-
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 -
Journal of Paediatrics and Child Health Apr 2023As the COVID-19 pandemic continues, multisystem inflammatory syndrome in children (MIS-C) maintains its importance in the differential diagnosis of common febrile...
AIMS
As the COVID-19 pandemic continues, multisystem inflammatory syndrome in children (MIS-C) maintains its importance in the differential diagnosis of common febrile diseases. MIS-C should be promptly diagnosed because corticosteroid and/or intravenous immunoglobulin treatment can prevent severe clinical outcomes. In this study, we aimed to evaluate clinical presentation, diagnostic parameters and management of MIS-C and compare its clinical features to those of common febrile disease.
METHODS
This study was conducted at a tertiary-level university hospital between December 2020 and October 2022. One hundred and six children who were initially considered to have MIS-C disease were included in the study. During the follow-up period in the hospital, when the clinical and laboratory findings were re-evaluated, 38 out of 106 children were diagnosed differently. The clinical and laboratory findings of 68 children followed up with the diagnosis of MIS-C and 38 children who were initially misdiagnosed as MIS-C but with different final diagnoses were retrospectively compared.
RESULTS
We identified 68 patients with MIS-C and 38 patients misdiagnosed as MIS-C during the study period. Infectious causes (71%), predominantly bacterial origin, were the most frequently confused conditions with MIS-C. Patients with MIS-C were older and had a more severe clinical course with high rates of respiratory distress, shock, and paediatric intensive care unit admission. While rash and conjunctivitis were more common among patients with MIS-C, cough, abdominal pain and diarrhoea were observed more frequently in patients misdiagnosed as MIS-C. Lower absolute lymphocyte counts, platelet counts and higher C-reactive protein and fibrinogen levels, pathological findings on echocardiography were the distinctive laboratory parameters for MIS-C. Multivariate analysis showed that older age, presence of conjunctivitis, high level of serum CRP and lower platelets were the most discriminative predictors for the diagnosis of MIS-C.
CONCLUSION
There are still no specific findings to diagnose MIS-C, which therefore can be confused with different clinical conditions. Further data are needed to assist the clinician in the differential diagnosis of MIS-C and the diagnostic criteria should be updated over time.
Topics: Child; Humans; COVID-19; Pandemics; Retrospective Studies; Confusion; Conjunctivitis; Diagnostic Errors; COVID-19 Testing
PubMed: 36779307
DOI: 10.1111/jpc.16371 -
Journal of Clinical Pathology Nov 2021An increasing number of small pulmonary nodules are being screened by CT, and an intraoperative diagnosis is necessary for preventing excessive treatment. However, there...
AIMS
An increasing number of small pulmonary nodules are being screened by CT, and an intraoperative diagnosis is necessary for preventing excessive treatment. However, there is limited literature on the frozen diagnosis of small sclerosing pneumocytomas (SPs). In particular, tumours smaller than 1 cm are challenging for pathologists performing intraoperative frozen diagnosis.
METHODS
In total, 230 cases of SP were surgically resected between January 2015 and March 2019 at Shanghai Chest Hospital, and of them, 76 cases were smaller than 1 cm. The histology and clinical information of these 76 cases (33.0%, 76/230) were reviewed retrospectively, 54 cases of which were diagnosed intraoperatively, and the pitfalls were summarised. All diagnoses were confirmed on permanent sections and immunohistochemical sections.
RESULTS
Histologically, 78.9% (60/76) of the small SP was dominated by one growth pattern, and solid and papillary growth pattern were the most commonly misdiagnosed circumstances. The rate of intraoperative misdiagnosis of these SP smaller than 1 cm was 11.1% (6/54).
CONCLUSIONS
The main reason for misdiagnosis was failure to recognise the dual cell populations and the cellular atypia. Diagnostic clues include the gross morphology, the presence of dual-cell populations and a hypercellular papillary core, foam cell accumulation in glandular spaces and haemorrhage and haemosiderin on the periphery. In spite of awareness of pitfalls some cases may still be essentially impossible to diagnose on frozen section.
Topics: Adult; Aged; Cytodiagnosis; Diagnosis, Differential; Diagnostic Errors; Female; Frozen Sections; Humans; Intraoperative Period; Lung Neoplasms; Male; Middle Aged; Multiple Pulmonary Nodules; Retrospective Studies; Sclerosis; Sensitivity and Specificity; Solitary Pulmonary Nodule
PubMed: 33782195
DOI: 10.1136/jclinpath-2020-206729 -
Journal of Neurologic Physical Therapy... Apr 2021Individuals with benign paroxysmal positional vertigo (BPPV) are frequently referred to physical therapy for management, but little is known on how reliable therapists...
BACKGROUND AND PURPOSE
Individuals with benign paroxysmal positional vertigo (BPPV) are frequently referred to physical therapy for management, but little is known on how reliable therapists are at diagnosing BPPV. The purpose of the study was to examine the agreement between physical therapists in identifying nystagmus and diagnosing BPPV.
METHODS
Thirty-eight individuals with complaints of positional vertigo, 19 from each of 2 clinics (clinics 1 and 2) that specialize in vestibular rehabilitation, had eye movements recorded using video goggles during positioning tests including supine-to-sit, supine roll, and Dix-Hallpike tests. Three therapists from each of the clinics independently observed videos, documented nystagmus characteristics of each testing position, and made a diagnosis for each case. Kappa (κ) statistics were calculated between therapists within each clinic for nystagmus identification and diagnosis.
RESULTS
Clinic 1 therapists demonstrated substantial to almost perfect agreement in identifying nystagmus during positional tests (κ = 0.68-1, P < 0.005). Clinic 2 therapists showed moderate to almost perfect agreement for presence of nystagmus (κ = 0.57-1, P < 0.005). Therapists at both sites had almost perfect agreement of diagnosis side, canal, and mechanism (κ = 0.81-1, P < 0.005).
DISCUSSION AND CONCLUSION
Therapists utilized observations from multiple positional tests to determine diagnoses. This was evident by occasional disagreement in nystagmus presence and characteristics, but agreement in diagnosis, including ruling out BPPV. The results may not be generalizable to all physical therapists or therapists' ability to diagnose central and atypical nystagmus presentations. Experienced physical therapists demonstrated strong agreement in diagnosing common forms of BPPV.Video Abstract available for more insight from the authors (see the Video Supplemental Digital Content 1, available at: http://links.lww.com/JNPT/A340).
Topics: Benign Paroxysmal Positional Vertigo; Humans; Nystagmus, Pathologic; Physical Therapists; Vestibular Function Tests
PubMed: 33675601
DOI: 10.1097/NPT.0000000000000349 -
Journal of the American Medical... Sep 2023Incorporating artificial intelligence (AI) into clinics brings the risk of automation bias, which potentially misleads the clinician's decision-making. The purpose of...
BACKGROUND
Incorporating artificial intelligence (AI) into clinics brings the risk of automation bias, which potentially misleads the clinician's decision-making. The purpose of this study was to propose a potential strategy to mitigate automation bias.
METHODS
This was a laboratory study with a randomized cross-over design. The diagnosis of anterior cruciate ligament (ACL) rupture, a common injury, on magnetic resonance imaging (MRI) was used as an example. Forty clinicians were invited to diagnose 200 ACLs with and without AI assistance. The AI's correcting and misleading (automation bias) effects on the clinicians' decision-making processes were analyzed. An ordinal logistic regression model was employed to predict the correcting and misleading probabilities of the AI. We further proposed an AI suppression strategy that retracted AI diagnoses with a higher misleading probability and provided AI diagnoses with a higher correcting probability.
RESULTS
The AI significantly increased clinicians' accuracy from 87.2%±13.1% to 96.4%±1.9% (P < .001). However, the clinicians' errors in the AI-assisted round were associated with automation bias, accounting for 45.5% of the total mistakes. The automation bias was found to affect clinicians of all levels of expertise. Using a logistic regression model, we identified an AI output zone with higher probability to generate misleading diagnoses. The proposed AI suppression strategy was estimated to decrease clinicians' automation bias by 41.7%.
CONCLUSION
Although AI improved clinicians' diagnostic performance, automation bias was a serious problem that should be addressed in clinical practice. The proposed AI suppression strategy is a practical method for decreasing automation bias.
Topics: Artificial Intelligence; Magnetic Resonance Imaging; Clinical Decision-Making; Humans; Anterior Cruciate Ligament Injuries; Diagnosis, Computer-Assisted
PubMed: 37561535
DOI: 10.1093/jamia/ocad118 -
The Journal of the Association of... Sep 2023Hyperglycemia occurring in pregnancy is a growing burden worldwide. It is now standard of care to screen all women during pregnancy, both to detect preexisting diabetes...
Hyperglycemia occurring in pregnancy is a growing burden worldwide. It is now standard of care to screen all women during pregnancy, both to detect preexisting diabetes as well as gestational diabetes mellitus (GDM). Traditionally, GDM was diagnosed at 24-28 weeks. However, with many international bodies recommending screening at first contact or booking, we are now diagnosing GDM earlier on in pregnancy. Based on the time of gestation at which it is diagnosed, GDM can be classified as conventional gestational diabetes mellitus (cGDM) or early gestational diabetes mellitus (eGDM). The cGDM is diagnosed between 24 and 28 weeks of gestation while eGDM is diagnosed in early pregnancy (<20 weeks). Till recently, there was little and conflicting evidence, on whether diagnosing and treating eGDM was beneficial or safe. The recent Treatment of BOoking Gestational diabetes Mellitus (ToBOGM) study, was a randomized control trial, showing clear benefits of diagnosing and treating eGDM. ToBOGM also showed that the best results were seen in those screened before 14 weeks of pregnancy and those in the higher band of glucose levels (FPG 95-109 mg/dL, 1-hour >191 mg/dL, and 2-hour glucose 162-199 mg/dL). In India, where the burden of hyperglycemia in pregnancy is high, the findings from the ToBOGM study further emphasize the need for screening for GDM at the time of first booking of the pregnancy followed by appropriate treatment for those detected to have eGDM. How to cite this article: Hannah W, Pradeepa R, Anjana RM, et al. Early Gestational Diabetes Mellitus: An Update. J Assoc Physicians India 2023;71(9):101-103.
Topics: Female; Humans; Pregnancy; Blood Glucose; Diabetes, Gestational; Early Diagnosis; Glucose Tolerance Test; India; Clinical Studies as Topic
PubMed: 38700309
DOI: 10.59556/japi.71.0351 -
Journal of Nuclear Medicine Technology Jun 2023Cardiac amyloidosis was thought to be rare, undiagnosable, and incurable. However, recently it has been discovered to be common, diagnosable, and treatable. This...
Cardiac amyloidosis was thought to be rare, undiagnosable, and incurable. However, recently it has been discovered to be common, diagnosable, and treatable. This knowledge has led to a resurgence in nuclear imaging with Tc-pyrophosphate-a scan once believed to be extinct-to identify cardiac amyloidosis, particularly in patients with heart failure but preserved ejection fraction. The renewed interest in Tc-pyrophosphate imaging has compelled technologists and physicians to reacquaint themselves with the procedure. Although Tc-pyrophosphate imaging is relatively simple, interpretation and diagnostic accuracy require an in-depth knowledge of amyloidosis etiology, clinical manifestations, disease progression, and treatment. Diagnosing cardiac amyloidosis is complicated because typical signs and symptoms are nonspecific and usually attributed to other cardiac disorders. In addition, physicians must be able to differentiate between monoclonal immunoglobulin light-chain amyloidosis (AL) and transthyretin amyloidosis (ATTR). Several clinical and noninvasive diagnostic imaging (echocardiography and cardiac MRI) red flags have been identified that suggest a patient may have cardiac amyloidosis. The intent of these red flags is to raise physician suspicion of cardiac amyloidosis and guide a series of steps (a diagnostic algorithm) for narrowing down and diagnosing the specific amyloid type. One element in the diagnostic algorithm is to identify monoclonal proteins indicative of AL. Monoclonal proteins are detected by serum or urine immunofixation electrophoresis and serum free light-chain assay. Another element is identifying and grading cardiac amyloid deposition using Tc-pyrophosphate imaging. When monoclonal proteins are present and the Tc-pyrophosphate scan is positive, the patient should be further evaluated for cardiac AL. The absence of monoclonal proteins and a positive Tc-pyrophosphate scan is diagnostic for cardiac ATTR. Patients with cardiac ATTR need to undergo genetic testing to differentiate between wild-type ATTR and variant ATTR. This article is the third in a 3-part series in this issue of the Part 1 reviewed amyloidosis etiology and outlined Tc-pyrophosphate study acquisition. Part 2 described Tc-pyrophosphate image quantification and protocol technical considerations. This article discusses scan interpretation along with cardiac amyloidosis diagnosis and treatment.
Topics: Humans; Diphosphates; Cardiomyopathies; Radiopharmaceuticals; Amyloid Neuropathies, Familial; Radionuclide Imaging
PubMed: 37268322
DOI: 10.2967/jnmt.123.265492 -
Journal of Neurology Sep 2022Numerous sonographic modalities and parameters have been used to diagnose carpal tunnel syndrome (CTS), with varying accuracy. Our umbrella review aimed to summarize the... (Review)
Review
BACKGROUND
Numerous sonographic modalities and parameters have been used to diagnose carpal tunnel syndrome (CTS), with varying accuracy. Our umbrella review aimed to summarize the evidence from systematic reviews and meta-analyses regarding the use of ultrasound imaging to diagnose CTS.
METHODS
Systematic reviews and meta-analyses meeting the inclusion criteria were searched in PubMed, Embase, Medline, Web of Science, and Cochrane databases from inception to March 2022. Critical appraisal, data extraction, and synthesis were performed in accordance with the criteria for conducting an umbrella review.
RESULTS
Sixteen reviews were included. Three reviews were classified as high quality, one as moderate, four as low, and eight as critically low. The cross-sectional area (CSA) of the median nerve at the carpal tunnel inlet demonstrated the best reliability and diagnostic accuracy among multiple parameters. A cutoff CSA value of 9-10.5 mm gave the highest diagnostic performance in the general population. The degree of CSA enlargement was correlated with CTS severity. Sonoelastography and Doppler ultrasound might provide additional insights into CTS evaluation as median nerve stiffness and vascularity at the wrist were increased in these patients.
CONCLUSIONS
Sonography is a reliable tool to diagnose CTS, with inlet CSA being the most robust parameter. Sonoelastography and Doppler ultrasound can serve as auxiliary tools to confirm CTS diagnoses. Further studies are needed to expand the use of sonography for diagnosing CTS, especially in the presence of concomitant neuromuscular disease(s).
Topics: Carpal Tunnel Syndrome; Humans; Median Nerve; Neural Conduction; Reproducibility of Results; Sensitivity and Specificity; Ultrasonography
PubMed: 35639198
DOI: 10.1007/s00415-022-11201-z -
Annals of Oncology : Official Journal... Sep 2021Clinical management of soft tissue sarcoma (STS) is particularly challenging. Here, we used digital pathology and deep learning (DL) for diagnosis and prognosis...
BACKGROUND
Clinical management of soft tissue sarcoma (STS) is particularly challenging. Here, we used digital pathology and deep learning (DL) for diagnosis and prognosis prediction of STS.
PATIENTS AND METHODS
Our retrospective, multicenter study included a total of 506 histopathological slides from 291 patients with STS. The Cancer Genome Atlas cohort (240 patients) served as training and validation set. A second, multicenter cohort (51 patients) served as an additional test set. The use of the DL model (DLM) as a clinical decision support system was evaluated by nine pathologists with different levels of expertise. For prognosis prediction, 139 slides from 85 patients with leiomyosarcoma (LMS) were used. Area under the receiver operating characteristic (AUROC) and accuracy served as main outcome measures.
RESULTS
The DLM achieved a mean AUROC of 0.97 (±0.01) and an accuracy of 79.9% (±6.1%) in diagnosing the five most common STS subtypes. The DLM significantly improved the accuracy of the pathologists from 46.3% (±15.5%) to 87.1% (±11.1%). Furthermore, they were significantly faster and more certain in their diagnosis. In LMS, the mean AUROC in predicting the disease-specific survival status was 0.91 (±0.1) and the accuracy was 88.9% (±9.9%). Cox regression showed the DLM's prediction to be a significant independent prognostic factor (P = 0.008, hazard ratio 5.5, 95% confidence interval 1.56-19.7) in these patients, outperforming other risk factors.
CONCLUSIONS
DL can be used to accurately diagnose frequent subtypes of STS from conventional histopathological slides. It might be used for prognosis prediction in LMS, the most prevalent STS subtype in our cohort. It can also help pathologists to make faster and more accurate diagnoses. This could substantially improve the clinical management of STS patients.
Topics: Deep Learning; Humans; Prognosis; Retrospective Studies; Sarcoma; Soft Tissue Neoplasms
PubMed: 34139273
DOI: 10.1016/j.annonc.2021.06.007 -
Journal of Magnetic Resonance Imaging :... Aug 2022The diagnosis of labral injury on MRI is time-consuming and potential for incorrect diagnoses. (Randomized Controlled Trial)
Randomized Controlled Trial
BACKGROUND
The diagnosis of labral injury on MRI is time-consuming and potential for incorrect diagnoses.
PURPOSE
To explore the feasibility of applying deep learning to diagnose and classify labral injuries with MRI.
STUDY TYPE
Retrospective.
POPULATION
A total of 1016 patients were divided into normal (n = 168, class 0) and abnormal labrum (n = 848) groups. The abnormal group consisted of n = 111 with class 1 (degeneration), n = 437 with class 2 (partial or complete tear), and n = 300 with unclassified injury. Patients were randomly divided into training, validation, and test cohort according to the ratio of 55%:15%:30%.
FIELD STRENGTH/SEQUENCE
Fat-saturation proton density-weighted fast spin-echo sequence at 3.0 T.
ASSESSMENT
Convolutional neural network-6 (CNN-6) was used to extract, discriminate, and detect oblique coronal (OCOR) and oblique sagittal (OSAG) images. Mask R-CNN was used for segmentation. LeNet-5 was used to diagnose and classify labral injuries. The weighting method combined the models of OCOR and OSAG. The output-input connection was used to correlate the whole diagnosis/classification system. Four radiologists performed subjective diagnoses to obtain the diagnosis results.
STATISTICAL TESTS
CNN-6 and LeNet-5 were evaluated by area under the receiver operating characteristic (ROC) curve and related parameters. The mean average precision (MAP) evaluated the Mask R-CNN. McNemar's test was used to compare the radiologists and models. A P value < 0.05 was considered statistically significant.
RESULTS
The area under the curve (AUC) of CNN-6 was 0.99 for extraction, discrimination, and detection. MAP values of Mask R-CNN for OCOR and OSAG image segmentation were 0.96 and 0.99. The accuracies of LeNet-5 in the diagnosis and classification were 0.94/0.94 (OCOR) and 0.92/0.91 (OSAG), respectively. The accuracy of the weighted models in the diagnosis and classification were 0.94 and 0.97, respectively. The accuracies of radiologists in the diagnosis and classification of labrum injuries ranged from 0.85 to 0.92 and 0.78 to 0.94, respectively.
DATA CONCLUSION
Deep learning can assist radiologists in diagnosing and classifying labrum injuries.
EVIDENCE LEVEL
3 TECHNICAL EFFICACY: Stage 2.
Topics: Deep Learning; Hip Joint; Humans; Magnetic Resonance Imaging; Neural Networks, Computer; Retrospective Studies
PubMed: 35081273
DOI: 10.1002/jmri.28069