-
Scientific Reports Nov 2020Heart disease is a fatal human disease, rapidly increases globally in both developed and undeveloped countries and consequently, causes death. Normally, in this disease,...
Heart disease is a fatal human disease, rapidly increases globally in both developed and undeveloped countries and consequently, causes death. Normally, in this disease, the heart fails to supply a sufficient amount of blood to other parts of the body in order to accomplish their normal functionalities. Early and on-time diagnosing of this problem is very essential for preventing patients from more damage and saving their lives. Among the conventional invasive-based techniques, angiography is considered to be the most well-known technique for diagnosing heart problems but it has some limitations. On the other hand, the non-invasive based methods, like intelligent learning-based computational techniques are found more upright and effectual for the heart disease diagnosis. Here, an intelligent computational predictive system is introduced for the identification and diagnosis of cardiac disease. In this study, various machine learning classification algorithms are investigated. In order to remove irrelevant and noisy data from extracted feature space, four distinct feature selection algorithms are applied and the results of each feature selection algorithm along with classifiers are analyzed. Several performance metrics namely: accuracy, sensitivity, specificity, AUC, F1-score, MCC, and ROC curve are used to observe the effectiveness and strength of the developed model. The classification rates of the developed system are examined on both full and optimal feature spaces, consequently, the performance of the developed model is boosted in case of high variated optimal feature space. In addition, P-value and Chi-square are also computed for the ET classifier along with each feature selection technique. It is anticipated that the proposed system will be useful and helpful for the physician to diagnose heart disease accurately and effectively.
Topics: Adult; Aged; Aged, 80 and over; Artificial Intelligence; Computational Biology; Female; Follow-Up Studies; Heart Diseases; Humans; Machine Learning; Male; Middle Aged; Models, Statistical; Prognosis; ROC Curve
PubMed: 33184369
DOI: 10.1038/s41598-020-76635-9 -
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 -
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 -
Indian Journal of Dermatology 2022Some alopecic diseases can be diagnosed by detailed history taking and physical examination, but in many cases, biopsy must be performed to make a definite diagnosis.
BACKGROUND
Some alopecic diseases can be diagnosed by detailed history taking and physical examination, but in many cases, biopsy must be performed to make a definite diagnosis.
AIMS AND OBJECTIVES
This study aimed to evaluate the clinico-pathological concordance of scalp lesions showing alopecia.
MATERIALS AND METHODS
We retrospectively reviewed the electronic medical records and biopsy slides of patients who underwent biopsy for evaluating scalp lesions showing alopecia. Based on the definitions of clinico-pathological concordances, scalp alopecic disease was evaluated.
RESULTS
A total of 121 patients were enrolled in the study. A total of 203 clinical differential diagnoses were made before performing a biopsy. Thirty-one patients showed full concordance, and 58 patients showed partial concordance; thus overall concordance was shown in 89 patients (73.55%). Folliculitis decalvans and alopecia areata showed a higher full concordance rate than average ( < 0.05), whereas dissecting folliculitis showed a lower overall concordance rate than average, and folliculitis decalvans showed a higher overall concordance rate than average ( < 0.05). The overall concordance rate of alopecia areata was 100% ( = 0.061).
CONCLUSION
In diagnosing folliculitis decalvans and alopecia areata, which showed high full and overall concordance, performing a biopsy to make a definite diagnosis is not always necessary, especially when patients show typical clinical features. Dissecting folliculitis, which showed low overall concordance, was less likely to be suspected as a clinical differential diagnosis, making it difficult to distinguish based on clinical findings alone. Therefore, when it is suspected, a detailed evaluation including a biopsy is recommended.
PubMed: 36578761
DOI: 10.4103/ijd.ijd_112_22 -
Journal of Cachexia, Sarcopenia and... Dec 2021Sarcopenia is defined as muscle wasting, characterized by a progressive loss of muscle mass and function due to ageing. Diagnosis of sarcopenia typically involves both...
BACKGROUND
Sarcopenia is defined as muscle wasting, characterized by a progressive loss of muscle mass and function due to ageing. Diagnosis of sarcopenia typically involves both muscle imaging and the physical performance of people exhibiting signs of muscle weakness. Despite its worldwide prevalence, a molecular method for accurately diagnosing sarcopenia has not been established.
METHODS
We develop an artificial intelligence (AI) diagnosis model of sarcopenia using a published transcriptome dataset comprising patients from multiple ethnicities. For the AI model for sarcopenia diagnosis, we use a transcriptome database comprising 17 339 genes from 118 subjects. Among the 17 339 genes, we select 27 features as the model inputs. For feature selection, we use a random forest, extreme gradient boosting and adaptive boosting. Using the top 27 features, we propose a four-layer deep neural network, named DSnet-v1, for sarcopenia diagnosis.
RESULTS
Among isolated testing datasets, DSnet-v1 provides high sensitivity (100%), specificity (94.12%), accuracy (95.83%), balanced accuracy (97.06%) and area under receiver operating characteristics (0.99). To extend the number of patient data, we develop a web application (http://sarcopeniaAI.ml/), where the model can be accessed unrestrictedly to diagnose sarcopenia if the transcriptome is available. A focused analysis of the top 27 genes for their differential or co-expression with other genes implied the potential existence of race-specific factors for sarcopenia, suggesting the possibility of identifying causal factors of sarcopenia when a more extended dataset is provided.
CONCLUSIONS
Our new AI model, DSnet-v1, accurately diagnoses sarcopenia and is currently available publicly to assist healthcare providers in diagnosing and treating sarcopenia.
Topics: Artificial Intelligence; Biomarkers; Humans; Intelligence; Prognosis; Sarcopenia
PubMed: 34704369
DOI: 10.1002/jcsm.12840 -
Gastric Cancer : Official Journal of... Mar 2024Patients with gastric atrophy and intestinal metaplasia (IM) were at risk for gastric cancer, necessitating an accurate risk assessment. We aimed to establish and... (Randomized Controlled Trial)
Randomized Controlled Trial
OBJECTIVE
Patients with gastric atrophy and intestinal metaplasia (IM) were at risk for gastric cancer, necessitating an accurate risk assessment. We aimed to establish and validate a diagnostic approach for gastric biopsy specimens using deep learning and OLGA/OLGIM for individual gastric cancer risk classification.
METHODS
In this study, we prospectively enrolled 545 patients suspected of atrophic gastritis during endoscopy from 13 tertiary hospitals between December 22, 2017, to September 25, 2020, with a total of 2725 whole-slide images (WSIs). Patients were randomly divided into a training set (n = 349), an internal validation set (n = 87), and an external validation set (n = 109). Sixty patients from the external validation set were randomly selected and divided into two groups for an observer study, one with the assistance of algorithm results and the other without. We proposed a semi-supervised deep learning algorithm to diagnose and grade IM and atrophy, and we compared it with the assessments of 10 pathologists. The model's performance was evaluated based on the area under the curve (AUC), sensitivity, specificity, and weighted kappa value.
RESULTS
The algorithm, named GasMIL, was established and demonstrated encouraging performance in diagnosing IM (AUC 0.884, 95% CI 0.862-0.902) and atrophy (AUC 0.877, 95% CI 0.855-0.897) in the external test set. In the observer study, GasMIL achieved an 80% sensitivity, 85% specificity, a weighted kappa value of 0.61, and an AUC of 0.953, surpassing the performance of all ten pathologists in diagnosing atrophy. Among the 10 pathologists, GasMIL's AUC ranked second in OLGA (0.729, 95% CI 0.625-0.833) and fifth in OLGIM (0.792, 95% CI 0.688-0.896). With the assistance of GasMIL, pathologists demonstrated improved AUC (p = 0.013), sensitivity (p = 0.014), and weighted kappa (p = 0.016) in diagnosing IM, and improved specificity (p = 0.007) in diagnosing atrophy compared to pathologists working alone.
CONCLUSION
GasMIL shows the best overall performance in diagnosing IM and atrophy when compared to pathologists, significantly enhancing their diagnostic capabilities.
Topics: Humans; Gastritis, Atrophic; Stomach Neoplasms; Deep Learning; Gastroscopy; Biopsy; Risk Factors; Atrophy; Metaplasia
PubMed: 38095766
DOI: 10.1007/s10120-023-01451-9 -
Chinese Clinical Oncology Oct 2018Intrahepatic cholangiocarcinoma (ICC) is the second most common primary hepatic malignant tumor and its incidence is increasing over the world. At present times, radical... (Review)
Review
Intrahepatic cholangiocarcinoma (ICC) is the second most common primary hepatic malignant tumor and its incidence is increasing over the world. At present times, radical liver resection is still the most effective treatment for ICC patients to achieve long term survival. Pathological lymph node metastases (LMN), found in 15% to 45% of the patients, have been recognized as an extremely poor prognostic risk factor, even if curative resection is performed. So, considering this issue, it acquires relevance to determine the validity of surgical resection for LNM cases that are diagnosed in the preoperative setting, or whether a routine lymphadenectomy should be performed systematically in all hepatectomies for ICC. The role of routine lymphadenectomy in the surgical treatment of ICC remains controversial, with some centers considering it standard whereas other surgeons perform lymphadenectomy only as a selective indication. Recently, a growing widespread adoption of lymphadenectomy was demonstrated that nearly doubled its commonly reported execution rate. The newly updated eight edition of the American Joint Committee on Cancer (AJCC) staging system now recommends that six nodes need to be analyzed to stage patients with ICC. In this review, we analyzed and summarized some anatomic considerations of the lymphatic anatomy of the liver and the current knowledge and potential advantages of performing a routine lymphadenectomy in patients with ICC, especially looking at pathological staging, prognosis, prevention of local recurrence and outcome. New areas like lymphadenectomy in cirrhotic patients and laparoscopic lymphadenectomy are also discussed.
Topics: Bile Duct Neoplasms; Cholangiocarcinoma; Humans; Lymph Node Excision; Neoplasm Staging
PubMed: 30180752
DOI: 10.21037/cco.2018.07.02 -
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 -
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