Cargando…

Bias or biology? Importance of model interpretation in machine learning studies from electronic health records

OBJECTIVE: The rate of diabetic complication progression varies across individuals and understanding factors that alter the rate of complication progression may uncover new clinical interventions for personalized diabetes management. MATERIALS AND METHODS: We explore how various machine learning (ML...

Descripción completa

Detalles Bibliográficos
Autores principales:	Momenzadeh, Amanda, Shamsa, Ali, Meyer, Jesse G
Formato:	Online Artículo Texto
Lenguaje:	English
Publicado:	Oxford University Press 2022
Materias:	Research and Applications
Acceso en línea:	https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9360778/ https://www.ncbi.nlm.nih.gov/pubmed/35958671 http://dx.doi.org/10.1093/jamiaopen/ooac063

Ejemplares similares

Using statistical and machine learning to help institutions detect suspicious access to electronic health records
por: Boxwala, Aziz A, et al.
Publicado: (2011)

Natural language processing and machine learning of electronic health records for prediction of first-time suicide attempts
por: Tsui, Fuchiang R, et al.
Publicado: (2021)

New onset delirium prediction using machine learning and long short-term memory (LSTM) in electronic health record
por: Liu, Siru, et al.
Publicado: (2022)

Detecting diabetic retinopathy through machine learning on electronic health record data from an urban, safety net healthcare system
por: Ogunyemi, Omolola I, et al.
Publicado: (2021)

DEPLOYR: a technical framework for deploying custom real-time machine learning models into the electronic medical record
por: Corbin, Conor K, et al.
Publicado: (2023)

Predicting hypertension onset from longitudinal electronic health records with deep learning
por: Datta, Suparno, et al.
Publicado: (2022)

Comparison and interpretability of machine learning models to predict severity of chest injury
por: Kulshrestha, Sujay, et al.
Publicado: (2021)

The electronic elephant in the room: Physicians and the electronic health record
por: Kroth, Philip J, et al.
Publicado: (2018)

Validity of electronic health record-derived quality measurement for performance monitoring
por: Parsons, Amanda, et al.
Publicado: (2012)

Parameterizing time in electronic health record studies
por: Hripcsak, George, et al.
Publicado: (2015)

PIE: A prior knowledge guided integrated likelihood estimation method for bias reduction in association studies using electronic health records data
por: Huang, Jing, et al.
Publicado: (2017)

Adverse drug events and medication relation extraction in electronic health records with ensemble deep learning methods
por: Christopoulou, Fenia, et al.
Publicado: (2019)

Electronic health records improve clinical note quality
por: Burke, Harry B, et al.
Publicado: (2015)

Electronic health records and support for primary care teamwork
por: O’Malley, Ann S., et al.
Publicado: (2015)

Linkage of Hospital Records and Death Certificates by a Search Engine and Machine Learning
por: Cossin, Sebastien, et al.
Publicado: (2021)

Bias and fairness assessment of a natural language processing opioid misuse classifier: detection and mitigation of electronic health record data disadvantages across racial subgroups
por: Thompson, Hale M, et al.
Publicado: (2021)

An analysis of electronic health record-related patient safety concerns
por: Meeks, Derek W, et al.
Publicado: (2014)

Correlating electronic health record concepts with healthcare process events
por: Hripcsak, George, et al.
Publicado: (2013)

Efficiency and safety of speech recognition for documentation in the electronic health record
por: Hodgson, Tobias, et al.
Publicado: (2017)

Understanding the perceived role of electronic health records and workflow fragmentation on clinician documentation burden in emergency departments
por: Moy, Amanda J, et al.
Publicado: (2023)

Desiderata for computable representations of electronic health records-driven phenotype algorithms
por: Mo, Huan, et al.
Publicado: (2015)

Synergistic drug combinations from electronic health records and gene expression
por: Low, Yen S, et al.
Publicado: (2017)

Research use of electronic health records: patients’ perspectives on contact by researchers
por: Brelsford, Kathleen M, et al.
Publicado: (2018)

Provider perspectives on the integration of patient-reported outcomes in an electronic health record
por: Zhang, Renwen, et al.
Publicado: (2019)

Characterizing non-heroin opioid overdoses using electronic health records
por: Averitt, Amelia J, et al.
Publicado: (2019)

Characterizing outpatient problem list completeness and duplications in the electronic health record
por: Wang, Edward Chia-Heng, et al.
Publicado: (2020)

Test collections for electronic health record-based clinical information retrieval
por: Wang, Yanshan, et al.
Publicado: (2019)

Characterizing employment of colorectal cancer survivors using electronic health records
por: Varga, Alexandra, et al.
Publicado: (2021)

I2b2-etl: Python application for importing electronic health data into the informatics for integrating biology and the bedside platform
por: Wagholikar, Kavishwar B, et al.
Publicado: (2022)

Interpretable Machine Learning Prediction of Drug-Induced QT Prolongation: Electronic Health Record Analysis
por: Simon, Steven T, et al.
Publicado: (2022)

The SMART Platform: early experience enabling substitutable applications for electronic health records
por: Mandl, Kenneth D, et al.
Publicado: (2012)

Physician champions’ perspectives and practices on electronic health records implementation: challenges and strategies
por: Gui, Xinning, et al.
Publicado: (2020)

UK phenomics platform for developing and validating electronic health record phenotypes: CALIBER
por: Denaxas, Spiros, et al.
Publicado: (2019)

Structured override reasons for drug-drug interaction alerts in electronic health records
por: Wright, Adam, et al.
Publicado: (2019)

Usability challenges with electronic health records (EHRs) during prerounding on pediatric inpatients
por: Alami, Jawad, et al.
Publicado: (2022)

SMART on FHIR: a standards-based, interoperable apps platform for electronic health records
por: Mandel, Joshua C, et al.
Publicado: (2016)

Leveraging electronic health record documentation for Failure Mode and Effects Analysis team identification
por: Kricke, Gayle Shier, et al.
Publicado: (2017)

Using a custom mobile application for change management in an electronic health record implementation
por: Threatt, Tony, et al.
Publicado: (2019)

Formal representation of patients’ care context data: the path to improving the electronic health record
por: Colicchio, Tiago K, et al.
Publicado: (2020)

FIBER: enabling flexible retrieval of electronic health records data for clinical predictive modeling
por: Datta, Suparno, et al.
Publicado: (2021)

Cannot write session to /tmp/vufind_sessions/sess_smoifi3r16rq1lsv0es0dpojcb