-
Journal of Cardiovascular... Jul 2023The advancement of artificial intelligence (AI) has aided clinicians in the interpretation of electrocardiograms (ECGs) serving as an essential tool to provide rapid...
INTRODUCTION
The advancement of artificial intelligence (AI) has aided clinicians in the interpretation of electrocardiograms (ECGs) serving as an essential tool to provide rapid triage and care. However, in some cases, AI can misinterpret an ECG and may mislead the interpreting physician. Therefore, we aimed to describe the rate of ECG misinterpretation and its potential clinical impact in patient's management.
METHODS
We performed a retrospective descriptive analysis of misinterpreted ECGs and its clinical impact from May 28, 2020 to May 9, 2021. An electrophysiologist screened ECGs with confirmed diagnosis of atrial fibrillation (AF), sinus tachycardia (ST), sinus bradycardia (SB), intraventricular conduction delay (IVCD), and premature atrial contraction (PAC) that were performed in the emergency department. We then classified the misinterpreted ECGs as wrongly diagnosed AF, ST, SB, IVCD, or PAC into the correct diagnosis and reviewed the misinterpreted ECGs and medical records to evaluate inappropriate use of antiarrhythmic drugs (AAD), beta-blockers (BB), calcium channel blockers (CCB), anticoagulation, or resource utilization of cardiology and/or electrophysiology (EP) consultation.
RESULTS
A total of 4969 ECGs were screened with diagnoses of AF (2282), IVCD (296), PAC (972), SB (895), and ST (638). Among these, 101 ECGs (2.0%) were misinterpreted. Wrongly diagnosed AF (58.4%) was the most common followed by wrongly diagnosed PAC (14.9%), wrongly diagnosed ST (12.9%), wrongly diagnosed IVCD (7.9%), and wrongly diagnosed SB (6.0%). Patients with misinterpreted ECGs were aged 76.6 ± 11.6 years with male (52.5%) predominance and hypertension being the most prevalent (83.2%) comorbid condition. The misinterpretation of ECGs led to the inappropriate use of BB (19.8%), CCB (5.0%), AAD therapy (7.9%), anticoagulation (6.9%) in patients with wrongly diagnosed AF, as well as inappropriate resource utilization including cardiology (41.6%) and EP (8.9%) consultations.
CONCLUSIONS
Misinterpretation of ECGs may lead to inappropriate medical therapies and increased resource utilization. Therefore, it is essential to encourage physicians to carefully examine AI interpreted ECG's, especially those interpreted as having AF.
Topics: Humans; Male; Retrospective Studies; Artificial Intelligence; Atrial Fibrillation; Anti-Arrhythmia Agents; Electrocardiography; Heart Block; Anticoagulants
PubMed: 37272686
DOI: 10.1111/jce.15943 -
Biochemia Medica Oct 2023Cardiorenal syndrome (CRS), first defined in 2004 as a consequence of the interactions between the kidneys and other circulatory departments leading to acute heart... (Review)
Review
Cardiorenal syndrome (CRS), first defined in 2004 as a consequence of the interactions between the kidneys and other circulatory departments leading to acute heart failure, has since been recognized as a complex clinical entity that is hard to define, diagnose and classify. The framework for the classification of CRS according to pathophysiologic background was laid out in 2008, dividing CRS into five distinct phenotypes. However, determining the timing of individual organ injuries and making a diagnosis of either renal or cardiac failure remains an elusive task. In clinical practice, the diagnosis and phenotyping of CRS is mostly based on using laboratory biomarkers in order to directly or indirectly estimate the degree of end-organ functional decline. Therefore, a well-educated clinician should be aware of the effects that the reduction of renal and cardiac function has on the diagnostic and predictive value and properties of the most commonly used biomarkers ( troponins, N-terminal pro-brain natriuretic peptide, serum creatinine ). They should also be acquainted, on a basic level, with emerging biomarkers that are specific to either the degree of glomerular integrity (cystatin C) or tubular injury (neutrophil gelatinase-associated lipocalin). This narrative review aims to provide a scoping overview of the different roles that biomarkers play in both the diagnosis of CRS and the prognosis of the disease in patients who have been diagnosed with it, along with highlighting the most important pitfalls in their interpretation in the context of impaired renal and/or cardiac function.
Topics: Humans; Cardio-Renal Syndrome; Biomarkers; Heart Failure; Kidney; Prognosis
PubMed: 37545695
DOI: 10.11613/BM.2023.030502 -
Canadian Journal of Ophthalmology.... Oct 2023To evaluate the accuracy of the initial diagnosis in the case of fungal infections of the orbit and identify factors that may influence patient outcomes.
OBJECTIVE
To evaluate the accuracy of the initial diagnosis in the case of fungal infections of the orbit and identify factors that may influence patient outcomes.
METHODS
An institutional review board-approved retrospective chart review was conducted across 2 large academic centres to identify cases of fungal infections involving the orbit from January 1, 1998, to November 15, 2019. Data collected included patient demographics, past medical history, examination findings, diagnosis, treatment, imaging, and outcomes.
RESULTS
Fifty cases of fungal infection involving the orbit were identified. Of these, 33 (66.0%) were initially misdiagnosed as nonfungal diagnoses. Sixteen patients (32.0%) received multiple initial diagnoses. The most common diagnoses on presentation were bacterial cellulitis (n = 12 of 50; 24.0%) and bacterial sinusitis (n = 12 of 50; 24.0%). These were followed by vascular and orbital inflammatory conditions (n = 9 of 50; 18.0%): 5 patients (10.0%) were clinically diagnosed with giant cell arteritis, 3 (6.0%) with nonspecific orbital inflammation, and 1 (2.0%) with optic neuritis. In this subset of patients, 77.8% (n = 7 of 9) were treated initially with systemic steroids. Additional initial diagnoses included neoplastic mass lesions, mucocele, dacryocystitis, cavernous sinus thrombosis, hemorrhage, tick-borne illness, allergic rhinitis, and allergic conjunctivitis. Misdiagnosis was significantly correlated with involvement of the masticator space on imaging (p = 0.04).
CONCLUSION
Fungal infections of the orbit are misdiagnosed in 2 of 3 cases. Nearly 15% of patients who are later diagnosed with fungal disease of the orbit were initially treated with systemic steroids. Misdiagnosis is more frequent when the masticator space is involved.
Topics: Humans; Orbit; Retrospective Studies; Mycoses; Orbital Diseases; Diagnostic Errors
PubMed: 35525264
DOI: 10.1016/j.jcjo.2022.04.007 -
Annals of Nuclear Medicine Mar 2024Rheumatoid Arthritis (RA) is a systemic inflammatory disorder that commonly presents with polyarthritis but can have multisystemic involvement and complications, leading... (Review)
Review
Rheumatoid Arthritis (RA) is a systemic inflammatory disorder that commonly presents with polyarthritis but can have multisystemic involvement and complications, leading to increased morbidity and mortality. The diagnosis of RA continues to be challenging due to its varied clinical presentations. In this review article, we aim to determine the potential of PET/CT to assist in the diagnosis of RA and its complications, evaluate the therapeutic response to treatment, and predict RA remission. PET/CT has increasingly been used in the last decade to diagnose, monitor treatment response, predict remissions, and diagnose subclinical complications in RA. PET imaging with [F]-fluorodeoxyglucose ([F]-FDG) is the most commonly applied radiotracer in RA, but other tracers are also being studied. PET/CT with [F]-FDG, [F]-NaF, and other tracers might lead to early identification of RA and timely evidence-based clinical management, decreasing morbidity and mortality. Although PET/CT has been evolving as a promising tool for evaluating and managing RA, more evidence is required before incorporating PET/CT in the standard clinical management of RA.
Topics: Humans; Positron Emission Tomography Computed Tomography; Fluorodeoxyglucose F18; Arthritis, Rheumatoid; Positron-Emission Tomography; Radiopharmaceuticals
PubMed: 38277115
DOI: 10.1007/s12149-023-01896-z -
European Radiology Dec 2023PSC strictures are routinely diagnosed on T2-MRCP as dominant- (DS) or high-grade stricture (HGS). However, high inter-observer variability limits their utility. We...
OBJECTIVES
PSC strictures are routinely diagnosed on T2-MRCP as dominant- (DS) or high-grade stricture (HGS). However, high inter-observer variability limits their utility. We introduce the "potential functional stricture" (PFS) on T1-weighted hepatobiliary-phase images of gadoxetic acid-enhanced MR cholangiography (T1-MRC) to assess inter-reader agreement on diagnosis, location, and prognostic value of PFS on T1-MRC vs. DS or HGS on T2-MRCP in PSC patients, using ERCP as the gold standard.
METHODS
Six blinded readers independently reviewed 129 MRIs to diagnose and locate stricture, if present. DS/HGS was determined on T2-MRCP. On T1-MRC, PFS was diagnosed if no GA excretion was seen in the CBD, hilum or distal RHD, or LHD. If excretion was normal, "no functional stricture" (NFS) was diagnosed. T1-MRC diagnoses (NFS = 87; PFS = 42) were correlated with ERCP, clinical scores, labs, splenic volume, and clinical events. Statistical analyses included Kaplan-Meier curves and Cox regression.
RESULTS
Interobserver agreement was almost perfect for NFS vs. PFS diagnosis, but fair to moderate for DS and HGS. Forty-four ERCPs in 129 patients (34.1%) were performed, 39 in PFS (92.9%), and, due to clinical suspicion, five in NFS (5.7%) patients. PFS and NFS diagnoses had 100% PPV and 100% NPV, respectively. Labs and clinical scores were significantly worse for PFS vs. NFS. PFS patients underwent more diagnostic and therapeutic ERCPs, experienced more clinical events, and reached significantly more endpoints (p < 0.001) than those with NFS. Multivariate analysis identified PFS as an independent risk factor for liver-related events.
CONCLUSION
T1-MRC was superior to T2-MRCP for stricture diagnosis, stricture location, and prognostication.
CLINICAL RELEVANCE STATEMENT
Because half of PSC patients will develop clinically-relevant strictures over the course of the disease, earlier more confident diagnosis and correct localization of functional stricture on gadoxetic acid-enhanced MRI may optimize management and improve prognostication.
KEY POINTS
• There is no consensus regarding biliary stricture imaging features in PSC that have clinical relevance. • Twenty-minute T1-weighted MRC images correctly classified PSC patients with potential (PFS) vs with no functional stricture (NFS). • T1-MRC diagnoses may reduce the burden of diagnostic ERCPs.
Topics: Humans; Cholangiopancreatography, Magnetic Resonance; Constriction, Pathologic; Cholangitis, Sclerosing; Retrospective Studies; Magnetic Resonance Imaging; Cholangiopancreatography, Endoscopic Retrograde
PubMed: 37470827
DOI: 10.1007/s00330-023-09915-3 -
Dermatologie (Heidelberg, Germany) Jan 2024Lichen sclerosus (LS) and lichen planus (LP) are chronic inflammatory dermatoses of unknown aetiology. They pose the most important differential diagnoses of... (Review)
Review
Lichen sclerosus (LS) and lichen planus (LP) are chronic inflammatory dermatoses of unknown aetiology. They pose the most important differential diagnoses of inflammatory dermatoses in the genital area. There is often a delay in diagnosing LS and LP and subsequently treatment is initiated late in the course of the disease, which will lead to scarring and a decreased quality of life. There is an increased risk of the development of malignancies in the genital area in both diseases; however, early and continuous treatment with potent topical steroids will decrease this risk.
Topics: Humans; Lichen Sclerosus et Atrophicus; Quality of Life; Lichen Planus; Diagnosis, Differential
PubMed: 38133692
DOI: 10.1007/s00105-023-05267-7 -
Danish Medical Journal Nov 2023Complicated appendicitis is a severe condition, requiring early diagnosis and intervention to prevent complications. We aimed to investigate how resident surgeons...
INTRODUCTION
Complicated appendicitis is a severe condition, requiring early diagnosis and intervention to prevent complications. We aimed to investigate how resident surgeons distinguish and manage complicated appendicitis and their perspectives on preoperative diagnostic markers.
METHODS
The electronic survey was face validated. It contained questions about demographics, resident surgeons' considerations on the preoperative diagnosis of complicated appendicitis, and views on the need for and relevance of preoperative diagnostic markers. It was sent to all resident surgeons in the Eastern part of Denmark.
RESULTS
Seven hospitals and their 92 resident surgeons received the survey, and 90% responded. Most resident surgeons used symptoms and signs of pain to diagnose suspected complicated appendicitis. Half of the surgeons used computed tomographies, and 95% used routine blood tests. Most surgeons (83%) would change the management of patients with preoperatively diagnosed complicated appendicitis in comparison to uncomplicated appendicitis. However, only 17% felt the need for a preoperative diagnostic marker.
CONCLUSIONS
Resident surgeons in Eastern Denmark use non-specific diagnostic techniques to distinguish complicated from uncomplicated appendicitis and would change treatment if appendicitis was diagnosed preoperatively. However, despite limited interest, our results suggest a need for new diagnostic markers to differentiate between the severity of appendicitis, thus enhancing education and training in managing such cases.
FUNDING
None.
TRIAL REGISTRATION
None.
Topics: Humans; Appendicitis; Appendectomy; Surveys and Questionnaires; Diagnosis, Differential; Tomography, X-Ray Computed; Acute Disease
PubMed: 38018705
DOI: No ID Found -
Artificial Intelligence in Medicine Jun 2024Hematology is the study of diagnosis and treatment options for blood diseases, including cancer. Cancer is considered one of the deadliest diseases across all age... (Review)
Review
Hematology is the study of diagnosis and treatment options for blood diseases, including cancer. Cancer is considered one of the deadliest diseases across all age categories. Diagnosing such a deadly disease at the initial stage is essential to cure the disease. Hematologists and pathologists rely on microscopic evaluation of blood or bone marrow smear images to diagnose blood-related ailments. The abundance of overlapping cells, cells of varying densities among platelets, non-illumination levels, and the amount of red and white blood cells make it more difficult to diagnose illness using blood cell images. Pathologists are required to put more effort into the traditional, time-consuming system. Nowadays, it becomes possible with machine learning and deep learning techniques, to automate the diagnostic processes, categorize microscopic blood cells, and improve the accuracy of the procedure and its speed as the models developed using these methods may guide an assisting tool. In this article, we have acquired, analyzed, scrutinized, and finally selected around 57 research papers from various machine learning and deep learning methodologies that have been employed in the diagnosis of leukemia and its classification over the past 20 years, which have been published between the years 2003 and 2023 by PubMed, IEEE, Science Direct, Google Scholar and other pertinent sources. Our primary emphasis is on evaluating the advantages and limitations of analogous research endeavors to provide a concise and valuable research directive that can be of significant utility to fellow researchers in the field.
Topics: Humans; Deep Learning; Hematologic Neoplasms; Machine Learning; Diagnosis, Computer-Assisted
PubMed: 38657439
DOI: 10.1016/j.artmed.2024.102883 -
Talanta Dec 2023Although there are new approaches in both cancer treatment and diagnosis, overall mortality is a major concern. New technologies have attempted to look at breath... (Review)
Review
Although there are new approaches in both cancer treatment and diagnosis, overall mortality is a major concern. New technologies have attempted to look at breath volatile organic compounds (VOCs) detection to diagnose cancer. Gas Chromatography and Mass Spectrometry (GC - MS) have remained the gold standard of VOC analysis for decades, but it has limitations in differentiating VOCs between cancer subtypes. To increase efficacy and accuracy, new methods to analyze these breath VOCs have been introduced, such as Solid Phase Microextraction/Gas Chromatography-Mass Spectrometry (SPME/GC-MS), Selected Ion Flow Tube - Mass Spectrometry (SIFT-MS), Proton Transfer Reaction - Mass Spectrometry (PRT-MS), Ion Mobility Spectrometry (IMS), and Colorimetric Sensors. This article highlights new technologies that have been studied and applied in the detection and quantification of breath VOCs for possible cancer diagnoses.
Topics: Volatile Organic Compounds; Gas Chromatography-Mass Spectrometry; Mass Spectrometry; Breath Tests; Solid Phase Microextraction; Neoplasms
PubMed: 37327663
DOI: 10.1016/j.talanta.2023.124767 -
European Journal of Internal Medicine Mar 2024Whipple's disease, an extremely rare, chronic infection caused by Tropheryma whipplei, an actinobacterium ubiquitously present in the environment, is a multisystemic... (Review)
Review
Whipple's disease, an extremely rare, chronic infection caused by Tropheryma whipplei, an actinobacterium ubiquitously present in the environment, is a multisystemic condition that can affect several organs. Therefore, Whipple's disease should always be considered by physicians working across various branches of medicine, including internal medicine, rheumatology, infectious diseases, gastroenterology, haematology, and neurology. Initially, Whipple's disease is challenging to diagnose due to both its rarity and non-specific clinical features, almost indistinguishable from rheumatological conditions. A few years later, the onset of gastrointestinal symptoms increases the specificity of its clinical picture and helps in reaching the correct diagnosis. Diagnosis is typically made by finding PAS-positive macrophages in the lamina propria at duodenal biopsy. PCR for Tropheryma whipplei is nowadays also increasingly available, and represents an undeniable help in diagnosing this condition. However, it may also be misleading as false positives can occur. If not promptly recognized and treated, central nervous system involvement may develop, which can be fatal. The therapeutic gold standard has not yet been fully established, particularly in cases of recurrent disease, neurological involvement, and an immune reconstitution inflammatory syndrome that may arise following the initiation of antibiotic therapy.
Topics: Humans; Whipple Disease; Rare Diseases; Anti-Bacterial Agents; Biopsy; Tropheryma; Physicians
PubMed: 38105122
DOI: 10.1016/j.ejim.2023.12.009