Accuracy Rate Of Diagnosis Research Articles

Adamic–Adar Similarity Indexed Wald Boost Data Classification for Diabetic Disease Diagnosis with Big Data

Big data contains vast amounts of information that can be processed in the future, leading to improved prediction outcomes. In the realm of big healthcare data, analyzing and preventing hospital errors, along with disease prevention and cost savings, are crucial. Healthcare data analysts play a pivotal role in enhancing healthcare outcomes by gathering, integrating, and analyzing data from diverse sources. Disease diagnosis involves identifying the disease or condition underlying a person's symptoms and signs. Ensemble learning methods, utilized in science and technology, have introduced various classification and clustering techniques to achieve more accurate and time-efficient disease diagnosis. To address these challenges, we introduce the Adamic–Adar Similarity Indexed Wald Boost Data Classification (AASIWBDC) Technique. This technique conducts feature selection and data classification to enhance the efficiency of diabetic disease diagnosis. It utilizes the Adamic–Adar Similarity Index to gauge the similarity between features and their objectives. Leveraging selected features, the AASIWBDC Technique implements the Wald Boost Classification Process to categorize patient data into normal and abnormal groups with greater accuracy. As a result, it achieves effective diabetic disease diagnosis in an efficient manner. We evaluate the performance of the AASIWBDC Technique in terms of diabetic disease diagnosis accuracy, diagnosis time, and error rate using the Diabetes 130-US hospitals dataset from 1999-2008. Experimental results illustrate that the AASIWBDC Technique enhances diabetic disease diagnosis accuracy, reduces diagnosis time, and lowers error rates compared to conventional methods.

Exploring $\<i>beta$</i>-Basic Rough Sets and Their Applications in Medicine

Advancements in the rough set theory of Pawlak have opened new avenues for enhancing decision-making processes, particularly in identifying disease risk factors in medical diagnoses. While traditional rough set methodologies have provided a solid foundation, there is a continuous need for improvements to increase accuracy and reliability. This study introduces mathematical techniques grounded in basic rough sets, incorporating $\beta$-open concepts to enhance precision. We present nearly basic rough sets and $\beta$-basic-approximations ($\beta _b$-approximations), examining their core properties and interrelationships. Our findings reveal that these novel constructs offer superior accuracy compared to traditional methods. Both theoretical analysis and practical examples support this, with our approach achieving a 100% accuracy rate in the medical diagnosis of COVID-19. This significant improvement highlights the potential of the methods of us to outperform existing ones in terms of precision and reliability. The introduction of $\beta _b$-approximations represents a significant advancement in rough set theory, offering enhanced accuracy in decision-making applications. Our results indicate that these methods can substantially outperform traditional techniques, especially in critical areas such as medical diagnosis. Additionally, we provide a mathematical algorithm suitable for implementation in programming languages, facilitating future research and applications across various theoretical and applied fields. This work lays the groundwork for further exploration and utilization of advanced rough set methodologies in diverse domains.

Failure analysis of photovoltaic strings by constructing a digital multi-twin integrating theory, features, and vision

Timely and accurate failure analysis of photovoltaic (PV) systems is crucial forensuring the stable operation of power grids. However, existing failure analysis and diagnosis algorithms based on deep neural networks excessively rely on high-quality failure state data collected by sensors. This is extremely difficult to achieve in real photovoltaic power plants that are commonly equipped with self-protection mechanisms. To address this issue, we propose a Digital Multi-Twin integrating Theory, Features, and Vision (TFV-DMT) for failure analysis of PV strings in PV systems. This method first constructs theoretical simulation twins, feature twins, and visual twins based on the concept of digital twins, specifically tailored for actual PV systems, and designs a multi-twin collaborative model for model updating and failure diagnosis. Secondly, to better construct the visual twin, we introduce a Two-Dimensional Gram Angle Field Transformation Algorithm (TDGAF) to achieve targeted two-dimensional mapping of PV feature data, facilitating a more direct expression of failure characteristics. Furthermore, by constructing a Swish-activated Deep Convolutional Generative Adversarial Network (SDCGAN) to achieve balanced augmentation of mapping data, the model bias of theoretical simulation twins can be reduced. Finally, we propose a Swin-LT network that incorporates a Lightweight Dual-Channel Attention Module (LDAM) to better analyze the features of the visual twin, enabling more precise fault diagnosis. The algorithm has been validated on a real 250 kW grid-connected PV system, with results indicating that the proposed digital twin model is effective, achieving a diagnosis accuracy rate of 98.8 % for string failures.

A Cross Spatio-Temporal Pathology-based Lung Nodule Dataset

Recently, intelligent analysis of lung nodules with the assistant of computer aided diagnosis (CAD) techniques can improve the accuracy rate of lung cancer diagnosis. However, existing CAD systems and pulmonary datasets mainly focus on Computed Tomography (CT) images from one single period, while ignoring the cross spatio-temporal features associated with the progression of nodules contained in imaging data from various captured periods of lung cancer. If the evolution patterns of nodules across various periods in the patients’ CT sequences can be explored, it will play a crucial role in guiding the precise screening identification of lung cancer. Therefore, a cross spatio-temporal lung nodule dataset with pathological information for nodule identification and diagnosis is constructed, which contains 317 CT sequences and 2,295 annotated nodules from 109 patients. This comprehensive database is intended to drive research in the field of CAD towards more practical and robust methods, and also contribute to the further exploration of precision medicine related field. To ensure patient confidentiality, we have removed sensitive information from the dataset.

Meropenem Usage Assessment amid the Antibiotic Resistance Crisis: A Comprehensive Analysis in a Tertiary Care Hospital in Pakistan

BACKGROUND: With antibiotic resistance posing a growing threat to global health, the prudent use of antibiotics like meropenem is imperative. However, empirical prescribing practices and inadequate adherence to guidelines contribute to challenges in meropenem utilization. This study aims to comprehensively assess prescribing patterns, adherence to guidelines, and patient education practices in a tertiary care hospital in Pakistan. METHODS: A cross-sectional study was conducted over six months, enrolling 100 patients. Data collection included variables such as age, gender, hospital stay duration, indication for meropenem prescription, dosage regimen, basis of prescription, treatment duration, and patient education. Statistical analysis was performed using IBM SPSS version 26. RESULTS: Empirical prescribing was common, with an initial diagnosis accuracy rate of 64%. Disparities were noted in aligning culture sensitivity with meropenem use, with only 36% of cases following culture results. Regarding treatment duration, an alarming 86% of cases had incorrect durations. Comparative analyses highlighted areas for prescription protocol and clinical outcome improvement. For instance, 96% of cases had the correct initial meropenem dosage. Despite meticulous monitoring, deficiencies persisted in patient education and antibiotic stewardship. CONCLUSION: The study underscores the urgent need for standardized guidelines, enhanced diagnostics, and educational initiatives to mitigate antibiotic resistance emergence. Addressing these challenges is crucial for safeguarding antibiotic efficacy and public health.

296. CLINICAL T1B-SM2-3N0M0 ESOPHAGEAL SQUAMOUS CELL CARCINOMA

Abstract Background With advancements in endoscopic techniques, safer and more reliable endoscopic resection of submucosal invasive lesions has become feasible. The evaluation of treatment outcomes for superficial esophageal carcinoma has typically been predicated on the depth of pathological diagnosis; however, there have been limited studies based on preoperative diagnosis. Given that treatment decisions in clinical practice are primarily guided by preoperative diagnosis, there is a heightened emphasis on studies grounded in preoperative assessments. This study aims to analyze the accuracy of preoperative diagnosis of T1b-SM2-3 N0M0, evaluate the accuracy of treatment selection and depth diagnosis, and assess long-term outcomes based on these determinations. Methods Thirty-eight patients diagnosed with T1b-SM2-3 N0M0 between April 2010 and December 2020 were included in the study. Depth diagnosis was determined through endoscopic evaluation utilizing white light, NBI, NBI magnification plus EUS, with lymph node metastasis diagnosis performed via CT imaging. Treatment decisions were made following patient consent, and long-term prognosis was assessed for each treatment modality. Results Initial treatment involved ESD in 14 patients, with an additional 5 patients undergoing additional treatment (ESD + AD) based on histological evaluation (surgery: 1, CRT: 4). Surgery or neoadjuvant chemotherapy (NAC) followed by surgery was performed in 15 patients, with CRT administered in 7. Among the 22 patients who did not receive NAC and whose histologic depth was evaluable, the accuracy rate of depth diagnosis was 64%, primarily attributable to overdiagnosis. In the 14 patients who underwent ESD excluding piecemeal resection, the negative rate of vertical margins was 93%. Five-year overall survival rates were as follows: ESD: 64.8%, ESD+AD: 75%, surgery: 86.2%, and CRT: 45.7%, with no statistically significant differences observed. The majority of deaths (83%) were attributed to other diseases or cancers, with only 2 deaths attributed to the primary disease. Conclusion ESD or surgery emerged as the preferred treatment modalities in the majority of cases, with relatively favorable long-term prognoses. Treatment decisions were influenced by comorbidities and other factors, potentially impacting long-term outcomes.

Mechanical fault diagnosis of high voltage circuit breaker using multimodal data fusion.

A high voltage circuit breaker (HVCB) plays a crucial role in current smart power system. However, the current research on HVCB mainly focuses on the convenience and efficiency of mechanical structures, ignoring the aspect of their fault diagnosis. It is very important to ensure the circuit breaker conducts in a normal state. According to real statistics when HVCB works, most defects and faults in high voltage circuit breakers is caused by mechanical faults such as contact fault, mechanism seizure, bolt loosening, spring fatigue and so on. In this study, vibration sensors were placed at four different locations in the HVCB system to detect four common mechanical faults using vibration signal. In our approach, a convolutional attention network (CANet) was introduced to extract features and determine which mechanical faults occur within a fixed period of time. The results indicate that the mechanical fault diagnosis accuracy rate is up to 94.2%, surpassing traditional methods that rely solely on vibration signals from a single location.

Integrated prenatal and postnatal management for neonates with transposition of the great arteries: thirteen-year experience at a single center

BackgroundTransposition of the great arteries (TGA) is the most common cyanotic congenital heart defect in neonates but with low prenatal detection rate. This study sought to review the prenatal diagnosis, associated abnormalities, and mid-term postnatal outcomes of fetuses with TGA and investigate the integrated prenatal and postnatal management for TGA neonates.MethodsA total of 134 infants prenatally diagnosed with TGA in Guangdong Provincial People’s Hospital, China, from January 2009 to December 2022 were included in the study. The prenatal ultrasound data and neonatal records were reviewed to assess the accuracy of prenatal diagnosis. Univariate and multivariate logistic and Cox analyses were used to identify risk factors associated with prognosis in such individuals.ResultsThe population originated from 40 cities in 10 provinces in China, with integrated antenatal and postnatal management rate reaching 94.0% (126/134) and a high accuracy rate (99.3%) of prenatal primary diagnosis. The median period of follow-up was 1.6 [interquartile range (IQR) 0.1–4.3] years. There were 3 (2.2%) postnatal deaths, 118 (88.1%) patients undergoing arterial switch operation (ASO), 3 (2.2%) undergoing Rastelli operations and 5 (3.7%) doing stage operations. Of 118 patients receiving ASO, the major morbidity occurred in 64 patients (54.2%), and right ventricular outflow tract obstruction (RVOTO) in 31 (26.3%). In the multivariate logistic analysis, gestational ages at birth (OR = 0.953, 95% CI 0.910–0.991; p = 0.025) and cardiopulmonary bypass (CPB) time (OR = 1.010, 95% CI 1.000–1.030; p = 0.038) were identified as independent risk factors associated with major morbidity. In the Cox multivariate analysis, aortic cross-clamping time (HR = 1.030, 95% CI 1.000–1.050; p = 0.017) was identified as independent risk factor associated with RVOTO.ConclusionEarlier gestational ages at birth and longer CPB time are significantly associated with increased morbidity. Integrated prenatal and postnatal management is recommended for patients with prenatal diagnosis of TGA.

The effect of health literacy on patient compliance in patients to whom prostate biopsies were recommended

BackgroundTransrectal ultrasound-guided prostate biopsy (TRUS-Bx) is the gold standard diagnostic method for prostate cancer. In people with low health literacy, accurate and early diagnosis rates decrease, making it difficult to maintain health and compliance with treatment. In our study, we investigated how health literacy and sociocultural parameters affected compliance and awareness in patients with suspected prostate cancer, for whom TRUS-Bx was planned.MethodsIn the study, 98 male patients aged 50–80 years, recommended for TRUS-Bx, were included in our study. The data including age, prostate-specific antigen, prostate volume, digital rectal examination findings, education leveland area of residence of the patients included in the study were recorded. Health Literacy Survey-Turkey- Questionnaire 47 and Turkish Health Literacy Scale-32 forms were completed by the patients who agreed to participate in the study, and their scores were recorded. Patients scheduled for TRUS-Bx were divided into two groups: those who attended their appointments and underwent the biopsy, and those who did not attend their scheduled appointments. The effect of health literacy and other parameters on the TRUS-Bx requirement was examined between the two groups. Furthermore, 52 patients who underwent TRUS-Bx were divided into two groups as malignancy (malignant) detected and not-detected (benign) patients according to the pathology results, and the parameters were analyzed separately for these groups.ResultsThe education level of the patients who underwent the TRUS-Bx procedure was found to be statistically higher (p = 0.026). Health Literacy Survey-Turkey- Questionnaire 47 and Turkish Health Literacy Scale-32 scores were statistically significantly higher in the TRUS-Bx group (p = 0.001, p < 0.001, respectively). In the logistic regression analysis, education level, Health Literacy Survey-Turkey- Questionnaire 47 and Turkish Health Literacy Scale-32 were found to be important predictors for awareness of the requirement for TRUS-Bx.ConclusionThe study’s findings indicate that patients with higher health literacy and education levels were more likely to receive an early diagnosis and promptly proceed with the recommended TRUS-Bx after visiting a urologist.

Fault Diagnosis Method of Special Vehicle Bearing Based on Multi-Scale Feature Fusion and Transfer Adversarial Learning.

To address the issues of inadequate feature extraction for rolling bearings, inaccurate fault diagnosis, and overfitting in complex operating conditions, this paper proposes a rolling bearing diagnosis method based on multi-scale feature fusion and transfer adversarial learning. Firstly, a multi-scale convolutional fusion layer is designed to effectively extract fault features from the original vibration signals at multiple time scales. Through a feature encoding fusion module based on the multi-head attention mechanism, feature fusion extraction is performed, which can model long-distance contextual information and significantly improve diagnostic accuracy and anti-noise capability. Secondly, based on the domain adaptation (DA) cross-domain feature adversarial learning strategy of transfer learning methods, the extraction of optimal domain-invariant features is achieved by reducing the gap in data distribution between the target domain and the source domain, addressing the call for research on fault diagnosis across operating conditions, equipment, and virtual-real migrations. Finally, experiments were conducted to verify and optimize the effectiveness of the feature extraction and fusion network. A public bearing dataset was used as the source domain data, and special vehicle bearing data were selected as the target domain data for comparative experiments on the effect of network transfer learning. The experimental results demonstrate that the proposed method exhibits an exceptional performance in cross-domain and variable load environments. In multiple bearing cross-domain transfer learning tasks, the method achieves an average migration fault diagnosis accuracy rate of up to 98.65%. When compared with existing methods, the proposed method significantly enhances the ability of data feature extraction, thereby achieving a more robust diagnostic performance.

Acil servis tanıları ile paramediklerin ilk değerlendirme tanılarının karşılaştırılması.

This study aims to evaluate the accuracy and quality of prehospital assessments and preliminary diagnoses made by Emergency Medical Services (EMS) providers compared to the final diagnoses given by Emergency Department physicians in a metropolitan area. This retrospective observational study utilized records from the Yenimahalle EMS Command Center in Ankara, Türkiye, from January 1, 2021, to December 31, 2022. Data were recorded as cases rather than individual patients, with repeated EMS admissions counted separately. Cases were categorized by EMS call time, reasons for EMS requests, age, gender, nationality, and weekday of hospital arrival to assess socioeconomic impacts and congestion patterns. The study included 2.528 pediatric cases, excluding patients aged 18 and older, those who refused EMS transfer, and cases resolved at the scene. Data analysis was conducted using IBM SPSS 27.0, with statistical significance set at p<0.05. The study included 2.528 cases. The data revealed that EMS providers had an average of 9.9±4.7 years of experience. In 1.839 cases (72.7%), the EMS provider was female, and in 689 cases (27.3%), the EMS provider was male. Patients had an average age of 9.2±5.8 years, with 1.173 (46.4%) being female and 1.355 (53.6%) being male. Preliminary diagnosis accuracy was higher in cases involving younger and male patients. Additionally, a lower preliminary diagnosis accuracy rate was observed during office hours (08: 00-15: 59) compared to non-office hours (16: 00-23: 59). The majority of EMS calls were for medical reasons (1,783 cases, 70.5%), followed by trauma-related calls (745 cases, 29.5%). This study highlights the need for improved on-field training for EMS providers to enhance the accuracy and quality of prehospital assessments and preliminary diagnoses. The findings suggest that younger and male patients have higher preliminary diagnosis accuracy rates, and there is a noticeable decrease in accuracy during office hours, indicating potential areas for targeted training and protocol adjustments.

RAPID: A rabbit pregnancy diagnosis device based on matrix optical sensing

Effective early pregnancy diagnosis is crucial for commercial rabbit breeding. Early pregnancy diagnosis enables the implementation of staged feeding for pregnant does, effectively preventing excessive weight gain and reducing the high mortality rates of kits during the birthing stage. This not only enhances production efficiency but also ensures the health and well-being of the breeding rabbits. The study introduces a method and device, the Rabbit Pregnancy Identification Device (RAPID), for detecting rabbit pregnancies using matrix optical sensing. RAPID comprises eight sensor modules and a central host unit. Each sensor module is equipped with three LEDs emitting light at wavelengths of 660 nm, 850 nm, and 940 nm, along with two photodiodes for data collection. A mobile application was developed to enable flexible control of the device. Signal-to-noise ratio tests were conducted to evaluate the stability of data collection by the device across varying light intensities. The experimental results reveal a direct correlation between light intensity levels and the signal-to-noise ratio of collected data. Notably, under a light intensity level of 4, RAPID achieves a signal-to-noise ratio ranging from 42 to 45 dB, satisfying the necessary criteria for data collection. Different classification models were trained using sample data from 216 does across various batches, and their generalization capabilities were evaluated. The experimental findings indicate that the optimal time for RAPID to diagnose the pregnancy status of does is on the 14th day after insemination, achieving an accuracy of 86.63 % and a recall of 80.49 %. Moreover, the model exhibits a degree of generalization, achieving an accuracy of 78.36 % when classifying another batch of sample data. RAPID achieves an accuracy of 97.25 % for pregnancy diagnosis of older does, which is 7.44 % higher than that of younger does; the accuracy rate for pregnancy diagnosis of does with sparse hair is 86.92 %, which is 4.78 % higher than that of does with dense hair. By comparing the effectiveness of using data from 8 sensor modules and data from a single sensor module for pregnancy diagnosis of different batches of does, it was found that the former exhibits more stable generalization capability in doe pregnancy detection.

Ultrasound-Based Multi-Planar Bilateral Comparisons as a Diagnostic and Treatment-Definition Method for Unilateral Peripheral Nerve Entrapment.

The primary goal was to determine the performance of the cross-section area swelling rate (CSASR) for diagnostic and therapeutic purposes based on the reference standard of electrodiagnosis examination (EDX) in this diagnostic test study. First, patients with symptoms like unilateral carpal tunnel syndrome (CTS), cubital tunnel syndrome (CuTS), and radial nerve compression (RNC) underwent EDX and ultrasound examination. Second, patients with positive ultrasound were calculated for the CSASR of diseased nerve. Based on previously established CSASR criteria, each patient was categorized as having or not having peripheral nerve entrapment, and for those meeting diagnostic criteria, non-surgical or surgical treatment was recommended. Then, the sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and accuracy rate (ACC) of ultrasound diagnosis and therapeutic decision-making were calculated based on the reference standard of EDX that had been historically used in the practice. The total sensitivity, specificity, PPV, NPV, and ACC of ultrasound diagnosis are respectively 93.4, 85.2, 94.7, 82.1, and 91.3%. Which of therapeutic decision-making by ultrasound are, respectively, 83.3, 52.2, 78.4, 60.0, and 73.2%. The sensitivity and Youden's index of CSASR diagnostic threshold for CuTS is higher than other ultrasound methods. The CSASR diagnostic threshold for CuTS has a potential diagnostic role, but the current date is still not enough to support the potential diagnostic role for CTS or RNS. There is insufficient evidence to suggest that CSASR for CuTS can be used in isolation for diagnosis. Additional research is needed to confirm the diagnostic role of CSASR. The current results suggest that this ultrasound examination method is not suitable for therapeutic decision-making.

Multiplane reconstruction modifies the diagnostic performance of CT angiography in carotid webs

IntroductionCarotid Web (CaW) represents an overlooked stroke etiology and has been associated with high recurrence rates and to be amenable to stenting. We evaluated the diagnostic performance of different computed tomography angiography (CTA) projections in CaW. MethodsConsecutive patients <65 years-old with symptomatic CaW (n=31), carotid atherosclerosis (n=27), or normal carotids (n=49) diagnosed with a thin-cut CTA were included. Deidentified CTAs were independently reviewed by three readers, who recorded the diagnosis and level of certainty after evaluating the axial plane alone, after adding sagittal/coronal maximum intensity projection (MIP), then after oblique MPR reformats. ResultsThere were 93 total CaW, 81 atherosclerosis, and 147 normal carotid reads. With CTA axial projection alone, less CaW cases (44.1 %) were appropriately diagnosed as compared to atherosclerosis (87.7 %; p<0.001) and normal carotid (83 %; p<0.001) cases. Sagittal/coronal MIPS increased the rate of accurate CaW diagnosis (44.1–76.3 %; p<0.001). Inter-rater agreement in CaW detection increased from k= 0.46 (0.35–0.57) using axial to k= 0.80 (0.69–0.91) with sagittal/coronal planes. The axial projection alone had lower sensitivity (44 % vs. 76 %) but similar specificity (95 % vs. 96 %) in CaW detection compared to axial+ sagittal/coronal MIPS. The accuracy in detecting atherosclerosis or normal carotids did not increase after adding sagittal/coronal MIPS and oblique MPRs. The certainty level for CaW diagnosis was lower when compared to atherosclerosis and normal carotids using axial alone (3.0 [3.0–4.0] vs. 4.0 [3.0–5.0]; p<0.001 and 4.0 [3.0–5.0]; p<0.001) as well as after adding sagittal/coronal MIPS (4.0 [3.0–5.0] vs. 5.0[4.0–5.0]; p=0.01 and 4.0 [4.0–5.0]; p<0.001). ConclusionCTA axial plane alone was insufficient for CaW detection. CTA sagittal/coronal MIP reconstructions as well as oblique MPR reformats enhanced the accuracy and confidence related to CaW diagnosis.

Causes of missed MRI diagnosis of radiotherapy-induced temporal lobe injury in nasopharyngeal carcinoma.

Radiotherapy is the primary treatment for nasopharyngeal carcinoma, but it frequently leads to radiotherapy-induced temporal lobe injury (RTLI). Magnetic resonance imaging (MRI) is the main diagnostic method for RTLI after radiotherapy for nasopharyngeal carcinoma, but it is prone to missed diagnoses. This study aims to investigate the causes of missed diagnoses of RTLI in nasopharyngeal carcinoma patients undergoing MRI after radiotherapy. Clinical and MRI data from nasopharyngeal carcinoma patients diagnosed and treated with radiotherapy at Xiangya Hospital of Central South University, from January 2010 to April 2021, were collected. Two radiologists reviewed all head and neck MRIs (including nasopharyngeal and brain MRIs) before and after radiotherapy of identify cases of late delayed response-type RTLI for the first time. If the original diagnosis of the initial RTLI in nasopharyngeal carcinoma patients did not report temporal lobe lesions, it was defined as a missed diagnosis. The first diagnosis of RTLI cases was divided into a missed diagnosis group and a non-missed diagnosis group. Clinical and imaging data were compared between the 2 groups, and multivariate logistic regression analysis was used to identify independent risk factors for MRI missed diagnoses of initial RTLI. A total of 187 nasopharyngeal carcinoma with post-radiotherapy RTLI were included. The original diagnostic reports missed 120 cases and accurately diagnosed 67 cases, with an initial RTLI diagnosis accuracy rate of 35.8% and a missed diagnosis rate of 64.2%. There were statistically significant differences between the missed diagnosis group and the non-missed diagnosis group in terms of lesion size, location, presence of contralateral temporal lobe lesions, white matter high signal, cystic degeneration, hemorrhage, fluid attenuated inversion recovery (FLAIR), and examination site (all P<0.05). Multivariate logistic regression analysis showed that lesions ≤25 mm, non-enhancing lesions, lesions without cystic degeneration or hemorrhage, lesions located only in the medial temporal lobe, and MRI examination only of the nasopharynx were independent risk factors for missed MRI diagnosis of initial RTLI (all P<0.05). The missed diagnosis of initial RTLI on MRI is mainly related to lesion size and location, imaging characteristics, and MRI examination site.

Clinico-pathological study of esophageal mucoepidermoid carcinoma: a 10-year survival from a single center

BackgroundMucoepidermoid Carcinoma of the Esophagus (MECE) is a relatively rare tumor type, with most of the current data derived from case reports or small sample studies. This retrospective study reports on the 10-year survival data and detailed clinicopathological characteristics of 48 patients with esophageal MEC.MethodsData were collected from 48 patients who underwent curative surgery for esophageal MEC at the Fourth Hospital of Hebei Medical University between January 1, 2004, and December 31, 2020. These were compared with contemporaneous cases of Esophageal Squamous Cell Carcinoma (ESCC) and Esophageal Adenocarcinoma (EAC). Using the Kaplan-Meier method and multivariate Cox regression analysis, we investigated the clinicopathological factors affecting the survival of patients with MEC.ResultsThe incidence of MECE was predominantly higher in males, with a male-to-female ratio of approximately 7:1. The mid-thoracic segment emerged as the most common site of occurrence. A mere 6.3% of cases were correctly diagnosed preoperatively. The lymph node metastasis rate stood at 35.4%. The overall 1-year, 3-year, 5-year, and 10-year survival rates for all patients were 85.4%, 52.1%, 37.0%, and 31.0%, respectively. Post 1:1 propensity score matching, no significant statistical difference was observed in the Overall Survival (OS) between MEC patients and those with Esophageal Squamous Cell Carcinoma (ESCC) and Esophageal Adenocarcinoma (EAC) (P = 0.119, P = 0.669). Univariate analysis indicated that T staging and N staging were the primary factors influencing the prognosis of esophageal MEC.ConclusionsMECE occurs more frequently in males than females, with the mid-thoracic segment being the most common site of occurrence. The rate of accurate preoperative endoscopic diagnosis is low. The characteristic of having a short lesion length yet exhibiting significant extramural invasion may be a crucial clinicopathological feature of MECE. The OS of patients with MEC does not appear to significantly differ from those with esophageal squamous carcinoma and adenocarcinoma.

AI-MARRVEL - A Knowledge-Driven AI System for Diagnosing Mendelian Disorders.

Diagnosing genetic disorders requires extensive manual curation and interpretation of candidate variants, a labor-intensive task even for trained geneticists. Although artificial intelligence (AI) shows promise in aiding these diagnoses, existing AI tools have only achieved moderate success for primary diagnosis. AI-MARRVEL (AIM) uses a random-forest machine-learning classifier trained on over 3.5 million variants from thousands of diagnosed cases. AIM additionally incorporates expert-engineered features into training to recapitulate the intricate decision-making processes in molecular diagnosis. The online version of AIM is available at https://ai.marrvel.org. To evaluate AIM, we benchmarked it with diagnosed patients from three independent cohorts. AIM improved the rate of accurate genetic diagnosis, doubling the number of solved cases as compared with benchmarked methods, across three distinct real-world cohorts. To better identify diagnosable cases from the unsolved pools accumulated over time, we designed a confidence metric on which AIM achieved a precision rate of 98% and identified 57% of diagnosable cases out of a collection of 871 cases. Furthermore, AIM's performance improved after being fine-tuned for targeted settings including recessive disorders and trio analysis. Finally, AIM demonstrated potential for novel disease gene discovery by correctly predicting two newly reported disease genes from the Undiagnosed Diseases Network. AIM achieved superior accuracy compared with existing methods for genetic diagnosis. We anticipate that this tool may aid in primary diagnosis, reanalysis of unsolved cases, and the discovery of novel disease genes. (Funded by the NIH Common Fund and others.).

Detailed Superiority of the CAD EYE Artificial Intelligence System over Endoscopists for Lesion Detection and Characterization Using Unique Movie Sets.

Detailed superiority of CAD EYE (Fujifilm, Tokyo, Japan), an artificial intelligence for polyp detection/diagnosis, compared to endoscopists is not well examined. We examined endoscopist's ability using movie sets of colorectal lesions which were detected and diagnosed by CAD EYE accurately. Consecutive lesions of ≤10 mm were examined live by CAD EYE from March-June 2022 in our institution. Short unique movie sets of each lesion with and without CAD EYE were recorded simultaneously using two recorders for detection under white light imaging (WLI) and linked color imaging (LCI) and diagnosis under blue laser/light imaging (BLI). Excluding inappropriate movies, 100 lesions detected and diagnosed with CAD EYE accurately were evaluated. Movies without CAD EYE were evaluated first by three trainees and three experts. Subsequently, movies with CAD EYE were examined. The rates of accurate detection and diagnosis were evaluated for both movie sets. Among 100 lesions (mean size: 4.7±2.6 mm; 67 neoplastic/33 hyperplastic), mean accurate detection rates of movies without or with CAD EYE were 78.7%/96.7% under WLI (p<0.01) and 91.3%/97.3% under LCI (p<0.01) for trainees and 85.3%/99.0% under WLI (p<0.01) and 92.6%/99.3% under LCI (p<0.01) for experts. Mean accurate diagnosis rates of movies without or with CAD EYE for BLI were 85.3%/100% for trainees (p<0.01) and 92.3%/100% for experts (p<0.01), respectively. The significant risk factors of not-detected lesions for trainees were right-sided, hyperplastic, not-reddish, in the corner, halation, and inadequate bowel preparation. Unique movie sets with and without CAD EYE could suggest it's efficacy for lesion detection/diagnosis.

Diagnosis and surgical treatment of high-risk anomalous aortic origin of coronary artery

Objective: To analyze the diagnosis and surgical treatment of high-risk anomalous aortic origin of coronary artery (AAOCA). Methods: This is a retrospective case series study. From January 2016 to July 2023, 24 cases of high-risk AAOCA underwent surgical treatment in Department of Cardiac Surgery, Guangdong Provincial People's Hospital. There were 18 males and 6 females, operatively aged (M (IQR)) 13 (26) years (range: 0.3 to 57.0 years). They were confirmed by cardiac ultrasound and cardiac CT, all of which had anomalous coronary running between the aorta and the pulmonary artery. There were 15 cases of the right coronary artery from the left aortic sinus of Valsalva, 6 cases of left coronary artery from the right aortic sinus of Valsalva, 3 cases of the sigle coronary artery. Only 3 patients had no obvious related symptoms (2 cases were complicated with a positive exercise stress test and 1 case with other intracardiac malformations), 21 cases had a history of chest tightness, chest pain, or syncope after exercise. Three patients suffered syncope after exercise and underwent cardiopulmonary resuscitation (2 cases were treated with an extracorporeal membrane oxygenerator (ECMO)). The gap from the first symptom to the diagnosis was 4.0 (11.5) months (range: 0.2 to 84.0 months). The detection rate of coronary artery abnormalities suggested by the first cardiac ultrasound was only 37.5% (9/24). Seven patients were complicated with other cardiac diseases (4 cases with congenital heart defects, 2 cases with coronary atherosclerotic heart disease, 1 case with mitral valve disease). Results: All 24 patients underwent surgical treatment (23 cases underwent abnormal coronary artery unroofing, 1 case underwent coronary artery bypass grafting), and 5 patients underwent other intracardiac malformation correction at the same time. There were no death or surgery related complications in the hospital for 30 days after the operation. A patient with preoperative extracorporeal cardiopulmonary resuscitation was continuously assisted by ECMO after emergency AAOCA correction and had complications such as limb ischemia necrosis and renal dysfunction after the operation. During the follow-up of 2.2 (3.3) years (range: 1 month to 7.2 years), one patient who previously underwent percutaneous transluminal coronary angioplasty with a stent implant experienced significant postoperative symptomatic relief, and the other discharged patients had no related symptoms. Conclusions: The accurate rate of initial diagnosis for high-risk AAOCA is still low, but the risk of cardiovascular accidents is high. For sports-related chest pain and other symptoms, more attention should be paid to the detection of AAOCA, especially for adolescents. Exercise stress testing can be helpful in evaluating the cardiovascular risk of asymptomatic AAOCA. Instant surgical treatment can achieve satisfactory curative effects.

Diagnostic capabilities of ChatGPT in ophthalmology.

The purpose of this study is to assess the diagnostic accuracy of ChatGPT in the field of ophthalmology. This is a retrospective cohort study conducted in one academic tertiary medical center. We reviewed data of patients admitted to the ophthalmology department from 06/2022 to 01/2023. We then created two clinical cases for each patient. The first case is according to the medical history alone (Hx). The second case includes an addition of the clinical examination (Hx and Ex). For each case, we asked for the three most likely diagnoses from ChatGPT, residents, and attendings. Then, we compared the accuracy rates (at least one correct diagnosis) of all groups. Additionally, we evaluated the total duration for completing the assignment between the groups. ChatGPT, residents, and attendings evaluated 126 cases from 63 patients (history only or history and exam findings for each patient). ChatGPT achieved a significantly lower accurate diagnosis rate (54%) in the Hx, as compared to the residents (75%; p < 0.01) and attendings (71%; p < 0.01). After adding the clinical examination findings, the diagnosis rate of ChatGPT was 68%, whereas for the residents and the attendings, it increased to 94% (p < 0.01) and 86% (p < 0.01), respectively. ChatGPT was 4 to 5 times faster than the attendings and residents. ChatGPT showed low diagnostic rates in ophthalmology cases compared to residents and attendings based on patient history alone or with additional clinical examination findings. However, ChatGPT completed the task faster than the physicians.