Factors influencing the development of primary care data collection projects from electronic health records: a systematic review of the literature

BACKGROUND More than 17 million people worldwide, including 360,000 people in the UK, were diagnosed with cancer in 2018. Cancer prognosis and disease burden is highly dependent on disease stage at diagnosis. Most people diagnosed with cancer first present in primary care settings, where improved assessment of the (often vague) presenting symptoms of cancer could lead to earlier detection, and improved outcomes for patients. There is accumulating evidence that artificial intelligence (AI) can assist clinicians in making better clinical decisions in some areas of healthcare. OBJECTIVE We aimed to systematically review AI technologies based on electronic health record (EHR) data that may facilitate the earlier diagnosis of cancer in primary care settings. We evaluated the quality of the evidence, the phase of development the AI technologies have reached, the gaps that exist in the evidence, and the potential for use in primary care. METHODS We searched Medline, Embase, SCOPUS, and Web of Science databases from 1st January 2000 to 11th June 2019 (PROSPERO ID CRD42020176674), and included all studies providing evidence for accuracy or effectiveness of applying AI technologies to early detection of cancer using electronic health records. We included all study designs, in all settings and all languages. We extended these searches through a scoping review of commercial AI technologies. The main outcomes assessed were measures of diagnostic accuracy for cancer. RESULTS We identified 10,456 studies: 16 met the inclusion criteria, representing the data of 3,862,910 patients. 13 studies described the initial development and testing of AI algorithms and three studies described the validation of an AI technology in independent datasets. One study was based on prospectively collected data; only three studies were based on primary care data. We found no data on implementation barriers or cost-effectiveness. Risk-of-bias assessment highlighted a wide range in study quality. The additional scoping review of commercial AI tools identified 21 technologies, only one meeting our inclusion criteria. Meta-analysis was not undertaken due to heterogeneity of AI modalities, dataset characteristics and outcome measures. CONCLUSIONS Applying AI technologies to electronic health records for early detection of cancer in primary care is at an early stage of maturity. Further evidence is needed on performance using primary care data, implementation barriers and cost-effectiveness before widespread adoption into routine primary care clinical practice can be recommended. This study was supported by funding from the NIHR Cancer Policy Research Programme and Cancer Research UK.

Download Full-text

Patients’ online access to their electronic health records and linked online services: a systematic review in primary care

British Journal of General Practice ◽

10.3399/bjgp15x683941 ◽

2015 ◽

Vol 65 (632) ◽

pp. e141-e151 ◽

Cited By ~ 75

Author(s):

Freda Mold ◽

Simon de Lusignan ◽

Aziz Sheikh ◽

Azeem Majeed ◽

Jeremy C Wyatt ◽

...

Keyword(s):

Systematic Review ◽

Primary Care ◽

Electronic Health Records ◽

Online Services ◽

Health Records ◽

Online Access ◽

Electronic Health

Download Full-text

Training medical students and residents in the use of electronic health records: a systematic review of the literature

Journal of the American Medical Informatics Association ◽

10.1093/jamia/ocz178 ◽

2019 ◽

Vol 27 (1) ◽

pp. 175-180 ◽

Cited By ~ 7

Author(s):

Akshay Rajaram ◽

Zachary Hickey ◽

Nimesh Patel ◽

Joseph Newbigging ◽

Brent Wolfrom

Keyword(s):

Systematic Review ◽

Medical Education ◽

Medical Students ◽

Electronic Health Records ◽

Postgraduate Medical Education ◽

Health Improvement ◽

Review Of The Literature ◽

High Quality ◽

Health Records ◽

Electronic Health

Abstract Objective Our objectives were to identify educational interventions designed to equip medical students or residents with knowledge or skills related to various uses of electronic health records (EHRs), summarize and synthesize the results of formal evaluations of these initiatives, and compare the aims of these initiatives with the prescribed EHR-specific competencies for undergraduate and postgraduate medical education. Materials and Methods We conducted a systematic review of the literature following PRISMA (Preferred Reporting Items for Systematic Reviews and Meta Analyses) guidelines. We searched for English-language, peer-reviewed studies across 6 databases using a combination of Medical Subject Headings and keywords. We summarized the quantitative and qualitative results of included studies and rated studies according to the Best Evidence in Medical Education system. Results Our search yielded 619 citations, of which 11 studies were included. Seven studies involved medical students, 3 studies involved residents, and 1 study involved both groups. All interventions used a practical component involving entering information into a simulated or prototypical EHR. None of the interventions involved extracting, aggregating, or visualizing clinical data for panels of patients or specific populations. Discussion This review reveals few high-quality initiatives focused on training learners to engage with EHRs for both individual patient care and population health improvement. In comparing these interventions with the broad set of electronic records competencies expected of matriculating physicians, critical gaps in undergraduate and postgraduate medical education remain. Conclusions With the increasing adoption of EHRs and rise of competency-based medical education, educators should address the gaps in the training of future physicians to better prepare them to provide high quality care for their patients and communities.

Download Full-text

Preliminary results from the COPE study using primary-care electronic health records and environmental modelling to examine COPD exacerbations

British Journal of General Practice ◽

10.3399/bjgp18x696749 ◽

2018 ◽

Vol 68 (suppl 1) ◽

pp. bjgp18X696749 ◽

Cited By ~ 2

Author(s):

Maimoona Hashmi ◽

Mark Wright ◽

Kirin Sultana ◽

Benjamin Barratt ◽

Lia Chatzidiakou ◽

...

Keyword(s):

Primary Care ◽

Electronic Health Records ◽

Health Management ◽

Practice Research ◽

Chronic Obstructive ◽

Clinical Practice Research Datalink ◽

Health Records ◽

Preliminary Results ◽

Copd Exacerbations ◽

Electronic Health

BackgroundChronic Obstructive Airway Disease (COPD) is marked by often severely debilitating exacerbations. Efficient patient-centric research approaches are needed to better inform health management primary-care.AimThe ‘COPE study’ aims to develop a method of predicting COPD exacerbations utilising personal air quality sensors, environmental exposure modelling and electronic health records through the recruitment of patients from consenting GPs contributing to the Clinical Practice Research Datalink (CPRD).MethodThe study made use of Electronic Healthcare Records (EHR) from CPRD, an anonymised GP records database to screen and locate patients within GP practices in Central London. Personal air monitors were used to capture data on individual activities and environmental exposures. Output from the monitors were then linked with the EHR data to obtain information on COPD management, severity, comorbidities and exacerbations. Symptom changes not equating to full exacerbations were captured on diary cards. Linear regression was used to investigate the relationship between subject peak flow, symptoms, exacerbation events and exposure data.ResultsPreliminary results on the first 80 patients who have completed the study indicate variable susceptibility to environmental stressors in COPD patients. Some individuals appear highly susceptible to environmental stress and others appear to have unrelated triggers.ConclusionRecruiting patients through EHR for a study is feasible and allows easy collection of data for long term follow up. Portable environmental sensors could now be used to develop personalised models to predict risk of COPD exacerbations in susceptible individuals. Identification of direct links between participant health and activities would allow improved health management thus cost savings.

Download Full-text

Patient participation in electronic nursing documentation: an interview study among community nurses

BMC Nursing ◽

10.1186/s12912-021-00590-7 ◽

2021 ◽

Vol 20 (1) ◽

Author(s):

Kim De Groot ◽

Elisah B. Sneep ◽

Wolter Paans ◽

Anneke L. Francke

Keyword(s):

Data Collection ◽

Electronic Health Records ◽

Thematic Analysis ◽

Patient Participation ◽

Medical Condition ◽

Nursing Documentation ◽

Health Records ◽

Technical Problems ◽

Care Plans ◽

Electronic Health

Abstract Background Patient participation in nursing documentation has several benefits like including patients’ personal wishes in tailor-made care plans and facilitating shared decision-making. However, the rise of electronic health records may not automatically lead to greater patient participation in nursing documentation. This study aims to gain insight into community nurses’ experiences regarding patient participation in electronic nursing documentation, and to explore the challenges nurses face and the strategies they use for dealing with challenges regarding patient participation in electronic nursing documentation. Methods A qualitative descriptive design was used, based on the principles of reflexive thematic analysis. Nineteen community nurses working in home care and using electronic health records were recruited using purposive sampling. Interviews guided by an interview guide were conducted face-to-face or by phone in 2019. The interviews were inductively analysed in an iterative process of data collection–data analysis–more data collection until data saturation was achieved. The steps of thematic analysis were followed, namely familiarization with data, generating initial codes, searching for themes, reviewing themes, defining and naming themes, and reporting. Results Community nurses believed patient participation in nursing documentation has to be tailored to each patient. Actual participation depended on the phase of the nursing process that was being documented and was facilitated by patients’ trust in the accuracy of the documentation. Nurses came across challenges in three domains: those related to electronic health records (i.e. technical problems), to work (e.g. time pressure) and to the patients (e.g. the medical condition). Because of these challenges, nurses frequently did the documentation outside the patient’s home. Nurses still tried to achieve patient participation by verbally discussing patients’ views on the nursing care provided and then documenting those views at a later moment. Conclusions Although community nurses consider patient participation in electronic nursing documentation important, they perceive various challenges relating to electronic health records, work and the patients to realize patient participation. In dealing with these challenges, nurses often fall back on verbal communication about the documentation. These insights can help nurses and policy makers improve electronic health records and develop efficient strategies for improving patient participation in electronic nursing documentation.

Download Full-text

Estimating the population health burden of musculoskeletal conditions using primary care electronic health records

Rheumatology ◽

10.1093/rheumatology/keab109 ◽

2021 ◽

Author(s):

Dahai Yu ◽

George Peat ◽

Kelvin P Jordan ◽

James Bailey ◽

Daniel Prieto-Alhambra ◽

...

Keyword(s):

Primary Care ◽

Chronic Pain ◽

Low Back Pain ◽

Back Pain ◽

Electronic Health Records ◽

High Impact ◽

Low Back ◽

Musculoskeletal Health ◽

Health Records ◽

Electronic Health

Abstract Objectives Better indicators from affordable, sustainable data sources are needed to monitor population burden of musculoskeletal conditions. We propose five indicators of musculoskeletal health and assessed if routinely available primary care electronic health records (EHR) can estimate population levels in musculoskeletal consulters. Methods We collected validated patient-reported measures of pain experience, function and health status through a local survey of adults (≥35 years) presenting to English general practices over 12 months for low back pain, shoulder pain, osteoarthritis and other regional musculoskeletal disorders. Using EHR data we derived and validated models for estimating population levels of five self-reported indicators: prevalence of high impact chronic pain, overall musculoskeletal health (based on Musculoskeletal Health Questionnaire), quality of life (based on EuroQoL health utility measure), and prevalence of moderate-to-severe low back pain and moderate-to-severe shoulder pain. We applied models to a national EHR database (Clinical Practice Research Datalink) to obtain national estimates of each indicator for three successive years. Results The optimal models included recorded demographics, deprivation, consultation frequency, analgesic and antidepressant prescriptions, and multimorbidity. Applying models to national EHR, we estimated that 31.9% of adults (≥35 years) presenting with non-inflammatory musculoskeletal disorders in England in 2016/17 experienced high impact chronic pain. Estimated population health levels were worse in women, older aged and those in the most deprived neighbourhoods, and changed little over 3 years. Conclusion National and subnational estimates for a range of subjective indicators of non-inflammatory musculoskeletal health conditions can be obtained using information from routine electronic health records.

Download Full-text