Diagnostic Errors Research Articles

Feedback Loop Failure Modes in Medical Diagnosis: How Biases Can Emerge and Be Reinforced.

Medical diagnosis in practice connects to research through continuous feedback loops: Studies of diagnosed cases shape our understanding of disease, which shapes future diagnostic practice. Without accounting for an imperfect and complex diagnostic process in which some cases are more likely to be diagnosed correctly (or diagnosed at all), the feedback loop can inadvertently exacerbate future diagnostic errors and biases. A feedback loop failure occurs if misleading evidence about disease etiology encourages systematic errors that self-perpetuate, compromising future diagnoses and patient care. This article defines scenarios for feedback loop failure in medical diagnosis. Through simulated cases, we characterize how disease incidence, presentation, and risk factors can be misunderstood when observational data are summarized naive to biases arising from diagnostic error. A fourth simulation extends to a progressive disease. When severe cases of a disease are diagnosed more readily, less severe cases go undiagnosed, increasingly leading to underestimation of the prevalence and heterogeneity of the disease presentation. Observed differences in incidence and symptoms between demographic groups may be driven by differences in risk, presentation, the diagnostic process itself, or a combination of these. We suggested how perceptions about risk factors and representativeness may drive the likelihood of diagnosis. Differing diagnosis rates between patient groups can feed back to increasingly greater diagnostic errors and disparities in the timing of diagnosis and treatment. A feedback loop between past data and future medical practice may seem obviously beneficial. However, under plausible scenarios, poorly implemented feedback loops can degrade care. Direct summaries from observational data based on diagnosed individuals may be misleading, especially concerning those symptoms and risk factors that influence the diagnostic process itself. Current evidence about a disease can (and should) influence the diagnostic process. A feedback loop failure may occur if biased "evidence" encourages diagnostic errors, leading to future errors in the evidence base.When diagnostic accuracy varies for mild versus severe cases or between demographic groups, incorrect conclusions about disease prevalence and presentation will result without specifically accounting for such variability.Use of demographic characteristics in the diagnostic process should be done with careful justification, in particular avoiding potential cognitive biases and overcorrection.

The Progress and Future of Artificial Intelligence in Nursing Care: A Review

Introduction The utilization of novel technologies in contemporary times not only reduces the cost associated with healthcare but also improves the efficiency of hospital resources and elevates the standard of medical assistance. One of the new technologies used in the field of health is Artificial Intelligence (AI). The purpose of this study is to investigate the application of AI in the field of nursing. Materials and Methods The present investigation was conducted in the year 2023 utilizing a review methodology and an innovative scientific inquiry. Comprehensive research was performed in reliable databases such as PubMed, Scopus, Google Scholar, Science Direct, and Springer, using the keywords AI, smart hospital, nursing, and health care to accomplish the intended objectives. From 2016 to 2023,120 articles were chosen as the initial selection. Studies that were not related to the subject matter were excluded from the analysis afterward. Results After searching and eliminating duplicate articles through objective screening, a total of 98 articles were reviewed, with 63 ultimately selected for the study. Within the realm of nursing care, research has been conducted in various areas, such as electronic health records (13 studies), health information collection and analysis (27 studies), healthcare cost analysis (16 studies), and the implementation of smart technology and hospitals (7 studies). The integration of AI technology has shown promise in enhancing nursing care by reducing diagnostic errors, improving emergency response times, improving patient care quality and psychological support, and enabling remote care for elderly patients through the use of smart technology. Conclusion AI is a significant technological advancement that can directly impact the operational effectiveness of healthcare organizations. This is achieved through the optimization of healthcare business processes and the enhancement of patient safety. However, limited research has been conducted regarding the affordability and economic aspects of AI implementation. Therefore, it is advisable for healthcare policymakers to establish the necessary infrastructure to leverage this technology, which will facilitate a more effective therapeutic and economic approach.

Use of neurological criteria to declare death in children.

Accurate determination of death is a necessary responsibility of the medical profession. Brain death, or death by neurological criteria (DNC), can be legally declared after the determination of permanent loss of clinical brain function, including the capacity for consciousness, brainstem reflexes, and the ability to breathe spontaneously. Despite longstanding debates over the exact definition of brain death or DNC and how it is determined, most middle- and high-income countries have compatible medical protocols and legal policies for brain death or DNC. This review summarizes the 2023 updated guidelines for brain death or DNC determination, which integrate adult and pediatric diagnostic criteria. We discuss the clinical challenges related to brain death or DNC determination in infants and young children. We emphasize that physicians must follow the standardized and meticulous evaluation processes outlined in these guidelines to reduce diagnostic error and ensure no false positive determinations. An essential component of the brain death or DNC evaluation is appropriate and transparent communication with families. Ongoing efforts to promote consistency and legal uniformity in the declaration of death are needed.

Digital Pathology is a Fast and Effective Platform for Providing Head and Neck Pathology Consultations.

Surgical pathology of the head and neck is one of the more challenging areas in all of diagnostic pathology. Its unparalleled diversity and complexity renders it highly vulnerable to diagnostic error compelling unconstrained access to specialized diagnostic expertise. Digital pathology (DP) is a state-of-the-art tool that could facilitate access to specialized expertise, but it is relatively untested in the context of pathology consultations. In a collaboration between Labcorp Dianon and a large academic hospital with subspecialized surgical pathology, DP was implemented to provide the pathology community access to head and neck pathology expertise. From this collaborative experience, glass slides from consecutive consult cases that had been previously diagnosed using DP were reviewed by an expert consultant in a blinded manner following an extended wash-out period. The intraobserver discrepancy rate was recorded. Major discrepancies were defined as those resulting in significant impact on clinical management and/or prognosis, whereas minor discrepancies were those with no impact on care or prognosis. Slides from 57 cases were available for review. The average wash-out period was 19 months. Five discrepancies were recorded (intraobserver concordance rate of 91%). All discrepancies were minor (major discrepancy rate, 0%; minor discrepancy rate, 9%). On appraisal of the discrepant cases, discordant diagnoses were attributed to subjective differences in interpretation rather than objective differences related to the inferiority of DP. DP decreased the median turnaround time by 97% (from 70h 26min to 2h 25min). DP provides efficient and fast access to expert consultants. The speed of case delivery does not compromise diagnostic precision. Discrepancies are uncommon, minor, and reflect subjective interpretative differences inherent to difficult and ambiguous head and neck cases, and not the inferiority of DP as a diagnostic platform. High concordance can be achieved even for those difficult and complex cases that are concentrated in the consultation practice. This observation carries profound implications regarding universal health care access to specialized diagnostic expertise.

Computable phenotype for diagnostic error: developing the data schema for application of symptom-disease pair analysis of diagnostic error (SPADE).

Diagnostic errors are the leading cause of preventable harm in clinical practice. Implementable tools to quantify and target this problem are needed. To address this gap, we aimed to generalize the Symptom-Disease Pair Analysis of Diagnostic Error (SPADE) framework by developing its computable phenotype and then demonstrated how that schema could be applied in multiple clinical contexts. We created an information model for the SPADE processes, then mapped data fields from electronic health records (EHR) and claims data in use to that model to create the SPADE information model (intention) and the SPADE computable phenotype (extension). Later we validated the computable phenotype and tested it in four case studies in three different health systems to demonstrate its utility. We mapped and tested the SPADE computable phenotype in three different sites using four different case studies. We showed that data fields to compute an SPADE base measure are fully available in the EHR Data Warehouse for extraction and can operationalize the SPADE framework from provider and/or insurer perspective, and they could be implemented on numerous health systems for future work in monitor misdiagnosis-related harms. Data for the SPADE base measure is readily available in EHR and administrative claims. The method of data extraction is potentially universally applicable, and the data extracted is conveniently available within a network system. Further study is needed to validate the computable phenotype across different settings with different data infrastructures.

The venereal morbidity in Russia in 1914-1924

It is accepted to explain increasing of venereal diseases during years of the Revolution by degradation of morality and general disorder of system of state administration and sanitary services in Russia. The cross-verification of information presented in scientific publications and primary information sources makes it possible to look into following issues: degree of venereal (syphilitic) contamination of population of pre-revolutionary Russia; influence on sanitary statistics by erroneous diagnostics and convictions of Zemstvo medicine about predominantly non-sexual path of transmission of syphilis pathogen in Russian countryside; dynamics and sources of venereal morbidity in wartime. The high indicators of pre-revolutionary statistics of venereal infections could be affected by diagnostic errors. The "village syphilis" encountered in public milieu could be completely different disease not sexually transmitted and not chronic form of disease. The primary documents allow to discuss increasing of the number of venereal patients during war years, that however, does not reach catastrophic numbers that can be found even in scientific publications. This is also confirmed by data of Chief Military Sanitary Board of the Red Army for 1920s and statistical materials of People's Commissariat of Health Care of the RSFSR. The high morbidity was demonstrated by same Gubernias that were problematic before the Revolution and only later by those ones through which during the war years passed army masses. In Russia, total level of syphilis morbidity after the end of Civil War occurred to be more than twice lower than in pre-war 1913 and continued to decrease under impact of sanitary measures of Soviet public health.

Artificial intelligence-based classification of breast nodules: a quantitative morphological analysis of ultrasound images.

Accurate classification of breast nodules into benign and malignant types is critical for the successful treatment of breast cancer. Traditional methods rely on subjective interpretation, which can potentially lead to diagnostic errors. Artificial intelligence (AI)-based methods using the quantitative morphological analysis of ultrasound images have been explored for the automated and reliable classification of breast cancer. This study aimed to investigate the effectiveness of AI-based approaches for improving diagnostic accuracy and patient outcomes. In this study, a quantitative analysis approach was adopted, with a focus on five critical features for evaluation: degree of boundary regularity, clarity of boundaries, echo intensity, and uniformity of echoes. Furthermore, the classification results were assessed using five machine learning methods: logistic regression (LR), support vector machine (SVM), decision tree (DT), naive Bayes, and K-nearest neighbor (KNN). Based on these assessments, a multifeature combined prediction model was established. We evaluated the performance of our classification model by quantifying various features of the ultrasound images and using the area under the receiver operating characteristic (ROC) curve (AUC). The moment of inertia achieved an AUC value of 0.793, while the variance and mean of breast nodule areas achieved AUC values of 0.725 and 0.772, respectively. The convexity and concavity achieved AUC values of 0.988 and 0.987, respectively. Additionally, we conducted a joint analysis of multiple features after normalization, achieving a recall value of 0.98, which surpasses most medical evaluation indexes on the market. To ensure experimental rigor, we conducted cross-validation experiments, which yielded no significant differences among the classifiers under 5-, 8-, and 10-fold cross-validation (P>0.05). The quantitative analysis can accurately differentiate between benign and malignant breast nodules.

Outcomes of a Novel Spine Virtual Fracture Clinic in an Australian Tertiary Hospital.

This was a retrospective cohort study. To determine the proportion of referrals diverted by the spine virtual fracture clinic (SVFC) from traditional outpatient clinic management. The consistent rise in demand for orthopedic outpatient clinic services is creating marked challenges to the provision of quality care. Virtual fracture clinics for upper and lower limb fractures have reduced the burden on outpatient clinics by providing an alternative telehealth management pathway. To date, no study describes the expansion of virtual care to the spine trauma population. A study of spine fractures referred to the RMH Department of Orthopaedic Surgery was conducted comparing outcomes before (January to December 2021) and following (July 2022 to November 2023) implementation of an SVFC. The primary aim of this study was to investigate the effect of a telephone-based SVFC on outpatient clinic activity, represented by the proportion of referrals discharged without requiring an outpatient clinic appointment. Secondary aims included appointment utilization, lost to follow-up rates, duration of care, missed or misdiagnoses, unplanned operations, and complications. Of the 731 referrals managed by the SVFC, 91.1% were discharged without requiring in-person outpatient clinic attendance. Compared with the outpatient clinic historical cohort (150 referrals), SVFC management was associated with reductions in the average number of consultations per referral (1.8 vs . 2.4, P <0.001), appointments not attended (5% vs . 13%, P <0.001), referrals lost to follow-up (0% vs . 10.7%, P <0.001), and a shorter duration of care (median 48 vs . 58d, P <0.001). A total of 65 patients (8.1%) were redirected to the outpatient clinic, of which three underwent surgical intervention. No diagnostic errors, complications or adverse events were identified. This study demonstrates that an SVFC is an effective and safe alternative pathway to traditional hospital-based outpatient clinics, ith low-risk for any adverse outcomes.

CRIM-negative infantile Pompe disease, long-term observation of the effect of enzyme replacement therapy: a clinical case

Background. Infantile-onset form of Pompe disease (IOPD) comprises a progressive and fatal disease in the absence of pathogenetic treatment. Enzyme replacement therapy using biologically active recombinant human alglucosidase alfa is considered as a treatment option to increase the life expectancy of patients with early diagnosis and timely initiation of therapy.Case description. A child aged 5 months was delivered to the Cardiology Department of Children’s Republican Clinical Hospital (Tatarstan, Russia) for examination and clarification of the diagnosis. The patient’s parents complained of his shortness of breath, unproductive cough, cyanosis of the nasolabial triangle when restless, weakness, lethargy during breastfeeding session, as well as decreased appetite up to refusal to eat, constantly enlarged tongue. The examination revealed macroglossia and hypersalivation, pseudohypertrophy of calf muscles, dyspnea involving the accessory muscles, hepatomegaly, diffuse muscular hypotonia. Laboratory tests revealed an increase in alanine aminotransferase level greater than four times the normal values, aspartate aminotransferase level — more than nine times, a significant rise of creatine phosphokinase and lactate dehydrogenase, as well as natriuretic peptide. Echocardiography revealed significant myocardial hypertrophy of both the left and right ventricles. Complaints, medical history, clinical examination, and all of the above changes in laboratory and instrumental examinations suggested a group of hereditary metabolic diseases (Pompe disease), confirmed by a pronounced decrease in the activity of the alpha-glucosidase enzyme to 0.12 μmol/l/h in dry blood spots with subsequent molecular genetic study and detection of compound-heterozygous mutations in the GAA gene. It was decided to initiate specific enzyme replacement therapy by intravenous administration of a recombinant form of human acidic alpha-glucosidase (alglucosidase alfa) at a dose of 20 mg/kg/injection in a frequency of once every 2 weeks. In addition, CRIM (cross-reactive immunological material)-negative status determined immune tolerance therapy, including the most studied combination of three drugs: rituximab, methotrexate, and intravenous immunoglobulin, as a response to enzyme replacement therapy. Long-term observation of the effect of enzyme replacement therapy brought positive results in the form of new motor skills, decreased content of intracellular enzymes and natriuretic peptide, reduction of myocardial hypertrophy of the left and right ventricles. In the future, the child needs lifelong treatment.Conclusion. Awareness of physicians about Pompe disease will prevent the growth in diagnostic errors and neglected cases. In case of early confirmation, the effectiveness of currently available ERT increases: the possibility to stop the disease progression, to reverse its individual clinical manifestations, and to improve the patient’s quality of life.

Reducing the Risk of Delayed Colorectal Cancer Diagnoses Through an Ambulatory Safety Net Collaborative

An estimated 12 million adults in the United States experience delayed diagnoses and other diagnostic errors annually. Ambulatory safety nets (ASNs) are an intervention to reduce delayed diagnoses by identifying patients with abnormal results overdue for follow-up using registries, workflow redesign, and patient navigation. The authors sought to co-design a collaborative and implement colorectal cancer (CRC) ASNs across various health care settings. A working group was convened to co-design implementation guidance, measures, and the collaborative model. Collaborative sites were recruited through a medical professional liability insurance program and chose to begin with developing an ASN for positive at-home CRC screening or overdue surveillance colonoscopy. The 18-month Breakthrough Series Collaborative ran from January 2022 to July 2023, with sites continuing to collect data while sustaining their ASNs. Data were collected from sites monthly on patients in the ASN, including the proportion that was successfully contacted, scheduled, and completed a follow-up colonoscopy. Six sites participated; four had an operational ASN at the end of the Breakthrough Series, with the remaining sites launching three months later. From October 2022 through February 2024, the Collaborative ASNs collectively identified 5,165 patients from the registry as needing outreach. Among patients needing outreach, 3,555 (68.8%) were successfully contacted, 2,060 (39.9%) were scheduled for a colonoscopy, and 1,504 (29.1%) completed their colonoscopy. The Collaborative successfully identified patients with previously abnormal CRC screening and facilitated completion of follow-up testing. The CRC ASN Implementation Guide offers a comprehensive road map for health care leaders interested in implementing CRC ASNs.

Prevalence of cranial autonomic symptoms in frequent episodic tension-type headache: A post hoc analysis of the cross-sectional Migraine in Poland study.

Cranial autonomic symptoms (CASs) include lacrimation, conjunctival injection, rhinorrhea, nasal congestion, facial flushing or sweating, ptosis, and myosis. These symptoms may be associated with trigeminal autonomic cephalalgias (TACs) and migraine. The aim of the study was to assess whether CASs are also reported by patients with frequent episodic tension-type headache (eTTH). A cross-sectional online survey of a large Polish population was conducted between August 2021 and June 2022. The analysis assessed diagnostic criteria for migraine and eTTH, as well as the presence of allodynia, headache-related disability and symptoms of depression. The survey involved 3,225 respondents (age: 13-80 years, mean (M) = 38.9 years; 87.1% female). A total of 166 individuals met the diagnostic criteria for isolated frequent eTTH without migraine or probable migraine with or without aura. Allodynia was present during the majority of attacks in 40 (24.1%) eTTH subjects, while 86 (51.8%) eTTH respondents reported at least 1 CAS during their headache attacks. The presence of at least 1 CAS was more prevalent in migraine than in eTTH (p = 0.001). The respondents with at least 1 CAS during eTTH attacks reported a higher burden associated with pain (p = 0.024) and higher Patient Health Questionnaire-9 (PHQ-9) scores (p = 0.016). The prevalence of retrospectively reported CASs was high among individuals with eTTH, which may potentially contribute to diagnostic errors. Cranial autonomic symptoms in eTTH do not appear to be caused by severe pain or central sensitization.

A qualitative examination of factors influencing pregnancy-related anxiety in Northern Ghana

IntroductionDespite high prevalence of anxiety among pregnant women in low- and -middle-income countries, research on context-specific conceptualisation, measurement, and predictors of pregnancy-related anxiety (PrA) is limited in these contexts. We explored local conceptualisations of factors influencing PrA in the Northern Region of Ghana. MethodsWe conducted 15 focus group discussions with antenatal care seekers in the Mion District, Savelugu Municipality, and Tamale Metropolis of the Northern Region, in July and August 2021. Multistage stratified purposive sampling was used to select respondents (n = 108). The data were audio-recorded and transcribed, and then we conducted a thematic analysis of the data. ResultsAt the individual level, fear of anaemia; pre-existing health conditions; challenges with daily activities; and physical, emotional, and sexual abuses from spouses contributed to PrA. Health system failures resulting in unexpected out-of-pocket payments, negative health worker attitudes, diagnostic errors, constraints on birth preparation and birth process, and potential adverse birth outcomes were understood as driving PrA. Socio-cultural factors influencing PrA comprised beliefs and practices around baby naming/outdooring ceremonies, fear of spiritual attacks, social construction of gender roles, and contextual factors such as transportation challenges. ConclusionPregnant women in the region understood, experienced, and could identify perceived predictors of PrA. To address PrA, we recommend that mental health services should be integrated into the basic package of antenatal care and rural health services should be improved. Perceived predictors of PrA identified here could be included in the design of a context-specific PrA measure for use in the region.

Using ChatGPT-4 to Create Structured Medical Notes From Audio Recordings of Physician-Patient Encounters: Comparative Study.

Medical documentation plays a crucial role in clinical practice, facilitating accurate patient management and communication among health care professionals. However, inaccuracies in medical notes can lead to miscommunication and diagnostic errors. Additionally, the demands of documentation contribute to physician burnout. Although intermediaries like medical scribes and speech recognition software have been used to ease this burden, they have limitations in terms of accuracy and addressing provider-specific metrics. The integration of ambient artificial intelligence (AI)-powered solutions offers a promising way to improve documentation while fitting seamlessly into existing workflows. This study aims to assess the accuracy and quality of Subjective, Objective, Assessment, and Plan (SOAP) notes generated by ChatGPT-4, an AI model, using established transcripts of History and Physical Examination as the gold standard. We seek to identify potential errors and evaluate the model's performance across different categories. We conducted simulated patient-provider encounters representing various ambulatory specialties and transcribed the audio files. Key reportable elements were identified, and ChatGPT-4 was used to generate SOAP notes based on these transcripts. Three versions of each note were created and compared to the gold standard via chart review; errors generated from the comparison were categorized as omissions, incorrect information, or additions. We compared the accuracy of data elements across versions, transcript length, and data categories. Additionally, we assessed note quality using the Physician Documentation Quality Instrument (PDQI) scoring system. Although ChatGPT-4 consistently generated SOAP-style notes, there were, on average, 23.6 errors per clinical case, with errors of omission (86%) being the most common, followed by addition errors (10.5%) and inclusion of incorrect facts (3.2%). There was significant variance between replicates of the same case, with only 52.9% of data elements reported correctly across all 3 replicates. The accuracy of data elements varied across cases, with the highest accuracy observed in the "Objective" section. Consequently, the measure of note quality, assessed by PDQI, demonstrated intra- and intercase variance. Finally, the accuracy of ChatGPT-4 was inversely correlated to both the transcript length (P=.05) and the number of scorable data elements (P=.05). Our study reveals substantial variability in errors, accuracy, and note quality generated by ChatGPT-4. Errors were not limited to specific sections, and the inconsistency in error types across replicates complicated predictability. Transcript length and data complexity were inversely correlated with note accuracy, raising concerns about the model's effectiveness in handling complex medical cases. The quality and reliability of clinical notes produced by ChatGPT-4 do not meet the standards required for clinical use. Although AI holds promise in health care, caution should be exercised before widespread adoption. Further research is needed to address accuracy, variability, and potential errors. ChatGPT-4, while valuable in various applications, should not be considered a safe alternative to human-generated clinical documentation at this time.

CONVOLUTIONAL NEURAL NETWORK (CNN) BASED ON ARTIFICIAL INTELLIGENCE IN PERIODONTAL DISEASES DIAGNOSIS

Introduction: The main problem by many clinicians is the correct diagnosis of periodontal disease. Usually, conventional clinical measurements such as measuring probing depth, attachment loss, presence of plaque and calculus are the way to diagnose and classify periodontal disease. However, clinical examination has limited reliability for periodontitis screening. Likewise, the ability of dentists to read radiographs using conventional methods increases the risk of misdiagnosis. Due to the diversity of existing clinical criteria and the increase in knowledge about human health, changes in the diagnostic criteria for periodontal disease that have occurred in recent decades have led to several updates. Recent research has focused on developing artificial intelligence tools to assist in diagnostic and therapeutic roles. This literature review aims to determine the use of artificial intelligence-based convolutional neural network (CNN) in diagnosing periodontal disease. Review: Artificial intelligence (AI) can make more accurate and efficient diagnoses, thereby reducing the workload of dentists. The use of the convolutional neural network (CNN) system in diagnosis and treatment planning allows dentists to reduce diagnostic errors that arise. Several studies have found that the CNN algorithm can assist in detecting alveolar bone loss, gingival abnormalities, and assisting early intervention in implantology. The CNN system can also capture details that dentists miss in diagnosis, especially radiographic diagnosis. Conclusion: Implementing an AI system is effective in helping to analyze periodontal disease. The CNN algorithm outperforms other AI techniques that can be used to facilitate diagnosis and treatment planning by dentists in the future.

Secondary recurrent syphilis in a patient with HIV infection. Clinical case

Relevance. HIV infection is a chronic sexually transmitted infectious disease. Given the single route of transmission, quite often HIV-infected patients develop a syphilitic infection. At the same time, syphilis against the background of HIV infection has its own clinical characteristics. It is important for doctors of various specialties to know these features.Description of the case. A clinical case of secondary syphilis and early neurosyphilis in a 52-year-old patient with HIV infection is presented.Discussion. Patients with HIV infection are characterized by unusual clinical manifestations of syphilis in the form of its malignity, atypical, severe course with the development of various complications. In the article, the authors describe atypical manifestations of papular syphilide of the palms and soles. The effectiveness of specific treatment has been shown.Conclusions. Doctors’ knowledge of the clinical features of syphilis against the background of HIV infection will allow them to avoid diagnostic errors leading to late treatment and the development of complications.

Reflecting on diagnosis: The Metacognitive Diagnostic Reasoning Model©.

Diagnostic reasoning is a complex cognitive process that requires intuitive, heuristic processing from knowledge and experience, as well as deliberate and reflective thinking. Evidence on interventions to improve diagnostic reasoning is inconsistent, in part because different terms and models are used to guide research. To present a model of the factors of diagnostic reasoning in Advanced Practice Registered Nurses (APRNs), based on a review of the literature supporting the Metacognitive Diagnostic Reasoning (MDR) Model©. A review of the literature through systematic database search, historical articles, texts, and documents was conducted from inception through August 2023 (N = 41). The MDR model depicts the following concepts: (1) metacognition is viewed as the driving force of diagnostic reasoning; (2) dual cognitive processing and knowledge representations are used; (3) once a diagnosis, treatment plan, and evaluation are complete, APRNs use metacognition for the next patient encounter, using repetition for improvement of the process. The model combines key concepts of diagnostic reasoning, providing a framework for researchers to develop and test, and faculty to teach and evaluate this complex process in learners. The MDR model provides research opportunities to validate its usefulness and effectiveness and a framework to guide educational research, contributing to the body of evidence-based practice in nursing. In addition, it may foster ongoing education and training that could lead to more accurate diagnoses and treatment plans, ultimately improving patient care by reducing diagnostic errors.

The influence of viewing time on visual diagnostic accuracy: Less is more.

Understanding the factors that contribute to diagnostic errors is critical if we are to correct or prevent them. Some scholars influenced by the default interventionist dual-process theory of cognition (dual-process theory) emphasise a narrow focus on individual clinician's faulty reasoning as a significant contributor. In this paper, we examine the validity of claims that dual process theory is a key to error reduction. We examined the relationship between a clinical experience (staff and resident physicians) and viewing time on accuracy for categorising chest X-rays (CXRs) and electrocardiograms (ECGs). In two studies, participants categorised images as normal or abnormal, presented at viewing times of 175, 250, 500 and 1000 ms, to encourage System 1 processing. Study 2 extended viewing times to 1, 5, 10 and 20 s to allow time for System 2 processing and a diagnosis. Descriptives and repeated measures analysis of variance were used to analyse the proportion of true and false positive rates (TP and FP) as well as correct diagnoses. In Study 1, physicians were able to detect abnormal CXRs (0.78) and ECGs (0.67) with relatively high accuracy. The effect of experience was found for ECGs only, as staff physicians (0.71, 95% CI =0.66-0.75) had higher ECG TP than resident physicians (0.63, 95% CI =0.58-0.68) in Study 1, and staff had lower ECG FP (0.10, 95% CI =0.03-0.18) than resident physicians (0.27, 95% CI =0.20-0.33) in Study 2. In other comparisons, experience was equivocal for ECG FPs and CXR TPs and FPs. In Study 2, overall diagnostic accuracy was similar for both ECGs and CXRs, (0.74). There were small interactions between experience and time for TP in ECGs and FP in CXRs, which are discussed further in the discussion and offer insights into the relationship between processing and experience. Overall, our findings raise concerns about the practical application of models that link processing type to diagnostic error, or to specific diagnostic error reduction strategies.

Diagnostic error during antenatal care visit in selected health facilities of Ethiopia: a survey

Diagnostic error in antenatal care is a critical concern within the broader challenge of diagnostic errors in healthcare. Antenatal care plays a crucial role in ensuring the well-being of both the mother and the developing fetus during pregnancy. As a result, missed or delayed antenatal care visits or diagnosis errors of maternity complications affect both the mother and the baby. Diagnostic errors in this context refer to mistakes or inaccuracies in identifying and interpreting medical conditions, risks, or abnormalities related to the pregnancy. Several factors contribute to diagnostic errors in antenatal care, and understanding these challenges is essential for improving the overall quality of maternal and fetal healthcare. Delivering an improved approach to underrating diagnostic error requires the combined usage of non-technological and technological solutions. Identifying the factors contributing to diagnostic errors among healthcare professionals can lead to targeted interventions, training programs, and system level changes to prevent or minimize such errors. In this study, the prevalence of DE among health care professionals, pregnant women, and their relatives, and the frequency of occurrence of DE among health workers in selected health facilities in Ethiopia has been assessed. The data was collected using a questionnaire. The assessment results show that the major causes of diagnostic errors (mainly incorrect diagnosis) are identified as loss of patient records (36.4%), lack of proper laboratory (22.7%), and an insufficient number of health care professionals (13.6%). The leading effects of diagnostic error recognized are disease aggravation (58.3%) and permanent disability (25.0%). The research shows that providing an accurate diagnosis is crucial for avoiding risky obstetric outcomes and, as a result, reducing morbidity and mortality due to complications of pregnancy.

Impact of technology on orthodontic practice

This paper explores the pivotal role of Artificial Intelligence (AI) in transforming orthodontic practice, focusing on its profound impact on diagnosis, treatment planning, and patient care. AI-powered algorithms, coupled with machine learning techniques, have revolutionized orthodontic workflows, enhancing efficiency, precision, and patient outcomes. By analysing vast datasets, AI facilitates predictive modelling for treatment outcomes, aiding orthodontists in devising personalized treatment plans tailored to individual patient needs. Moreover, AI-driven image analysis techniques enable automated cephalometric analysis, intraoral scanning, and 3D imaging interpretation, significantly reducing diagnostic errors and streamlining treatment processes. Furthermore, AI-enabled virtual treatment simulations empower patients to visualize treatment outcomes and actively participate in decision-making processes. The integration of AI into orthodontic practice also extends to tele orthodontics, enabling remote monitoring and virtual consultations, thereby enhancing accessibility and convenience for patients. Despite the transformative potential of AI, challenges such as data privacy, algorithm bias, and the need for clinician training must be addressed to ensure its ethical and effective implementation. Nevertheless, the advent of AI heralds a new era in orthodontics, characterized by unprecedented levels of efficiency, accuracy, and patient satisfaction. This paper underscores the revolutionary impact of AI on orthodontic practice and highlights the opportunities and challenges associated with its integration into clinical workflows.

Collective Intelligence Increases Diagnostic Accuracy in a General Practice Setting.

General practitioners (GPs) work in an ill-defined environment where diagnostic errors are prevalent. Previous research indicates that aggregating independent diagnoses can improve diagnostic accuracy in a range of settings. We examined whether aggregating independent diagnoses can also improve diagnostic accuracy for GP decision making. In addition, we investigated the potential benefit of such an approach in combination with a decision support system (DSS). We simulated virtual groups using data sets from 2 previously published studies. In study 1, 260 GPs independently diagnosed 9 patient cases in a vignette-based study. In study 2, 30 GPs independently diagnosed 12 patient actors in a patient-facing study. In both data sets, GPs provided diagnoses in a control condition and/or DSS condition(s). Each GP's diagnosis, confidence rating, and years of experience were entered into a computer simulation. Virtual groups of varying sizes (range: 3-9) were created, and different collective intelligence rules (plurality, confidence, and seniority) were applied to determine each group's final diagnosis. Diagnostic accuracy was used as the performance measure. Aggregating independent diagnoses by weighing them equally (i.e., the plurality rule) substantially outperformed average individual accuracy, and this effect increased with increasing group size. Selecting diagnoses based on confidence only led to marginal improvements, while selecting based on seniority reduced accuracy. Combining the plurality rule with a DSS further boosted performance. Combining independent diagnoses may substantially improve a GP's diagnostic accuracy and subsequent patient outcomes. This approach did, however, not improve accuracy in all patient cases. Therefore, future work should focus on uncovering the conditions under which collective intelligence is most beneficial in general practice. We examined whether aggregating independent diagnoses of GPs can improve diagnostic accuracy.Using data sets of 2 previously published studies, we composed virtual groups of GPs and combined their independent diagnoses using 3 collective intelligence rules (plurality, confidence, and seniority).Aggregating independent diagnoses by weighing them equally substantially outperformed average individual GP accuracy, and this effect increased with increasing group size.Combining independent diagnoses may substantially improve GP's diagnostic accuracy and subsequent patient outcomes.