-
BMC Oral Health Jun 2023Artificial intelligence (AI) has been introduced to interpret the panoramic radiographs (PRs). The aim of this study was to develop an AI framework to diagnose multiple...
BACKGROUND
Artificial intelligence (AI) has been introduced to interpret the panoramic radiographs (PRs). The aim of this study was to develop an AI framework to diagnose multiple dental diseases on PRs, and to initially evaluate its performance.
METHODS
The AI framework was developed based on 2 deep convolutional neural networks (CNNs), BDU-Net and nnU-Net. 1996 PRs were used for training. Diagnostic evaluation was performed on a separate evaluation dataset including 282 PRs. Sensitivity, specificity, Youden's index, the area under the curve (AUC), and diagnostic time were calculated. Dentists with 3 different levels of seniority (H: high, M: medium, L: low) diagnosed the same evaluation dataset independently. Mann-Whitney U test and Delong test were conducted for statistical analysis (ɑ=0.05).
RESULTS
Sensitivity, specificity, and Youden's index of the framework for diagnosing 5 diseases were 0.964, 0.996, 0.960 (impacted teeth), 0.953, 0.998, 0.951 (full crowns), 0.871, 0.999, 0.870 (residual roots), 0.885, 0.994, 0.879 (missing teeth), and 0.554, 0.990, 0.544 (caries), respectively. AUC of the framework for the diseases were 0.980 (95%CI: 0.976-0.983, impacted teeth), 0.975 (95%CI: 0.972-0.978, full crowns), and 0.935 (95%CI: 0.929-0.940, residual roots), 0.939 (95%CI: 0.934-0.944, missing teeth), and 0.772 (95%CI: 0.764-0.781, caries), respectively. AUC of the AI framework was comparable to that of all dentists in diagnosing residual roots (p > 0.05), and its AUC values were similar to (p > 0.05) or better than (p < 0.05) that of M-level dentists for diagnosing 5 diseases. But AUC of the framework was statistically lower than some of H-level dentists for diagnosing impacted teeth, missing teeth, and caries (p < 0.05). The mean diagnostic time of the framework was significantly shorter than that of all dentists (p < 0.001).
CONCLUSIONS
The AI framework based on BDU-Net and nnU-Net demonstrated high specificity on diagnosing impacted teeth, full crowns, missing teeth, residual roots, and caries with high efficiency. The clinical feasibility of AI framework was preliminary verified since its performance was similar to or even better than the dentists with 3-10 years of experience. However, the AI framework for caries diagnosis should be improved.
Topics: Humans; Radiography, Panoramic; Artificial Intelligence; Tooth, Impacted; Dental Caries; Tooth
PubMed: 37270488
DOI: 10.1186/s12903-023-03027-6 -
BMC Medical Informatics and Decision... Mar 2022Acute Rheumatic Fever (ARF) is a critically important condition for which there is no diagnostic test. Diagnosis requires the use of a set of criteria comprising...
BACKGROUND
Acute Rheumatic Fever (ARF) is a critically important condition for which there is no diagnostic test. Diagnosis requires the use of a set of criteria comprising clinical, laboratory, electrocardiographic and echocardiographic findings. The complexity of the algorithm and the fact that clinicians lack familiarity with ARF, make ARF diagnosis ideally suited to an electronic decision support tool. The ARF Diagnosis Calculator was developed to assist clinicians in diagnosing ARF and correctly assign categories of 'possible, 'probable' or 'definite' ARF. This research aimed to evaluate the acceptability, accuracy, and test performance of the ARF Diagnosis Calculator.
METHODS
Three strategies were used to provide triangulation of data. Users of the calculator employed at Top End Health Service, Northern Territory, Australia were invited to participate in an online survey, and clinicians with ARF expertise were invited to participate in semi-structured interviews. Qualitative data were analysed using inductive analysis. Performance of the calculator in correctly diagnosing ARF was assessed using clinical data from 35 patients presenting with suspected ARF. Diagnoses obtained from the calculator were compared using the Kappa statistic with those obtained from a panel of expert clinicians.
RESULTS
Survey responses were available from 23 Top End Health Service medical practitioners, and interview data were available from five expert clinicians. Using a 6-point Likert scale, participants highly recommended the ARF Diagnosis Calculator (median 6, IQR 1), found it easy to use (median 5, IQR 1) and believed the calculator helped them diagnose ARF (median 5, IQR 1). Clinicians with ARF expertise noted that electronic decision making is not a substitute for clinical experience. There was high agreement between the ARF Diagnosis Calculator and the 'gold standard' ARF diagnostic process (κ = 0.767, 95% CI: 0.568-0.967). Incorrect assignment of diagnosis occurred in 4/35 (11%) patients highlighting the greater accuracy of expert clinical input for ambiguous presentations. Sixteen changes were incorporated into a revised version of the calculator.
CONCLUSIONS
The ARF Diagnosis Calculator is an easy-to-use, accessible tool, but it does not replace clinical expertise. The calculator performed well amongst clinicians and is an acceptable tool for use within the clinical setting with a high level of accuracy in comparison to the gold standard diagnostic process. Effective resources to support clinicians are critically important for improving the quality of care of ARF.
Topics: Echocardiography; Humans; Northern Territory; Rheumatic Fever; Surveys and Questionnaires
PubMed: 35346167
DOI: 10.1186/s12911-022-01816-7 -
American Family Physician Mar 2010Physicians often have difficulty diagnosing a generalized rash because many different conditions produce similar rashes, and a single condition can result in different... (Review)
Review
Physicians often have difficulty diagnosing a generalized rash because many different conditions produce similar rashes, and a single condition can result in different rashes with varied appearances. A rapid and accurate diagnosis is critically important to make treatment decisions, especially when mortality or significant morbidity can occur without prompt intervention. When a specific diagnosis is not immediately apparent, it is important to generate an inclusive differential diagnosis to guide diagnostic strategy and initial treatment. In part I of this two-part article, tables listing common, uncommon, and rare causes of generalized rash are presented to help generate an inclusive differential diagnosis. The tables describe the key clinical features and recommended tests to help accurately diagnose generalized rashes. If the diagnosis remains unclear, the primary care physician must decide whether to observe and treat empirically, perform further diagnostic testing, or refer the patient to a dermatologist. This decision depends on the likelihood of a serious disorder and the patient's response to treatment.
Topics: Child; Child, Preschool; Dermatology; Diagnosis, Differential; Exanthema; Family Practice; Humans; Infant; Referral and Consultation
PubMed: 20229971
DOI: No ID Found -
Journal of Medical Internet Research Jul 2021Diabetic retinopathy (DR), whose standard diagnosis is performed by human experts, has high prevalence and requires a more efficient screening method. Although machine... (Meta-Analysis)
Meta-Analysis Review
BACKGROUND
Diabetic retinopathy (DR), whose standard diagnosis is performed by human experts, has high prevalence and requires a more efficient screening method. Although machine learning (ML)-based automated DR diagnosis has gained attention due to recent approval of IDx-DR, performance of this tool has not been examined systematically, and the best ML technique for use in a real-world setting has not been discussed.
OBJECTIVE
The aim of this study was to systematically examine the overall diagnostic accuracy of ML in diagnosing DR of different categories based on color fundus photographs and to determine the state-of-the-art ML approach.
METHODS
Published studies in PubMed and EMBASE were searched from inception to June 2020. Studies were screened for relevant outcomes, publication types, and data sufficiency, and a total of 60 out of 2128 (2.82%) studies were retrieved after study selection. Extraction of data was performed by 2 authors according to PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses), and the quality assessment was performed according to the Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2). Meta-analysis of diagnostic accuracy was pooled using a bivariate random effects model. The main outcomes included diagnostic accuracy, sensitivity, and specificity of ML in diagnosing DR based on color fundus photographs, as well as the performances of different major types of ML algorithms.
RESULTS
The primary meta-analysis included 60 color fundus photograph studies (445,175 interpretations). Overall, ML demonstrated high accuracy in diagnosing DR of various categories, with a pooled area under the receiver operating characteristic (AUROC) ranging from 0.97 (95% CI 0.96-0.99) to 0.99 (95% CI 0.98-1.00). The performance of ML in detecting more-than-mild DR was robust (sensitivity 0.95; AUROC 0.97), and by subgroup analyses, we observed that robust performance of ML was not limited to benchmark data sets (sensitivity 0.92; AUROC 0.96) but could be generalized to images collected in clinical practice (sensitivity 0.97; AUROC 0.97). Neural network was the most widely used method, and the subgroup analysis revealed a pooled AUROC of 0.98 (95% CI 0.96-0.99) for studies that used neural networks to diagnose more-than-mild DR.
CONCLUSIONS
This meta-analysis demonstrated high diagnostic accuracy of ML algorithms in detecting DR on color fundus photographs, suggesting that state-of-the-art, ML-based DR screening algorithms are likely ready for clinical applications. However, a significant portion of the earlier published studies had methodology flaws, such as the lack of external validation and presence of spectrum bias. The results of these studies should be interpreted with caution.
Topics: Algorithms; Diabetes Mellitus; Diabetic Retinopathy; Diagnostic Techniques, Ophthalmological; Humans; Machine Learning; Neural Networks, Computer
PubMed: 34407500
DOI: 10.2196/23863 -
Chronic Respiratory Disease 2021Asthma is a common, chronic, and heterogeneous disease with a global impact and substantial economic costs. It is also associated with significant mortality and... (Review)
Review
Asthma is a common, chronic, and heterogeneous disease with a global impact and substantial economic costs. It is also associated with significant mortality and morbidity and the burden of undiagnosed asthma is significant. Asthma can be difficult to diagnose as there is no gold standard test and, while spirometry is central in diagnosing asthma, it may not be sufficient to confirm or exclude the diagnosis. The most commonly reported spirometric measures (forced expiratory volume in one second (FEV) and forced vital capacity assess function in the larger airways. However, small airway dysfunction is highly prevalent in asthma and some studies suggest small airway involvement is one of the earliest disease manifestations. Moreover, there are new inhaled therapies with ultrafine particles that are specifically designed to target the small airways. Potentially, tests of small airways may more accurately diagnose early or mild asthma and assess the response to treatment than spirometry. Furthermore, some assessment techniques do not rely on forced ventilatory manoeuvres and may, therefore, be easier for certain groups to perform. This review discusses the current evidence of small airways tests in asthma and future research that may be needed to further assess their utility.
Topics: Asthma; Forced Expiratory Volume; Humans; Respiratory Function Tests; Spirometry; Vital Capacity
PubMed: 34693751
DOI: 10.1177/14799731211053332 -
Neuroscience Mar 2022This study investigates the error processing components in the EEG signal of Performers and Observers using an auditory lexical decision task, in which participants...
This study investigates the error processing components in the EEG signal of Performers and Observers using an auditory lexical decision task, in which participants heard spoken items and decided for each item if it was a real word or not. Pairs of participants were tested in both the role of the Performer and the Observer. In the literature, an Error Related Negativity (ERN)-Error Positivity (Pe) complex has been identified for performed (ERN-Pe) and observed (oERN-oPe) errors. While these effects have been widely studied for performance errors in speeded decision tasks relying on visual input, relatively little is known about the performance monitoring signatures in observed language processing based on auditory input. In the lexical decision task, native Dutch speakers listened to real Dutch Words, Non-Words, and crucially, long Pseudowords that resembled words until the final syllable and were shown to be error-prone in a pilot study, because they were responded to too soon. We hypothesised that the errors in the task would result in a response locked ERN-Pe pattern both for the Performer and for the Observer. Our hypothesis regarding the ERN was not supported, however a Pe-like effect, as well as a P300 were present. Analyses to disentangle lexical and error processing similarly indicated a P300 for errors, and the results furthermore pointed to differences between responses before and after word offset. The findings are interpreted as marking attention during error processing during auditory word recognition.
Topics: Attention; Electroencephalography; Evoked Potentials; Humans; Language; Pilot Projects; Reaction Time
PubMed: 33577954
DOI: 10.1016/j.neuroscience.2021.02.001 -
Head & Face Medicine Mar 2015Oral squamous cell carcinoma (OSCC) has a remarkably high incidence worldwide, and a fairly serious prognosis, encouraging further research into advanced technologies... (Review)
Review
BACKGROUND
Oral squamous cell carcinoma (OSCC) has a remarkably high incidence worldwide, and a fairly serious prognosis, encouraging further research into advanced technologies for noninvasive methods of making early diagnoses, ideally in primary care settings.
OBJECTIVES
Our purpose was to examine the validity of using advanced noninvasive technologies in diagnosis of OSCC by identifying and evaluating relevant published reports.
DATA SOURCE
MEDLINE, EMBASE, and CINAHL were searched to identify clinical trials and other information published between 1990 and 10 June 2014; the searches of MEDLINE and EMBASE were updated to November 2014.
STUDY SELECTION
Studies of noninvasive methods of diagnosing OSCC, including oral brush biopsy, optical biopsy, saliva-based oral cancer diagnosis, and others were included.
DATA EXTRACTION
Data were abstracted and evaluated in duplicate for possible relevance on two occasions at an interval of 2 months before being included or excluded.
DATA SYNTHESIS
This study identified 163 studies of noninvasive methods for diagnosing OSCC that met the inclusion criteria. These included six studies of oral brush biopsy, 42 of saliva-based oral diagnosis, and 115 of optical biopsy. Sixty nine of these studies were assessed by the modified version of the QUADAS instrument. Saliva-based oral cancer diagnosis and optical biopsy were found to be promising noninvasive methods for diagnosing OSCC.
LIMITATION
The strength of evidence was rated low for accuracy outcomes because the studies did not report important details required to assess the risk for bias.
CONCLUSIONS
It is clear that screening for and early detection of cancer and pre-cancerous lesions have the potential to reduce the morbidity and mortality of this disease. Advances in technologies for saliva-based oral diagnosis and optical biopsy are promising pathways for the future development of more effective noninvasive methods for diagnosing OSCC that are easy to perform clinically in primary care settings.
Topics: Biopsy; Carcinoma, Squamous Cell; Diagnostic Tests, Routine; Female; Humans; Male; Mouth Neoplasms; Physical Examination; Saliva; Visual Analog Scale
PubMed: 25889859
DOI: 10.1186/s13005-015-0063-z -
Medicina Oral, Patologia Oral Y Cirugia... Jul 2023Knowledge of oral mucosal lesions (OMLs) among dentists is relevant in diagnosing potentially malignant diseases and oral cancer at an early stage. The aim of this...
BACKGROUND
Knowledge of oral mucosal lesions (OMLs) among dentists is relevant in diagnosing potentially malignant diseases and oral cancer at an early stage. The aim of this survey was to explore dentists' knowledge about OMLs.
MATERIAL AND METHODS
Respondents to a web-based questionnaire, containing 11 clinical vignettes representing patients with various OMLs, provided a (differential) diagnosis and management for each. Information about demographics and clinical experience of the participants was acquired as well. Descriptive statistics were performed and T-tests were used to test for significant (p<0.05) differences in mean scores for correct diagnosis and management between subgroups based on demographic variables.
RESULTS
Forty-four of 500 invited dentists completed the questionnaire. For (potentially) malignant OMLs, the number of correct diagnoses ranged from 14 to 93%, whilst the number of correct management decisions ranged from 43 to 86%. For benign OMLs, the number of correct diagnoses and management decisions ranged from 32 to 100% and 9 to 48%, respectively. For 11 clinical vignettes, mean scores for correct diagnosis, correct management and correct diagnosis and management were respectively 7.2 (±1.8), 5.7 (±1.5), and 3.8 (±1.7).
CONCLUSIONS
The results show that dentists in the Netherlands do not have sufficient knowledge to accurately diagnose some OMLs and to select a correct management. This may result in over-referral of benign OMLs and under-referral for (potentially) malignant OMLs. Clinical guidelines, that include standardized criteria for referral, and continuing education, may improve dentists' ability to correctly diagnose and accurately manage OMLs.
Topics: Humans; Netherlands; Mouth Neoplasms; Referral and Consultation; Diagnosis, Differential; Dentists; Surveys and Questionnaires
PubMed: 36641742
DOI: 10.4317/medoral.25774 -
Primary Care Respiratory Journal :... Jun 2013Respiratory disorders are responsible for considerable morbidity and mortality in children. Spirometry is a useful investigation for diagnosing and monitoring a variety... (Review)
Review
Respiratory disorders are responsible for considerable morbidity and mortality in children. Spirometry is a useful investigation for diagnosing and monitoring a variety of paediatric respiratory diseases, but it is underused by primary care physicians and paediatricians treating children with respiratory disease. We now have a better understanding of respiratory physiology in children, and newer computerised spirometry equipment is available with updated regional reference values for the paediatric age group. This review evaluates the current literature for indications, test procedures, quality assessment, and interpretation of spirometry results in children. Spirometry may be useful for asthma, cystic fibrosis, congenital or acquired airway malformations and many other respiratory diseases in children. The technique for performing spirometry in children is crucial and is discussed in detail. Most children, including preschool children, can perform acceptable spirometry. Steps for interpreting spirometry results include identification of common errors during the test by applying acceptability and repeatability criteria and then comparing test parameters with reference standards. Spirometry results depict only the pattern of ventilation, which may be normal, obstructive, restrictive, or mixed. The diagnosis should be based on both clinical features and spirometry results. There is a need to encourage primary care physicians and paediatricians treating respiratory diseases in children to use spirometry after adequate training.
Topics: Age Factors; Asthma; Child; Child, Preschool; Cystic Fibrosis; Forced Expiratory Volume; Humans; Lung Diseases; Severity of Illness Index; Spirometry; Vital Capacity
PubMed: 23732636
DOI: 10.4104/pcrj.2013.00042 -
Critical Care (London, England) 2008Early, accurate diagnosis is fundamental in the management of patients with ventilator-associated pneumonia (VAP). The aim of this qualitative review was to compare... (Review)
Review
INTRODUCTION
Early, accurate diagnosis is fundamental in the management of patients with ventilator-associated pneumonia (VAP). The aim of this qualitative review was to compare various criteria of diagnosing VAP in the intensive care unit (ICU) with a special emphasis on the value of clinical diagnosis, microbiological culture techniques, and biomarkers of host response.
METHODS
A MEDLINE search was performed using the keyword 'ventilator associated pneumonia' AND 'diagnosis'. Our search was limited to human studies published between January 1966 and June 2007. Only studies of at least 25 adult patients were included. Predefined variables were collected, including year of publication, study design (prospective/retrospective), number of patients included, and disease group.
RESULTS
Of 572 articles fulfilling the initial search criteria, 159 articles were chosen for detailed review of the full text. A total of 64 articles fulfilled the inclusion criteria and were included in our review. Clinical criteria, used in combination, may be helpful in diagnosing VAP, however, the considerable inter-observer variability and the moderate performance should be taken in account. Bacteriologic data do not increase the accuracy of diagnosis as compared to clinical diagnosis. Quantitative cultures obtained by different methods seem to be rather equivalent in diagnosing VAP. Blood cultures are relatively insensitive to diagnose pneumonia. The rapid availability of cytological data, including inflammatory cells and Gram stains, may be useful in initial therapeutic decisions in patients with suspected VAP. C-reactive protein, procalcitonin, and soluble triggering receptor expressed on myeloid cells are promising biomarkers in diagnosing VAP.
CONCLUSION
An integrated approach should be followed in diagnosing and treating patients with VAP, including early antibiotic therapy and subsequent rectification according to clinical response and results of bacteriologic cultures.
Topics: Biopsy; Bronchoalveolar Lavage Fluid; Colony Count, Microbial; Cross Infection; Humans; Intensive Care Units; Pneumonia, Bacterial; Radiography, Thoracic; Respiration, Artificial; Risk Factors
PubMed: 18426596
DOI: 10.1186/cc6877