Search Articles

View query in Help articles search

Search Results (1 to 10 of 17 Results)

Download search results: CSV END BibTex RIS


Developing an ICD-10 Coding Assistant: Pilot Study Using RoBERTa and GPT-4 for Term Extraction and Description-Based Code Selection

Developing an ICD-10 Coding Assistant: Pilot Study Using RoBERTa and GPT-4 for Term Extraction and Description-Based Code Selection

The system is hierarchically organized and includes detailed coding guidelines. Medical coding entails the allocation of unique codes to medical records and is a standard procedure in most hospitals. Hospitals collect a list of ICD codes relevant to each patient’s hospital admission. Medical coding is a time-consuming and error-prone task, which has led to interest in automating it, and in turn, to the emergence of the medical coding subfield within medical natural language processing (NLP) [1,2].

Sander Puts, Catharina M L Zegers, Andre Dekker, Iñigo Bermejo

JMIR Form Res 2025;9:e60095

Patient Perspectives on AI for Mental Health Care: Cross-Sectional Survey Study

Patient Perspectives on AI for Mental Health Care: Cross-Sectional Survey Study

Free-text responses to the 2 open-ended questions were analyzed using a singular coding scheme. A second analyst then used the coding scheme to independently dual code each free-text response. The analysts met with a third team member to resolve discrepancies, coding via consensus and updating the codebook throughout the discussion.

Natalie Benda, Pooja Desai, Zayan Reza, Anna Zheng, Shiveen Kumar, Sarah Harkins, Alison Hermann, Yiye Zhang, Rochelle Joly, Jessica Kim, Jyotishman Pathak, Meghan Reading Turchioe

JMIR Ment Health 2024;11:e58462

Determining an Appropriate Sample Size for Qualitative Interviews to Achieve True and Near Code Saturation: Secondary Analysis of Data

Determining an Appropriate Sample Size for Qualitative Interviews to Achieve True and Near Code Saturation: Secondary Analysis of Data

We then extracted code- and interview-specific data from the NVivo databases—including transcript name, code name, number of files coded, number of associated parent and child codes, and number of coding references—and compiled these data in an Excel (Microsoft Corp) file.

Claudia M Squire, Kristen C Giombi, Douglas J Rupert, Jacqueline Amoozegar, Peyton Williams

J Med Internet Res 2024;26:e52998

Using a Semiautomated Procedure (CleanADHdata.R Script) to Clean Electronic Adherence Monitoring Data: Tutorial

Using a Semiautomated Procedure (CleanADHdata.R Script) to Clean Electronic Adherence Monitoring Data: Tutorial

The script Clean ADHdata.R can be used to clean adherence data collected with the EM and other digital technologies and can be adapted according to the study aims and designs (eg, the calculation of treatment implementation can be revised in the dedicated coding section). Providing blurred data sets, we allow users to practice using Clean ADHdata.R. Moreover, users can improve the script by providing feedback directly on the Git Hub platform so it can be updated upon needs.

Carole Bandiera, Jérôme Pasquier, Isabella Locatelli, Marie P Schneider

JMIR Form Res 2024;8:e51013

A Web-Based, Respondent-Driven Sampling Survey Among Men Who Have Sex With Men (Kai Noi): Description of Methods and Characteristics

A Web-Based, Respondent-Driven Sampling Survey Among Men Who Have Sex With Men (Kai Noi): Description of Methods and Characteristics

We describe here the design, coding, and procedures of a largely automated web RDS system that aimed to replace and fulfill all attributes of a physical, staffed RDS office. A separate publication describes the sampling and survey findings [9]. Our goal was to design and conduct a web RDS among MSM in Thailand. The objectives were 2-fold: to create a ready-to-use (coded) web RDS system and to pilot the feasibility of collecting HIV-related biomarkers through such a sampling design.

Samart Karuchit, Panupit Thiengtham, Suvimon Tanpradech, Watcharapol Srinor, Thitipong Yingyong, Thananda Naiwatanakul, Sanny Northbrook, Wolfgang Hladik

JMIR Form Res 2024;8:e50812

Coding of Childhood Psychiatric and Neurodevelopmental Disorders in Electronic Health Records of a Large Integrated Health Care System: Validation Study

Coding of Childhood Psychiatric and Neurodevelopmental Disorders in Electronic Health Records of a Large Integrated Health Care System: Validation Study

This problem is further complicated by the accuracy of coding after the mandatory introduction of the International Classification of Diseases, Tenth Revision, Clinical Modification (ICD-10-CM) coding systems to classify diagnoses and procedures in the United States, which occurred on October 1, 2015 [12]. The ICD-10-CM provides increased specificity and detail for many health conditions [12], including childhood psychiatric and neurodevelopmental conditions.

Jiaxiao M Shi, Vicki Y Chiu, Chantal C Avila, Sierra Lewis, Daniella Park, Morgan R Peltier, Darios Getahun

JMIR Ment Health 2024;11:e56812

The Use of ICD-9-CM Coding to Identify COVID-19 Diagnoses and Determine Risk Factors for 30-Day Death Rate in Hospitalized Patients in Italy: Retrospective Study

The Use of ICD-9-CM Coding to Identify COVID-19 Diagnoses and Determine Risk Factors for 30-Day Death Rate in Hospitalized Patients in Italy: Retrospective Study

Indeed, with the beginning of the COVID-19 pandemic, the World Health Organization provided, in response to member state requests, codes and instructions for COVID-19 coding in the International Classification of Diseases, 10th Revision (ICD-10) and International Classification of Diseases, 11th Revision (ICD-11) [12], but not in the International Classification of Diseases, Ninth Revision, Clinical Modification (ICD-9-CM), which is the international classification of diseases currently used in Italy for coding

Barbara Giordani, Alessandra Burgio, Francesco Grippo, Alessandra Barone, Erica Eugeni, Giovanni Baglio

JMIR Public Health Surveill 2024;10:e44062

AI Education for Fourth-Year Medical Students: Two-Year Experience of a Web-Based, Self-Guided Curriculum and Mixed Methods Study

AI Education for Fourth-Year Medical Students: Two-Year Experience of a Web-Based, Self-Guided Curriculum and Mixed Methods Study

Students were asked to fill out formal surveys to rate their confidence in AI and ML concepts and in technical data science and coding skills. Before starting the elective, students were asked: How familiar are you with AI or ML concepts? (Likert scale, 1-5) How would you rate your technical data science or coding experience? (Likert scale, 1-5) After completing the elective, students were asked: Did you choose the Technical or Nontechnical Track?

Areeba Abid, Avinash Murugan, Imon Banerjee, Saptarshi Purkayastha, Hari Trivedi, Judy Gichoya

JMIR Med Educ 2024;10:e46500

Assessing Facilitator Fidelity to Principles of Public Deliberation: Tutorial

Assessing Facilitator Fidelity to Principles of Public Deliberation: Tutorial

To expedite the coding process, we developed 3 templates to facilitate the process. Template 1 displays the coding rules, template 2 is a table for organizing and displaying the codes, and template 3 is a table for displaying the final code counts.

Claire Draucker, Andrés Carrión, Mary A Ott, Amelia Knopf

JMIR Form Res 2023;7:e51202

An End-to-End Natural Language Processing Application for Prediction of Medical Case Coding Complexity: Algorithm Development and Validation

An End-to-End Natural Language Processing Application for Prediction of Medical Case Coding Complexity: Algorithm Development and Validation

Therefore, the improvement of medical coding using AI-assisted strategies remains an open challenge (Kaur R, unpublished data, July 2021). The purpose of our study was not to find a way to predict ICD-10 codes from medical records. Instead, it was to improve coding quality and efficiency by predicting coding complexity before the coding process.

He Ayu Xu, Bernard Maccari, Hervé Guillain, Julien Herzen, Fabio Agri, Jean Louis Raisaro

JMIR Med Inform 2023;11:e38150