Scandinavian journal of primary health care
-
Scand J Prim Health Care · Dec 2021
Artificial intelligence in the GPs office: a retrospective study on diagnostic accuracy.
Machine learning (ML) is expected to play an increasing role within primary health care (PHC) in coming years. No peer-reviewed studies exist that evaluate the diagnostic accuracy of ML models compared to general practitioners (GPs). The aim of this study was to evaluate the diagnostic accuracy of an ML classifier on primary headache diagnoses in PHC, compare its performance to GPs, and examine the most impactful signs and symptoms when making a prediction. ⋯ In a retrospective comparison, the diagnostic accuracy of the ML classifier for primary headache diagnoses is superior to GPs. According to SHAP values, the ML classifier relies on the same signs and symptoms as a physician when making a diagnostic prediction.KeypointsLittle is known about the diagnostic accuracy of machine learning (ML) in the context of primary health care, despite its considerable potential to aid in clinical work. This novel research sheds light on the diagnostic accuracy of ML in a clinical context, as well as the interpretation of its predictions. If the vast potential of ML is to be utilized in primary health care, its performance, safety, and inner workings need to be understood by clinicians.
-
Scand J Prim Health Care · Dec 2021
Men's perception of information and descriptions of emotional strain in the diagnostic phase of prostate cancer-a qualitative individual interview study.
To explore men`s perception of information and their possible emotional strain in the diagnostic phase of prostate cancer. ⋯ The findings indicate that men in the diagnostic phase of prostate cancer are not a homogeneous group, but need personalized information. Some men may benefit from other men's experiences and support. Men's emotional strain can affect their communication about prostate cancer, which should be acknowledged. Procedures that identify patients' information needs early on should be an integrated part of the diagnostic phase of prostate cancer.KEY POINTSKnowledge about men's information needs and possible emotional strain in the diagnostic phase of prostate cancer are limited.Men with suspected prostate cancer have different preferences and information needs; however, insufficient information prevents men from participating in decisions.Men experience a sense of affinity with other men affected by prostate cancer, and some men benefit from exchanging experiences.Men consider prostate cancer as a less aggressive type of cancer but may experience emotional strain.
-
Scand J Prim Health Care · Dec 2021
'Never change a winning team': GPs' perspectives on discontinuation of long-term antidepressants.
Long-term antidepressant use, much longer than recommended by guidelines, can harm patients and generate unnecessary costs. Most antidepressants are prescribed by general practitioners (GPs) but it remains unclear why they do not discontinue long-term use. ⋯ Discontinuation of long-term antidepressants is a difficult and uncertain process for GPs, especially in the absence of a facilitating life-event or patient demand. The absence of a compelling need for discontinuation and fear of relapse of symptoms in a stable patient are important barriers for GPs when considering discontinuation. In order to increase GPs' motivation to discontinue long-term antidepressants, more emphasis on the futility of the actual effect and on potential harms related to long-term use is needed.KEY POINTSCurrent awareness:Long-term antidepressant use, much longer than recommended by guidelines, can harm patients and generate unnecessary costs.Main statements: • Discontinuation of long-term antidepressants is a difficult and uncertain process for GPs. • More emphasis on the futility of the actual effect of antidepressants and on potential harms related to long-term use is needed.
-
Scand J Prim Health Care · Dec 2021
General practice - a fertile lagoon in the ocean of medical knowledge.
General practitioners (GPs) often find that linear, deductive knowledge does not provide a sufficient map for clinical management. But experience, accompanied by enduring familiarity with individual patients, may offer unique complementary skills to interpret a patient's symptoms and navigate skilfully through diagnosis, treatment, follow-up and prevention. In this article, we draw attention to the nature of this tacit knowing that is executed by many GPs every day. ⋯ The VUCA model (volatility, uncertainty, complexity, ambiguity) embraces dynamic and confusing situations in which agile work (adaptive, flexible and responsive behaviour and cognitive creativity) is assumed to be an appropriate response. Using such perspectives, we may sharpen our gaze and apply reflexivity and analytic elaboration to interpret unique incidents and experiences and appreciate the complexity of general practice. In this way, exploratory research can fertilize general practice and offer innovation to the entire domain of clinical knowledge.