scholarly journals Envisioning an artificial intelligence documentation assistant for future primary care consultations: A co-design study with general practitioners

2020 ◽  
Vol 27 (11) ◽  
pp. 1695-1704
Author(s):  
A Baki Kocaballi ◽  
Kiran Ijaz ◽  
Liliana Laranjo ◽  
Juan C Quiroz ◽  
Dana Rezazadegan ◽  
...  

Abstract Objective The study sought to understand the potential roles of a future artificial intelligence (AI) documentation assistant in primary care consultations and to identify implications for doctors, patients, healthcare system, and technology design from the perspective of general practitioners. Materials and Methods Co-design workshops with general practitioners were conducted. The workshops focused on (1) understanding the current consultation context and identifying existing problems, (2) ideating future solutions to these problems, and (3) discussing future roles for AI in primary care. The workshop activities included affinity diagramming, brainwriting, and video prototyping methods. The workshops were audio-recorded and transcribed verbatim. Inductive thematic analysis of the transcripts of conversations was performed. Results Two researchers facilitated 3 co-design workshops with 16 general practitioners. Three main themes emerged: professional autonomy, human-AI collaboration, and new models of care. Major implications identified within these themes included (1) concerns with medico-legal aspects arising from constant recording and accessibility of full consultation records, (2) future consultations taking place out of the exam rooms in a distributed system involving empowered patients, (3) human conversation and empathy remaining the core tasks of doctors in any future AI-enabled consultations, and (4) questioning the current focus of AI initiatives on improved efficiency as opposed to patient care. Conclusions AI documentation assistants will likely to be integral to the future primary care consultations. However, these technologies will still need to be supervised by a human until strong evidence for reliable autonomous performance is available. Therefore, different human-AI collaboration models will need to be designed and evaluated to ensure patient safety, quality of care, doctor safety, and doctor autonomy.

2002 ◽  
Vol 8 (2) ◽  
pp. 59 ◽  
Author(s):  
Helen R. Winefield ◽  
Bronwyn M. Veale

The relationship between work stress and work performance has received little empirical attention in professional areas such as health care where measurement of work quality is difficult. In health sciences there is growing concern about work errors, although little is known about the determinants and prevention of these in primary care. This study aimed to explore connections between workload, work stress in terms of burnout, job satisfaction and retirement age intentions, and reported mistakes at work, in general practice. A randomly-selected sample of mid-career General Practitioners (aged 35-45 years) was approached and 86% agreed to participate (N = 30). Satisfaction with work supports was a better predictor of work stress indicators than was workload. There was no evidence of the hypothesised association between work stress and severity of mistakes. Although response biases are a likely threat to the validity of mistakes as a quality indicator, results can be seen as supporting the need for a systems-level analysis of primary care work performance.


2019 ◽  
Vol 19 (1) ◽  
Author(s):  
Doug Cronie ◽  
Hilde Perdok ◽  
Corine Verhoeven ◽  
Suze Jans ◽  
Marieke Hermus ◽  
...  

Abstract Background Job satisfaction is generally considered to be an important element of work quality and workplace relations. Little is known about levels of job satisfaction among hospital and primary-care midwives in the Netherlands. Proposed changes to the maternity care system in the Netherlands should consider how the working conditions of midwives affect their job satisfaction. Aim We aimed to measure and compare job satisfaction among hospital and primary-care midwives in the Netherlands. Methods Online survey of all practising midwives in the Netherlands using a validated measure of job satisfaction (the Leiden Quality of Work Questionnaire) to analyze the attitudes of hospital and primary-care midwives about their work. Descriptive and inferential statistics were used to assess differences between the two groups. Results Approximately one in six of all practising midwives in the Netherlands responded to our survey (hospital midwives n = 103, primary-care midwives n = 405). All midwives in our survey were satisfied with their work (n = 508). However, significant differences emerged between hospital and primary-care midwives in terms of what was most important to them in relation to their job satisfaction. For hospital midwives, the most significant domains were: working hours per week, workplace agreements, and total years of experience. For primary-care midwives, social support at work, work demands, job autonomy, and the influence of work on their private life were most significant. Conclusion Although midwives were generally satisfied, differences emerged in the key predictors of job satisfaction between hospital and primary-care midwives. These differences could be of importance when planning workforce needs and should be taken into consideration by policymakers in the Netherlands and elsewhere when planning new models of care.


2020 ◽  
Vol 30 (Supplement_5) ◽  
Author(s):  
B Meza-Torres ◽  
C Heiss ◽  
S Cunningham ◽  
F Carinci ◽  
S de Lusignan

Abstract Background Different patterns of co-morbidities observed among people with type 2 diabetes (T2D) and lower extremity amputations (LEA) compared with those without may provide insights into the quality of care provided by general practitioners in England. We analysed routinely recorded clinical data to build predictive models for benchmarking and continuous improvement. Methods A cross-sectional computerized data extraction of clinical records from the Royal College of General Practitioners (RCGP) Research and Surveillance Centre (RSC) database of people with T2D in England. Key target cases were defined as adults with T2D and a record of major/minor LEA between 2008-2019 vs all subjects with T2D without amputation. Quality of care was assessed in terms of percentage of patients treated with optimal medical therapy and diagnostic procedures and referred to specialized care according to their clinical profile. The association between quality of care and outcomes was explored using a logistic regression model, adjusting for case-mix. Results During the last decade, in a sample covering approximately 7.4% of all general practitioners in England, a total of 1,052 subjects out of 127,100 adults with T2D had a LEA (832 per 100,000). The median time since amputation was 3.4 years. Only 410 (38%) patients had a recorded DFU diagnosis prior to the amputation, with a median of 2 years from diagnosis to amputation. Major LEA was recorded in 280 (27%) cases. People with a record of retinopathy, peripheral arterial disease, renal disease, neuropathy and DFU had a higher risk of amputations. Quality of care was heterogeneous between patients with and without LEA. Conclusions People with T2D and LEA have a distinct pattern of co-morbidities some of which may be sensitive to improved primary care management, and differential quality of care. Models built using this national database can routinely monitor amputations in England. Variation in treatment should be properly investigated. Key messages The automated extraction of clinical cases from a national database may help shed light on clinical patterns among people with diabetes at high risk of amputations, based on evidence-based criteria. Variation in treatment and quality of care among amputated vs non-amputated subjects can be rapidly explored using a cross-sectional analysis of current records.


BJGP Open ◽  
2021 ◽  
pp. BJGPO.2021.0052
Author(s):  
Yemi Oluboyede ◽  
Sarah Hill ◽  
Suzanne McDonald ◽  
Emily Henderson

BackgroundObesity is thought to be one of the most serious global public health challenges of the 21st century. The primary care setting is important in terms of the diagnosis, education and management of obesity in children and young people. This study explored the views of primary care clinicians on the implementation of a quality of life (QoL) tool to help young people and their families identify the impact of weight on QoL.AimTo assess the acceptability and feasibility of implementing the Weight-specific Adolescent Instrument for Economic-evaluation (WAItE) QoL tool for young people aged 11–18 years in primary care.MethodOne-to-one, semi-structured interviews were conducted with a purposive sample of primary healthcare clinicians working in practices located in areas of varying deprivation in Northern England, UK. Interview transcripts were coded and analysed using Framework Analysis in NVivo 10.ResultsParticipants (n=16 General Practitioners; n=4 practice nurses) found the WAItE tool acceptable for them and their patients and believed it was feasible for use in routine clinical practice. It was important to primary care clinicians that the tool would provide an overall QoL score that would be easy for General Practitioners and nurses to interpret, to help them identify patients most in need of specialist help.ConclusionsThis study has developed a platform for further research around QoL in overweight and obese young people. A future feasibility study will focus on implementing the tool in a small number of primary healthcare practices.


2013 ◽  
Vol 127 (4) ◽  
pp. 364-367 ◽  
Author(s):  
N Su ◽  
P P Cheang ◽  
H Khalil

AbstractBackground:Chronic sinusitis is the most common routine presentation for a general ENT surgeon. The 2007 ‘Primary Care Guidelines: European Position Paper on the Primary Care Diagnosis and Management of Rhinosinusitis and Nasal Polyps’ aimed to deliver evidence-based guidelines for the diagnosis and management of rhinosinusitis in specialist and primary care.Objective:The aim of this audit was to assess the information provided in the referral letters to the ENT department regarding patients with potential rhinosinusitis, and compare this to the information required for the rhinology care pathways.Method:We evaluated one month of referrals to the ENT department.Results:The quality of information in the referral letters was poor. Only 22 per cent of patient referrals included basic information about symptoms, duration and treatment.Conclusion:We plan to investigate why general practitioners are not complying with the pathway. In addition, the pathways will be more widely disseminated via the ‘Map of Medicine’ (an online resource for general practitioners). This should facilitate the receipt of the best evidence-based treatment for patients prior to referral to secondary care.


Author(s):  
Julian Wangler ◽  
Michael Jansky

SummaryMedical guidelines aim to ensure that care processes take place in an evidence-based and structured manner. They are especially relevant in outpatient primary care due to the wide range of symptoms and clinical pictures. In German-speaking countries, there is a lack of current findings documenting general practitioners’ opinions and experiences regarding guidelines, their expectations and their views on what improvements could be made to increase the use of this type of evidence-based instrument in the primary care setting. Between April and August 2020, a total of 3098 general practitioners were surveyed in the states of Baden–Württemberg, Hesse and Rhineland–Palatinate via an online questionnaire. Alongside the descriptive evaluation, t‑testing was used to determine significant differences between two independent sampling groups. A factor analysis was also used to cluster the expectations of those surveyed regarding the fulfilment of requirements relating to guidelines. A total of 52% of those surveyed have a positive view of guidelines. Overall, guidelines are associated with an increased evidence-based approach (69%), standardisation of diagnosis and treatment (62%) and a reduction in overprovision or underprovision of care (57%). In all, 62% of the physicians who implemented guidelines observed positive effects on the quality of care provided, and 67% reported that the implementation of guidelines improved the quality of their diagnostic or therapeutic skills. However, implementation is often seen as being complicated (43%) and restricting the physician’s ability to act independently (63%). Survey participants suggested that guidelines could be optimised by giving greater consideration to nondrug alternatives (46%), focusing on issues related to quality of life (42%) and offering a comparative assessment of various treatment options (39%). In order to further promote the attractiveness of guidelines for primary care the design of guidelines should be oriented more towards their application; they should be well-presented to make them easier to implement. The scope of action available to the physician should be stressed. The guidelines should provide recommendations on opportunities for the delegation of tasks within practice teams.


Sign in / Sign up

Export Citation Format

Share Document