharrazi  

  Abstract:

  Background: Most US health care providers have adopted electronic health records (EHRs) that facilitate the uniform collection of clinical information. However, standardized data formats to capture social and behavioral determinants of health (SBDH) in structured EHR fields are still evolving and not adopted widely. Consequently, at the point of care, SBDH data are often documented within unstructured EHR fields that require time-consuming and subjective methods to retrieve. Meanwhile, collecting SBDH data using traditional surveys on a large sample of patients is infeasible for health care providers attempting to rapidly incorporate SBDH data in their population health management efforts. A potential approach to facilitate targeted SBDH data collection is applying information extraction methods to EHR data to prescreen the population for identification of immediate social needs. Objective: Our aim was to examine the availability and characteristics of SBDH data captured in the EHR of a multilevel academic health care system that provides both inpatient and outpatient care to patients with varying SBDH across Maryland. Methods: We measured the availability of selected patient-level SBDH in both structured and unstructured EHR data. We assessed various SBDH including demographics, preferred language, alcohol use, smoking status, social connection and/or isolation, housing issues, financial resource strains, and availability of a home address. EHR’s structured data were represented by information collected between January 2003 and June 2018 from 5,401,324 patients. EHR’s unstructured data represented information captured for 1,188,202 patients between July 2016 and May 2018 (a shorter time frame because of limited availability of consistent unstructured data). We used text-mining techniques to extract a subset of SBDH factors from EHR’s unstructured data. Results: We identified a valid address or zip code for 5.2 million (95.00%) of approximately 5.4 million patients. Ethnicity was captured for 2.7 million (50.00%), whereas race was documented for 4.9 million (90.00%) and a preferred language for 2.7 million (49.00%) patients. Information regarding alcohol use and smoking status was coded for 490,348 (9.08%) and 1,728,749 (32.01%) patients, respectively. Using the International Classification of Diseases–10th Revision diagnoses codes, we identified 35,171 (0.65%) patients with information related to social connection/isolation, 10,433 (0.19%) patients with housing issues, and 3543 (0.07%) patients with income/financial resource strain. Of approximately 1.2 million unique patients with unstructured data, 30,893 (2.60%) had at least one clinical note containing phrases referring to social connection/isolation, 35,646 (3.00%) included housing issues, and 11,882 (1.00%) had mentions of financial resource strain. Conclusions: Apart from demographics, SBDH data are not regularly collected for patients. Health care providers should assess the availability and characteristics of SBDH data in EHRs. Evaluating the quality of SBDH data can potentially enable health care providers to modify underlying workflows to improve the documentation, collection, and extraction of SBDH data from EHRs.

  • JMIR Med Inform 2019;7(3):e13802

  • Choose one of the following formats:

  • Share this article:

    Or, copy the article link to your clipboard:

    Article URL

  • Citation

    • END

      for: Endnote

    • BibTeX

      for: BibDesk and LaTeX

    • RIS

      for: RefMan, Procite, Endnote, RefWorks

    Add this article to your Mendeley library Add this article to your CiteULike library Copy Citation to Clipboard

  • Metrics

    Discover Social Media mentions by hovering over the donut. Click the 'details' link for a full report.

• 

  Natural Language Processing

  Jul 29, 2019

  Word Embedding for the French Natural Language in Health Care: Comparative Study

  View Authors View Abstract

  Authors List:

  • Emeric Dynomant  
  • Romain Lelong  
  • Badisse Dahamna  
  • Clément Massonnaud  
  • Gaétan Kerdelhué  
  • Julien Grosjean  
  • Stéphane Canu  
  • Stefan J Darmoni  

  Abstract:

  Background: Word embedding technologies, a set of language modeling and feature learning techniques in natural language processing (NLP), are now used in a wide range of applications. However, no formal evaluation and comparison have been made on the ability of each of the 3 current most famous unsupervised implementations (Word2Vec, GloVe, and FastText) to keep track of the semantic similarities existing between words, when trained on the same dataset. Objective: The aim of this study was to compare embedding methods trained on a corpus of French health-related documents produced in a professional context. The best method will then help us develop a new semantic annotator. Methods: Unsupervised embedding models have been trained on 641,279 documents originating from the Rouen University Hospital. These data are not structured and cover a wide range of documents produced in a clinical setting (discharge summary, procedure reports, and prescriptions). In total, 4 rated evaluation tasks were defined (cosine similarity, odd one, analogy-based operations, and human formal evaluation) and applied on each model, as well as embedding visualization. Results: Word2Vec had the highest score on 3 out of 4 rated tasks (analogy-based operations, odd one similarity, and human validation), particularly regarding the skip-gram architecture. Conclusions: Although this implementation had the best rate for semantic properties conservation, each model has its own qualities and defects, such as the training time, which is very short for GloVe, or morphological similarity conservation observed with FastText. Models and test sets produced by this study will be the first to be publicly available through a graphical interface to help advance the French biomedical research.

  • JMIR Med Inform 2019;7(3):e12310

  • Choose one of the following formats:

  • Share this article:

    Or, copy the article link to your clipboard:

    Article URL

  • Citation

    • END

      for: Endnote

    • BibTeX

      for: BibDesk and LaTeX

    • RIS

      for: RefMan, Procite, Endnote, RefWorks

    Add this article to your Mendeley library Add this article to your CiteULike library Copy Citation to Clipboard

  • Metrics

    Discover Social Media mentions by hovering over the donut. Click the 'details' link for a full report.

• 

  Electronic Health Records

  Jul 26, 2019

  Estimating Morbidity Rates Based on Routine Electronic Health Records in Primary Care: Observational Study

  View Authors View Abstract

  Authors List:

  • Mark MJ Nielen  
  • Inge Spronk  
  • Rodrigo Davids  
  • Joke C Korevaar  
  • René Poos  
  • Nancy Hoeymans  
  • Wim Opstelten  
  • Marianne AB van der Sande  
  • Marion CJ Biermans  
  • Francois G Schellevis  
  • Robert A Verheij  

  Abstract:

  Background: Routinely recorded electronic health records (EHRs) from general practitioners (GPs) are increasingly available and provide valuable data for estimating incidence and prevalence rates of diseases in the population. This paper describes how we developed an algorithm to construct episodes of illness based on EHR data to calculate morbidity rates. Objective: The goal of the research was to develop a simple and uniform algorithm to construct episodes of illness based on electronic health record data and develop a method to calculate morbidity rates based on these episodes of illness. Methods: The algorithm was developed in discussion rounds with two expert groups and tested with data from the Netherlands Institute for Health Services Research Primary Care Database, which consisted of a representative sample of 219 general practices covering a total population of 867,140 listed patients in 2012. Results: All 685 symptoms and diseases in the International Classification of Primary Care version 1 were categorized as acute symptoms and diseases, long-lasting reversible diseases, or chronic diseases. For the nonchronic diseases, a contact-free interval (the period in which it is likely that a patient will visit the GP again if a medical complaint persists) was defined. The constructed episode of illness starts with the date of diagnosis and ends at the time of the last encounter plus half of the duration of the contact-free interval. Chronic diseases were considered irreversible and for these diseases no contact-free interval was needed. Conclusions: An algorithm was developed to construct episodes of illness based on routinely recorded EHR data to estimate morbidity rates. The algorithm constitutes a simple and uniform way of using EHR data and can easily be applied in other registries.

  • JMIR Med Inform 2019;7(3):e11929

  • Choose one of the following formats:

  • Share this article:

    Or, copy the article link to your clipboard:

    Article URL

  • Citation

    • END

      for: Endnote

    • BibTeX

      for: BibDesk and LaTeX

    • RIS

      for: RefMan, Procite, Endnote, RefWorks

    Add this article to your Mendeley library Add this article to your CiteULike library Copy Citation to Clipboard

  • Metrics

    Discover Social Media mentions by hovering over the donut. Click the 'details' link for a full report.

• 

  Clinical Communication, Electronic...

  Jul 26, 2019

  Implementation of a Heart Failure Telemonitoring System in Home Care Nursing: Feasibility Study

  View Authors View Abstract

  Authors List:

  • Emily Seto  
  • Plinio Pelegrini Morita  
  • Jonathan Tomkun  
  • Theresa M Lee  
  • Heather Ross  
  • Cheryl Reid-Haughian  
  • Andrew Kaboff  
  • Deb Mulholland  
  • Joseph A Cafazzo  

  Abstract:

  Background: Telemonitoring (TM) of heart failure (HF) patients in a clinic setting has been shown to be effective if properly implemented, but little is known about the feasibility and impact of implementing TM through a home care nursing agency. Objective: This study aimed to determine the feasibility of implementing a mobile phone–based TM system through a home care nursing agency and to explore the feasibility of conducting a future effectiveness trial. Methods: A feasibility study was conducted by recruiting, through community cardiologists and family physicians, 10 to 15 HF patients who would use the TM system for 4 months by taking daily measurements of weight and blood pressure and recording symptoms. Home care nurses responded to alerts generated by the TM system through either a phone call and/or a home visit. Patients and their clinicians were interviewed poststudy to determine their perceptions and experiences of using the TM system. Results: Only one community cardiologist was recruited who was willing to refer patients to this study, even after multiple attempts were made to recruit further physicians, including family physicians. The cardiologist referred only 6 patients over a 6-month period, and half of the patients dropped out of the study. The identified barriers to implementing the TM system in home care nursing were numerous and led to the small recruitment in patients and clinicians and large dropout rate. These barriers included challenges in nurses contacting patients and physicians, issues related to retention, and challenges related to integrating the TM system into a complex home care nursing workflow. However, some potential benefits of TM through a home care nursing agency were indicated, including improved patient education, providing nurses with a better understanding of the patient’s health status, and reductions in home visits. Conclusions: Lessons learned included the need to incentivize physicians, to ensure streamlined processes for recruitment and communication, to target appropriate patient populations, and to create a core clinical group. Barriers encountered in this feasibility trial should be considered to determine their applicability when deploying innovations into different service delivery models.

  • JMIR Med Inform 2019;7(3):e11722

  • Choose one of the following formats:

  • Share this article:

    Or, copy the article link to your clipboard:

    Article URL

  • Citation

    • END

      for: Endnote

    • BibTeX

      for: BibDesk and LaTeX

    • RIS

      for: RefMan, Procite, Endnote, RefWorks

    Add this article to your Mendeley library Add this article to your CiteULike library Copy Citation to Clipboard

  • Metrics

    Discover Social Media mentions by hovering over the donut. Click the 'details' link for a full report.

• 

  Decision Support for Health...

  Jul 24, 2019

  A Real-Time Automated Patient Screening System for Clinical Trials Eligibility in an Emergency Department: Design and Evaluation

  View Authors View Abstract

  Authors List:

  • Yizhao Ni  
  • Monica Bermudez  
  • Stephanie Kennebeck  
  • Stacey Liddy-Hicks  
  • Judith Dexheimer  

  Abstract:

  Background: One critical hurdle for clinical trial recruitment is the lack of an efficient method for identifying subjects who meet the eligibility criteria. Given the large volume of data documented in electronic health records (EHRs), it is labor-intensive for the staff to screen relevant information, particularly within the time frame needed. To facilitate subject identification, we developed a natural language processing (NLP) and machine learning–based system, Automated Clinical Trial Eligibility Screener (ACTES), which analyzes structured data and unstructured narratives automatically to determine patients’ suitability for clinical trial enrollment. In this study, we integrated the ACTES into clinical practice to support real-time patient screening. Objective: This study aimed to evaluate ACTES’s impact on the institutional workflow, prospectively and comprehensively. We hypothesized that compared with the manual screening process, using EHR-based automated screening would improve efficiency of patient identification, streamline patient recruitment workflow, and increase enrollment in clinical trials. Methods: The ACTES was fully integrated into the clinical research coordinators’ (CRC) workflow in the pediatric emergency department (ED) at Cincinnati Children’s Hospital Medical Center. The system continuously analyzed EHR information for current ED patients and recommended potential candidates for clinical trials. Relevant patient eligibility information was presented in real time on a dashboard available to CRCs to facilitate their recruitment. To assess the system’s effectiveness, we performed a multidimensional, prospective evaluation for a 12-month period, including a time-and-motion study, quantitative assessments of enrollment, and postevaluation usability surveys collected from the CRCs. Results: Compared with manual screening, the use of ACTES reduced the patient screening time by 34% (P<.001). The saved time was redirected to other activities such as study-related administrative tasks (P=.03) and work-related conversations (P=.006) that streamlined teamwork among the CRCs. The quantitative assessments showed that automated screening improved the numbers of subjects screened, approached, and enrolled by 14.7%, 11.1%, and 11.1%, respectively, suggesting the potential of ACTES in streamlining recruitment workflow. Finally, the ACTES achieved a system usability scale of 80.0 in the postevaluation surveys, suggesting that it was a good computerized solution. Conclusions: By leveraging NLP and machine learning technologies, the ACTES demonstrated good capacity for improving efficiency of patient identification. The quantitative assessments demonstrated the potential of ACTES in streamlining recruitment workflow and improving patient enrollment. The postevaluation surveys suggested that the system was a good computerized solution with satisfactory usability.

  • JMIR Med Inform 2019;7(3):e14185

  • Choose one of the following formats:

  • Share this article:

    Or, copy the article link to your clipboard:

    Article URL

  • Citation

    • END

      for: Endnote

    • BibTeX

      for: BibDesk and LaTeX

    • RIS

      for: RefMan, Procite, Endnote, RefWorks

    Add this article to your Mendeley library Add this article to your CiteULike library Copy Citation to Clipboard

  • Metrics

    Discover Social Media mentions by hovering over the donut. Click the 'details' link for a full report.

• 

  Ontologies, Classifications, and Coding

  Jul 23, 2019

  Projection Word Embedding Model With Hybrid Sampling Training for Classifying ICD-10-CM Codes: Longitudinal Observational Study

  View Authors View Abstract

  Authors List:

  • Chin Lin  
  • Yu-Sheng Lou  
  • Dung-Jang Tsai  
  • Chia-Cheng Lee  
  • Chia-Jung Hsu  
  • Ding-Chung Wu  
  • Mei-Chuen Wang  
  • Wen-Hui Fang  

  Abstract:

  Background: Most current state-of-the-art models for searching the International Classification of Diseases, Tenth Revision Clinical Modification (ICD-10-CM) codes use word embedding technology to capture useful semantic properties. However, they are limited by the quality of initial word embeddings. Word embedding trained by electronic health records (EHRs) is considered the best, but the vocabulary diversity is limited by previous medical records. Thus, we require a word embedding model that maintains the vocabulary diversity of open internet databases and the medical terminology understanding of EHRs. Moreover, we need to consider the particularity of the disease classification, wherein discharge notes present only positive disease descriptions. Objective: We aimed to propose a projection word2vec model and a hybrid sampling method. In addition, we aimed to conduct a series of experiments to validate the effectiveness of these methods. Methods: We compared the projection word2vec model and traditional word2vec model using two corpora sources: English Wikipedia and PubMed journal abstracts. We used seven published datasets to measure the medical semantic understanding of the word2vec models and used these embeddings to identify the three–character-level ICD-10-CM diagnostic codes in a set of discharge notes. On the basis of embedding technology improvement, we also tried to apply the hybrid sampling method to improve accuracy. The 94,483 labeled discharge notes from the Tri-Service General Hospital of Taipei, Taiwan, from June 1, 2015, to June 30, 2017, were used. To evaluate the model performance, 24,762 discharge notes from July 1, 2017, to December 31, 2017, from the same hospital were used. Moreover, 74,324 additional discharge notes collected from seven other hospitals were tested. The F-measure, which is the major global measure of effectiveness, was adopted. Results: In medical semantic understanding, the original EHR embeddings and PubMed embeddings exhibited superior performance to the original Wikipedia embeddings. After projection training technology was applied, the projection Wikipedia embeddings exhibited an obvious improvement but did not reach the level of original EHR embeddings or PubMed embeddings. In the subsequent ICD-10-CM coding experiment, the model that used both projection PubMed and Wikipedia embeddings had the highest testing mean F-measure (0.7362 and 0.6693 in Tri-Service General Hospital and the seven other hospitals, respectively). Moreover, the hybrid sampling method was found to improve the model performance (F-measure=0.7371/0.6698). Conclusions: The word embeddings trained using EHR and PubMed could understand medical semantics better, and the proposed projection word2vec model improved the ability of medical semantics extraction in Wikipedia embeddings. Although the improvement from the projection word2vec model in the real ICD-10-CM coding task was not substantial, the models could effectively handle emerging diseases. The proposed hybrid sampling method enables the model to behave like a human expert.

  • JMIR Med Inform 2019;7(3):e14499

  • Choose one of the following formats:

  • Share this article:

    Or, copy the article link to your clipboard:

    Article URL

  • Citation

    • END

      for: Endnote

    • BibTeX

      for: BibDesk and LaTeX

    • RIS

      for: RefMan, Procite, Endnote, RefWorks

    Add this article to your Mendeley library Add this article to your CiteULike library Copy Citation to Clipboard

  • Metrics

    Discover Social Media mentions by hovering over the donut. Click the 'details' link for a full report.

• 

  Decision Support for Health...

  Jul 18, 2019

  Identification of Knee Osteoarthritis Based on Bayesian Network: Pilot Study

  View Authors View Abstract

  Authors List:

  • Bo Sheng  
  • Liang Huang  
  • Xiangbin Wang  
  • Jie Zhuang  
  • Lihua Tang  
  • Chao Deng  
  • Yanxin Zhang  

  Abstract:

  Background: Early identification of knee osteoarthritis (OA) can improve treatment outcomes and reduce medical costs. However, there are major limitations among existing classification or prediction models, including abstract data processing and complicated dataset attributes, which hinder their applications in clinical practice. Objective: The aim of this study was to propose a Bayesian network (BN)–based classification model to classify people with knee OA. The proposed model can be treated as a prescreening tool, which can provide decision support for health professionals. Methods: The proposed model’s structure was based on a 3-level BN structure and then retrained by the Bayesian Search (BS) learning algorithm. The model’s parameters were determined by the expectation-maximization algorithm. The used dataset included backgrounds, the target disease, and predictors. The performance of the model was evaluated based on classification accuracy, area under the curve (AUC), specificity, sensitivity, positive predictive value (PPV), and negative predictive value (NPV); it was also compared with other well-known classification models. A test was also performed to explore whether physical fitness tests could improve the performance of the proposed model. Results: A total of 249 elderly people between the ages of 60 and 80 years, living in the Kongjiang community (Shanghai), were recruited from April to September 2007. A total of 157 instances were adopted as the dataset after data preprocessing. The experimental results showed that the results of the proposed model were higher than, or equal to, the mean scores of other classification models: .754 for accuracy, .78 for AUC, .78 for specificity, and .73 for sensitivity. The proposed model provided .45 for PPV and .92 for NPV at the prevalence of 20%. The proposed model also showed a significant improvement when compared with the traditional BN model: 6.3% increase in accuracy (from .709 to .754), 4.0% increase in AUC (from .75 to .78), 6.8% increase in specificity (from .73 to .78), 5.8% increase in sensitivity (from .69 to .73), 15.4% increase in PPV (from .39 to .45), and 2.2% increase in NPV (from .90 to .92). Furthermore, the test results showed that the performance of the proposed model could be largely enhanced through physical fitness tests in 3 evaluation indices: 10.6% increase in accuracy (from .682 to .754), 16.4% increase in AUC (from .67 to .78), and 30.0% increase in specificity (from .60 to .78). Conclusions: The proposed model presents a promising method to classify people with knee OA when compared with other classification models and the traditional BN model. It could be implemented in clinical practice as a prescreening tool for knee OA, which would not only improve the quality of health care for elderly people but also reduce overall medical costs.

  • JMIR Med Inform 2019;7(3):e13562

  • Choose one of the following formats:

  • Share this article:

    Or, copy the article link to your clipboard:

    Article URL

  • Citation

    • END

      for: Endnote

    • BibTeX

      for: BibDesk and LaTeX

    • RIS

      for: RefMan, Procite, Endnote, RefWorks

    Add this article to your Mendeley library Add this article to your CiteULike library Copy Citation to Clipboard

  • Metrics

    Discover Social Media mentions by hovering over the donut. Click the 'details' link for a full report.