Manual Reading Research Articles

Cognitive Query System Using Generative AI

Abstract: The Cognitive Query System using Generative AI is a cutting-edge tool designed to transform the way we retrieve and analyse data from a wide range of sources, including text, images, and documents. Powered by the Google Gemini API and deployed through Streamlit, this system allows users to easily ask questions, process images, and explore document contents via an intuitive, interactive interface. The system comprises three core modules: the Question-Answering Module, which uses advanced natural language processing (NLP) techniques to provide contextually accurate, conversational responses to user queries, facilitating seamless, real-time interactions. The Image Processing and Querying Module enables users to upload images and ask questions related to their content, leveraging computer vision algorithms and AI to interpret and analyse visual data, making it easier to extract valuable insights. The Document Exploration Module supports various formats, including PDFs, Word documents, and spreadsheets, allowing users to quickly ask questions and navigate through sections without manual reading. Deployed online via Streamlit, the Cognitive Query System offers a smooth, real-time experience that does not require installation, making it ideal for remote and collaborative work environments. This innovative solution is designed to streamline workflows and effective outputs in the model.

A Review on the Application of Automatic Text Summarization and Its Bias Analysis

Abstract. In the era of information explosion, the Internet produces a large number of text documents daily, providing rich information but also posing a challenge: how to swiftly extract key information. Traditional manual reading is time-consuming and inadequate for handling vast data. Thus, automatic text summarization technology emerges as a crucial solution. This paper reviews the application and deviation analysis of this technology across various fields, focusing on addressing shortcomings of traditional methods, such as initial cluster center selection and redundancy. An automatic text summarization method based on an improved TextRank algorithm and K-Means clustering is introduced. Existing methods often struggle with inaccurate initial clustering center selection and high summary redundancy, especially with long texts, resulting in summaries that fail to reflect core content accurately. Furthermore, the widespread use of pre-trained language models introduces potential biases that can propagate to downstream tasks, affecting summary accuracy and impartiality. To address these issues, this paper proposes an innovative automatic text summarization method that optimizes initial clustering center selection and clustering refinement strategies to enhance summary accuracy and readability. Additionally, it discusses name-nationality bias in pre-trained language models and its propagation in text summary tasks, offering a theoretical foundation and practical guidance for developing a more just and reliable Natural Language Processing (NLP) system.

Performance of a Full-Coverage Cervical Cancer Screening Program Using on an Artificial Intelligence- and Cloud-Based Diagnostic System: Observational Study of an Ultralarge Population.

The World Health Organization has set a global strategy to eliminate cervical cancer, emphasizing the need for cervical cancer screening coverage to reach 70%. In response, China has developed an action plan to accelerate the elimination of cervical cancer, with Hubei province implementing China's first provincial full-coverage screening program using an artificial intelligence (AI) and cloud-based diagnostic system. This study aimed to evaluate the performance of AI technology in this full-coverage screening program. The evaluation indicators included accessibility, screening efficiency, diagnostic quality, and program cost. Characteristics of 1,704,461 individuals screened from July 2022 to January 2023 were used to analyze accessibility and AI screening efficiency. A random sample of 220 individuals was used for external diagnostic quality control. The costs of different participating screening institutions were assessed. Cervical cancer screening services were extended to all administrative districts, especially in rural areas. Rural women had the highest participation rate at 67.54% (1,147,839/1,699,591). Approximately 1.7 million individuals were screened, achieving a cumulative coverage of 13.45% in about 6 months. Full-coverage programs could be achieved by AI technology in approximately 1 year, which was 87.5 times more efficient than the manual reading of slides. The sample compliance rate was as high as 99.1%, and compliance rates for positive, negative, and pathology biopsy reviews exceeded 96%. The cost of this program was CN ¥49 (the average exchange rate in 2022 is as follows: US $1=CN ¥6.7261) per person, with the primary screening institution and the third-party testing institute receiving CN ¥19 and ¥27, respectively. AI-assisted diagnosis has proven to be accessible, efficient, reliable, and low cost, which could support the implementation of full-coverage screening programs, especially in areas with insufficient health resources. AI technology served as a crucial tool for rapidly and effectively increasing screening coverage, which would accelerate the achievement of the World Health Organization's goals of eliminating cervical cancer.

Abstract 4144529: Cardiac Allograft Hypertrophy (CAH) at 6 Months Post Transplant Is a Prognostic Marker of Long-Term Outcomes: Are We Missing a Simple Biomarker?

Introduction: Cardiac hypertrophy is a known adverse prognostic marker in various non-transplant pathologies. In heart transplant patients, due to many confounders, it has been controversial on the relevance and timing of cardiac hypertrophy as an adverse remodeling vs acute injury pattern in an immunologically hostile environment. Previous studies have shown prognostication of hypertrophy on echocardiogram at 1-year post-heart transplant. Research Questions: Does cardiac hypertrophy within a year after transplant have long-term prognostic implications? Methods: We collected relevant clinical variables for all heart transplants using EPIC EHR’s Clarity database. Hypertrophy was defined based on LV Mass Indexed to body surface area where LV Mass = 0.8 x (1.04 x (((LVIDD + IVSd + PWd) 3 - LVIDD 3 ))) + 0.6. Relative Wall Thickness was defined as RWT = 2 x PWd / LVIDD. We used a rule-based natural language processing program validated by correlation with manual readings by trained cardiologists (r=0.96, p=0.007) to abstract echo variables. Results: Inclusion criteria were heart transplants performed from 2015 to 2023 at our center, with an echocardiogram closest to 6 months (+/- 1 month). Ten percent (n=33) showed hypertrophy on echocardiograms at 6 months (Table 1). Of these, 20 (61%) had mild, 3 (9%) severe, and 10 (30%) moderate hypertrophy. Of 33 patients, 28 (85%) had concentric, and 5 (15%) had eccentric hypertrophy. Patients with hypertrophy at 6 months had significantly worse survival at 5 years (p=0.01) and 10 years (p=0.05) compared to patients without hypertrophy (Fig 1). Survival at 5 and 10 years was not statistically different for patients with hypertrophy at 3 months (5 yrs p=0.17, 10 yrs p=0.06), 12 months (5 yrs p=0.38, 10 yrs p=0.30), and 18 months (5 yrs p=0.15, 10 yrs p=0.08) compared to those without hypertrophy. Conclusion: Cardiac hypertrophy on echocardiogram at 6 months predicts adverse long-term survival, while other time points did not.

Abstract 4124675: Deep Learning Screening of Cardiac MRIs Uncovers Undiagnosed Hypertrophic Cardiomyopathy in the UK BioBank

Introduction: The prevalence of hypertrophic cardiomyopathy (HCM) in the UK Biobank based on ICD-10 codes (.07%) is lower than global estimates of disease prevalence (0.2 - 0.5%). Prior studies using this data have remarked on the limitations of findings given likely underdiagnosis. The availability of cardiac MRI scans on a fraction of the participants offers an opportunity to identify missed diagnoses. Aims: This study seeks to utilize a generalizable deep learning model to detect likely cases of undiagnosed hypertrophic cardiomyopathy from cardiac MRIs in the UK Biobank. Methods: The foundational model was trained on a multi-institutional dataset of 14,073 cardiac MRIs via a self-supervised contrastive learning approach that sought to minimize the divergence between scans and their associated radiology reports. The pre-trained model was fine-tuned to diagnose hypertrophic cardiomyopathy on a distinct cohort of 4,870 MRIs with 368 cases of HCM, achieving an AUC of 0.94. The fine-tuned model was applied to the UK Biobank cardiac MRI dataset to ascertain predicted probabilities of HCM. Cases exceeding a threshold of 95% – correlating to the top 0.5% of cases (expected specificity of 97% and sensitivity of 60%) – were screened in for manual reading. In a blinded fashion, a board-certified radiologist was tasked with diagnosing HCM on a sample of cases composed of high and low predicted probabilities. Results: Of the 43,017 patients with cardiac MRIs, only 9 (.02%) had an ICD diagnosis of HCM. 266 cardiac MRIs were manually reviewed: 216 had greater than 95% predicted probability of HCM; 50 negative controls were randomly selected amongst cases with predicted probability less than 10%. The radiologist concurred with an HCM diagnosis for 115 cases (sensitivity 53%, specificity 98%), 112 of which were previously undiagnosed. The prevalence of hypertension and aortic stenosis did not significantly differ between the cohort of true positives (69.2%) and false positives (76.6%). The corrected prevalence of HCM in the UK BioBank MRI cohort is estimated at 0.28%. Conclusions: The findings of this study illustrate the remarkable ability of a generalizable deep learning model to detect undiagnosed cases of a rare disease process from cardiac MRIs. This is an important milestone that may allow for widespread screening of hypertrophic cardiomyopathy while minimizing demand for radiologist labor, and thereby allow patients to reap the substantial benefits of earlier treatment.

NIMG-54. AUTOMATED IMAGING RESPONSE EVALUATION SYSTEM (AIRES) FOR NEURO-ONCOLOGY: PROTOTYPE SOFTWARE TOOL FOR DETERMINING STANDARDIZED RADIOGRAPHIC RESPONSE ASSESSMENT FOR GLIOBLASTOMA CLINICAL TRIALS

Abstract Standardized radiographic response assessment criteria like Modified Response Assessment in Neuro-Oncology (mRANO) and now the RANO 2.0 are utilized for evaluating progression-free survival and objective response rate during glioblastoma clinical trials. After measuring tumor size with either bidimensional diameters or volumetric segmentations, the crucial and final time-consuming step of categorizing progression, stable disease, and response based on multiple criteria and numerical thresholds (e.g. ≥40% volumetric growth = progressive disease) is currently done manually. We developed an application prototype, Automated Imaging Response Evaluation System (AIRES) for Neuro-Oncology, that uses the mRANO criteria to label each timepoint as treatment response, stable disease, or disease progression based on either bidimensional or volumetric measurements as well as optional inputs of clinical status and corticosteroid dosage. These inputs may be uploaded via CSV files, which can integrate with automated tumor segmentation volumetry workflows, or entered in the AIRES graphical user interface (GUI). The AIRES GUI displays a patient report consisting of a table and graph that contain the lesion size, percent change from baseline, percent change from nadir, and the mRANO response category for each timepoint. To test AIRES in a real-world application, tumor size measurements from 367 scans across 41 patients from NUTMEG, a phase II multicenter clinical trial, were used to perform mRANO reads and calculate progression-free survival and time to response. AIRES-assisted reads performed by reader 1 were significantly quicker than fully manual reads performed by reader 2 (37.1±8.6 vs 107.7±58.6 seconds, P<0.0001). These results show that the AIRES app can make the reads quicker and potentially feasible for non-trained personnel, while reducing the amount of error-prone manual steps. Additionally, the underlying logic of AIRES is easily adaptable to integrate other response criteria including but not limited to RANO 2.0 and other future response assessment updates.

External validation of a machine learning based classification algorithm for ambulatory heart rhythm diagnostics using smartphone-photoplethysmography - the SMARTBEATS algorithm study

Abstract Introduction Smartphone-photoplethysmography (PPG) can be used for heart rhythm monitoring. According to current guidelines, ECG verification is required for a new diagnosis of atrial fibrillation (AF). Accurate machine learning (ML) based automatic algorithms have the potential to facilitate clinical applications generating large numbers of PPG recordings, by offloading the need for manual over-read. Purpose The aim of this study was to evaluate the diagnostic performance of an automatic ML-based algorithm for heart rhythm diagnostics using smartphone-PPG recorded by patients with AF in an unsupervised ambulatory setting. Methods Patients undergoing direct current cardioversion (DCCV) at a university hospital for treatment of AF or atrial flutter (AFL) were asked to perform one-minute heart rhythm recordings post-cardioversion at least twice daily for 30 days. All participants were provided with an iPhone 7 smartphone running the CORAI Heart Monitor PPG application simultaneously with a single-lead ECG recording (KardiaMobile). The automatic algorithm uses support vector machines (SVM) to classify heart rhythm from smartphone-PPG recordings. The SVM classifier evaluated here was trained on ambulatory PPG recordings made by patients in a separate cardioversion cohort, ensuring complete independence between training and validation sets. PPG recordings in the validation cohort were analyzed by the automatic algorithm and diagnostic performance was calculated by comparing heart rhythm classification output from the SVM classifier to the heart rhythm diagnosis from the simultaneous ECG recordings. ECG recordings were interpreted independently by two cardiologists and were set as gold standard. Results The SVM classifier was trained on data from 153 patients with 11,749 PPG recordings, of which 5,873 (50.0%) were labelled as AF and 5,876 (50.0%) as sinus rhythm (SR), as assessed by manual reading. In the validation cohort, 280 patients, with a median age of 69.0 years (31% women), registered 18,005 simultaneous PPG and ECG recordings. Recordings interpreted as AFL on ECG (2.0%), as having insufficient quality on ECG (4.9%) or PPG (2.8%), and low certainty algorithmic classifications (1.2%) were excluded, leaving 16,057 PPG recordings. Included ECG recordings consisted of 71.2% interpreted as (SR) and 28.8% as AF. Algorithm classification of the PPG recordings in the validation cohort diagnosed AF (sensitivity) in 99.7% and SR (specificity) in 99.7% of the recordings, with an overall accuracy of 99.7%. F1-score was 99.4% and area under the ROC curve (AUC) was 0.999. Conclusion A machine learning based algorithm for automatic heart rhythm diagnostics showed excellent diagnostic performance for smartphone-PPG recordings in an unsupervised ambulatory setting, minimizing the need for ECG verification in cardioversion populations.

Bone scintigraphy based on deep learning model and modified growth optimizer

Bone scintigraphy is recognized as an efficient diagnostic method for whole-body screening for bone metastases. At the moment, whole-body bone scan image analysis is primarily dependent on manual reading by nuclear medicine doctors. However, manual analysis needs substantial experience and is both stressful and time-consuming. To address the aforementioned issues, this work proposed a machine-learning technique that uses phases to detect Bone scintigraphy. The first phase in the proposed model is the feature extraction and it was conducted based on integrating the Mobile Vision Transformer (MobileViT) model in our framework to capture highly complex representations from raw medical imagery using two primary components including ViT and lightweight CNN featuring a limited number of parameters. In addition, the second phase is named feature selection, and it is dependent on the Arithmetic Optimization Algorithm (AOA) being used to improve the Growth Optimizer (GO). We evaluate the performance of the proposed FS model, named GOAOA using a set of 18 UCI datasets. Additionally, the applicability of Bone scintigraphy for real-world application is evaluated using 2800 bone scan images (1400 normal and 1400 abnormal). The results and statistical analysis revealed that the proposed GOAOA algorithm as an FS technique outperforms the other FS algorithms employed in this study.

Computer vision and deep transfer learning for automatic gauge reading detection

This manuscript proposes an automatic reading detection system for an analogue gauge using a combination of deep learning, machine learning, and image processing. The study suggests image-processing techniques in manual analogue gauge reading that include generating readings for the image to provide supervised data to address difficulties in unsupervised data in gauges and to achieve better accuracy using DenseNet 169 compared to other approaches. The model uses artificial intelligence to automate reading detection using deep transfer learning models like DenseNet 169, InceptionNet V3, and VGG19. The models were trained using 1011 labeled pictures, 9 classes, and readings from 0 to 8. The VGG19 model exhibits a high training precision of 97.00% but a comparatively lower testing precision of 75.00%, indicating the possibility of overfitting. On the other hand, InceptionNet V3 demonstrates consistent precision across both datasets, but DenseNet 169 surpasses other models in terms of precision and generalization capabilities.

Fully Automated Artificial Intelligence Solution for Human Epidermal Growth Factor Receptor 2 Immunohistochemistry Scoring in Breast Cancer: A Multireader Study.

The proven efficacy of human epidermal growth factor receptor 2 (HER2) antibody-drug conjugate therapy for treating HER2-low breast cancers necessitates more accurate and reproducible HER2 immunohistochemistry (IHC) scoring. We aimed to validate performance and utility of a fully automated artificial intelligence (AI) solution for interpreting HER2 IHC in breast carcinoma. A two-arm multireader study of 120 HER2 IHC whole-slide images from four sites assessed HER2 scoring by four surgical pathologists without and with the aid of an AI HER2 solution. Both arms were compared with high-confidence ground truth (GT) established by agreement of at least four of five breast pathology subspecialists according to ASCO/College of American Pathologists (CAP) 2018/2023 guidelines. The mean interobserver agreement among GT pathologists across all HER2 scores was 72.4% (N = 120). The AI solution demonstrated high accuracy for HER2 scoring, with 92.1% agreement on slides with high confidence GT (n = 92). The use of the AI tool led to improved performance by readers, interobserver agreement increased from 75.0% for digital manual read to 83.7% for AI-assisted review, and scoring accuracy improved from 85.3% to 88.0%. For the distinction of HER2 0 from 1+ cases (n = 58), pathologists supported by AI showed significantly higher interobserver agreement (69.8% without AI v 87.4% with AI) and accuracy (81.9% without AI v 88.8% with AI). This study demonstrated utility of a fully automated AI solution to aid in scoring HER2 IHC accurately according to ASCO/CAP 2018/2023 guidelines. Pathologists supported by AI showed improvements in HER2 IHC scoring consistency and accuracy, especially for distinguishing HER2 0 from 1+ cases. This AI solution could be used by pathologists as a decision support tool for enhancing reproducibility and consistency of HER2 scoring and particularly for identifying HER2-low breast cancers.

Data-Driven Water Monitoring System with Descriptive Analytics for Aquaculture Prawn Farms

This study aimed to develop a data-driven water monitoring system with descriptive analytics for aquaculture prawn farms. This system was designed to automate the monitoring of the water quality of the prawn farm so as to minimize labor and time spent for manually testing the water. Utilizing a rapid prototyping methodology, which is a rapid or quick creation of a prototype or a physical model of a device used in the development of a project, the said monitoring system was evaluated through a comparative analysis between the data gathered manually and the data collected by the monitoring system. To ensure reliability and validity of this monitoring system, it was used various times over several consecutive days. Also, a t-test was used to determine the significant differences between manual and system readings. Findings of the study showed that the designed water monitoring system provided accurate results, and the objectives of the study were met, particularly in terms of integrating a Raspberry Pi 3 microprocessor to automate the system in monitoring the water quality. It was also found out that the use of different sensors to test the water condition in terms of its temperature, pH level, salinity, dissolved oxygen, and turbidity was accurate. Furthermore, the system also met its objective of developing an Android mobile application to monitor the status remotely. With this, it is recommended for prawn farmers to utilize the system (with internet connectivity) for their efficient water quality management and to improve their remote monitoring capabilities.

Nurse-Supported Self-Directed Cognitive Behavioral Therapy for Insomnia

Cognitive behavioral therapy for insomnia (CBTi) is the standard of care for treating insomnia disorder, but access is limited. Alternative approaches are needed to expand access to the standard of care. To examine the effectiveness of a nurse-supported, self-directed behavioral insomnia intervention for decreasing insomnia severity and improving sleep outcomes among veterans, a population with considerable mental health comorbidity. This randomized clinical trial included 178 patients with insomnia disorder who were recruited from a Veterans Affairs hospital (Durham VA Healthcare System) from September 2019 to April 2022 and randomized following baseline assessment; follow-ups were conducted at 8 weeks (primary end point) and 6 months. Data analysis was primarily conducted during the summer of 2023 and concluded in May 2024. Six weekly phone calls from a nurse interventionist plus assigned treatment manual readings covering CBTi treatment components. The health education manual focused on health topics but not sleep. The primary outcome was the Insomnia Severity Index (score range, 0-28; remission <8; differential improvement of 3 points targeted) score assessed at 8 weeks postrandomization. Secondary outcomes were sleep outcomes, depression, fatigue, treatment response, and remission. Of 178 study participants, the mean (SD) age was 55.1 (13.2) years, and 128 (71.9%) identified as men. At 8 weeks, Insomnia Severity Index scores decreased by an estimated mean (SE) of 5.7 (0.51) points in the intervention group and 2.0 (0.47) points in the control group, a differential mean improvement of 3.7 points (95% CI, -5.0 to -2.4; P < .001). Differences were sustained at 6 months (mean, -2.8; 95% CI, -4.4 to -1.3; P < .001). The intervention also resulted in greater improvements at 8 weeks postrandomization in diary sleep onset latency, wake after sleep onset, and sleep efficiency and actigraphy sleep efficiency; these differences were sustained at 6 months. At 8 weeks, depression and fatigue were significantly reduced, and the odds of treatment response and remission were greater in the intervention group compared with controls. This randomized clinical trial found that despite greater prevalence of mental health conditions and sleep difficulties among veterans, a nurse-supported self-directed CBTi was more effective than health education control for reducing insomnia severity and improving sleep outcomes. Although less effective than therapist-delivered CBTi, findings were comparable with other trials using modified CBTi protocols. ClinicalTrials.gov Identifier: NCT03727438.

Evaluation of AI-enhanced non-mydriatic fundus photography for diabetic retinopathy screening

ObjectiveTo assess the feasibility of using non-mydriatic fundus photography in conjunction with an artificial intelligence (AI) reading platform for large-scale screening of diabetic retinopathy (DR). MethodsIn this study, we selected 120 patients with diabetes hospitalized in our institution from December 2019 to April 2021. Retinal imaging of 240 eyes was obtained using non-mydriatic fundus photography. The fundus images of these patients were divided into two groups based on different interpretation methods. In Experiment Group 1, the images were analyzed and graded for DR diagnosis using an AI reading platform. In Experiment Group 2, the images were analyzed and graded for DR diagnosis by an associate chief physician in ophthalmology, specializing in fundus diseases. Concurrently, all patients underwent the gold standard for DR diagnosis and grading—fundus fluorescein angiography (FFA)—with the outcomes serving as the Control Group. The diagnostic value of the two methods was assessed by comparing the results of Experiment Groups 1 and 2 with those of the Control Group. ResultsKeeping the control group (FFA results) as the gold standard, no significant differences were observed between the two experimental groups regarding diagnostic sensitivity, specificity, false positive rate, false negative rate, positive predictive value, negative predictive value, Youden's index, Kappa value, and diagnostic accuracy (X2 = 0.371, P > 0.05). ConclusionCompared with the manual reading group, the AI reading group revealed no significant differences across all diagnostic indicators, exhibiting high sensitivity and specificity, as well as a relatively high positive predictive value. Additionally, it demonstrated a high level of diagnostic consistency with the gold standard. This technology holds potential for suitability in large-scale screening of DR.

Application of artificial intelligence in lung cancer screening: A real-world study in a Chinese physical examination population.

With the rapid increase of chest computed tomography (CT) images, the workload faced by radiologists has increased dramatically. It is undeniable that the use of artificial intelligence (AI) image-assisted diagnosis system in clinical treatment is a major trend in medical development. Therefore, in order to explore the value and diagnostic accuracy of the current AI system in clinical application, we aim to compare the detection and differentiation of benign and malignant pulmonary nodules between AI system and physicians, so as to provide a theoretical basis for clinical application. Our study encompassed a cohort of 23 336 patients who underwent chest low-dose spiral CT screening for lung cancer at the Health Management Center of West China Hospital. We conducted a comparative analysis between AI-assisted reading and manual interpretation, focusing on the detection and differentiation of benign and malignant pulmonary nodules. The AI-assisted reading exhibited a significantly higher screening positive rate and probability of diagnosing malignant pulmonary nodules compared with manual interpretation (p < 0.001). Moreover, AI scanning demonstrated a markedly superior detection rate of malignant pulmonary nodules compared with manual scanning (97.2% vs. 86.4%, p < 0.001). Additionally, the lung cancer detection rate was substantially higher in the AI reading group compared with the manual reading group (98.9% vs. 90.3%, p < 0.001). Our findings underscore the superior screening positive rate and lung cancer detection rate achieved through AI-assisted reading compared with manual interpretation. Thus, AI exhibits considerable potential as an adjunctive tool in lung cancer screening within clinical practice settings.

Incidental pulmonary nodules: Natural language processing analysis of radiology reports

BackgroundPulmonary nodules are a common incidental finding on chest Computed Tomography scans (CT), most of the time outside of lung cancer screening (LCS). We aimed to evaluate the number of incidental pulmonary nodules (IPN) found in 1 year in our hospital, as well as the follow-up (FUP) rate and the clinical and radiological features associated with FUP. MethodsWe trained a Natural Language Processing (NLP) tool to identify the transcripts mentioning the presence of a pulmonary nodule, among a large population of patients from a French hospital. We extracted nodule characteristics using keyword analysis. NLP algorithm accuracy was determined through manual reading from a sample of our population. Electronic health database and medical record analysis by clinician allowed us to obtain information about FUP and cancer diagnoses. ResultsIn this retrospective observational study, we analyzed 101,703 transcripts corresponding to the entire CTs performed in 2020. We identified 1,991 (2 %) patients with an IPN. NLP accuracy for nodule detection in CT reports was 99 %. Only 41 % received a FUP between January 2020 and December 2021. Patient age, nodule size, and the mention of the nodule in the impression part were positively associated with FUP, while nodules diagnosed in the context of COVID-19 were less followed. 36 (2 %) lung cancers were subsequently diagnosed, with 16 (45 %) at a non-metastatic stage. ConclusionsWe identified a high prevalence of IPN with a low FUP rate, encouraging the implementation of IPN management program. We also highlighted the potential of NLP for database analysis in clinical research.

The simulation of wireless body temperature monitoring system based on Internet of Things

Traditional body temperature monitoring technology has some problems, such as inaccurate manual reading, unable to monitor continuously for a long time, and difficult data storage and analysis. To solve these problems, this paper designs an application scenario of Internet of Things in body temperature monitoring, which integrates Internet of Things, network communication, network programming and other technologies, designs the overall architecture, topology structure and IP address allocation scheme of the system, and realizes real-time acquisition, transmission, storage, analysis, and display functions based on the Packet Tracer simulation platform. The performance evaluation and optimization are also carried out. The system realizes wireless monitoring and analysis of the body temperature data collected by the temperature sensor through the home gateway and single chip microcomputer and other devices. After testing, the designed system is stable, which provides a solution for the application of Internet of Things in body temperature monitoring.

Maize plant height automatic reading of measurement scale based on improved YOLOv5 lightweight model.

Plant height is a significant indicator of maize phenotypic morphology, and is closely related to crop growth, biomass, and lodging resistance. Obtaining the maize plant height accurately is of great significance for cultivating high-yielding maize varieties. Traditional measurement methods are labor-intensive and not conducive to data recording and storage. Therefore, it is very essential to implement the automated reading of maize plant height from measurement scales using object detection algorithms. This study proposed a lightweight detection model based on the improved YOLOv5. The MobileNetv3 network replaced the YOLOv5 backbone network, and the Normalization-based Attention Module attention mechanism module was introduced into the neck network. The CioU loss function was replaced with the EioU loss function. Finally, a combined algorithm was used to achieve the automatic reading of maize plant height from measurement scales. The improved model achieved an average precision of 98.6%, a computational complexity of 1.2 GFLOPs, and occupied 1.8 MB of memory. The detection frame rate on the computer was 54.1 fps. Through comparisons with models such as YOLOv5s, YOLOv7 and YOLOv8s, it was evident that the comprehensive performance of the improved model in this study was superior. Finally, a comparison between the algorithm's 160 plant height data obtained from the test set and manual readings demonstrated that the relative error between the algorithm's results and manual readings was within 0.2 cm, meeting the requirements of automatic reading of maize height measuring scale.

Detecting the distribution of and public attitudes to charismatic alien species based on media coverage

Charismatic species are often reported by the media, providing information for detecting population status and public perception. To identify the number and distribution of free-living Black Swan (Cygnus atratus), a charismatic alien species in Chinese mainland and to detect the public and the media attitudes to the species, we analyzed the reports and emotional tendency from media coverage in 2000–2022 using manual reading, crawler extraction and latent Dirichlet allocation. A total of 6654 Black Swans were reported at 711 sites, including 147 individuals at 30 nature reserves. Successful breeding was reported at one-fourth of the total sites, including five nature reserves. The proportion of positive emotional tendency to Black Swans was overwhelming in the reports and was higher than that to alien species in general, suggesting that the public and the media are unaware of the risk of biological invasion. Effective management of invasive species requires the media clarifies the invasion risk of charismatic alien species. Promoting the unity between the harmfulness of abstract concept of alien species and the charisma of a specific alien species among the public help effective management.

Occurrence of Wetness on the Fruit Surface Modeled Using Spatio-Temporal Temperature Data from Sweet Cherry Tree Canopies

Typically, fruit cracking in sweet cherry is associated with the occurrence of free water at the fruit surface level due to direct (rain and fog) and indirect (cold exposure and dew) mechanisms. Recent advances in close range remote sensing have enabled the monitoring of the temperature distribution with high spatial resolution based on light detection and ranging (LiDAR) and thermal imaging. The fusion of LiDAR-derived geometric 3D point clouds and merged thermal data provides spatially resolved temperature data at the fruit level as LiDAR 4D point clouds. This paper aimed to investigate the thermal behavior of sweet cherry canopies using this new method with emphasis on the surface temperature of fruit around the dew point. Sweet cherry trees were stored in a cold chamber (6 °C) and subsequently scanned at different time intervals at room temperature. A total of 62 sweet cherry LiDAR 4D point clouds were identified. The estimated temperature distribution was validated by means of manual reference readings (n = 40), where average R2 values of 0.70 and 0.94 were found for ideal and real scenarios, respectively. The canopy density was estimated using the ratio of the number of LiDAR points of fruit related to the canopy. The occurrence of wetness on the surface of sweet cherry was visually assessed and compared to an estimated dew point (Ydew) index. At mean Ydew of 1.17, no wetness was observed on the fruit surface. The canopy density ratio had a marginal impact on the thermal kinetics and the occurrence of wetness on the surface of sweet cherry in the slender spindle tree architecture. The modelling of fruit surface wetness based on estimated fruit temperature distribution can support ecophysiological studies on tree architectures considering resilience against climate change and in studies on physiological disorders of fruit.

Comparison of QT interval readings between smartwatch ECG combined with artificial intelligence and 12-lead ECG in subjects hospitalized for antiarrhythmic drug initiation and follow-up

Abstract Background/Introduction Class III antiarrhythmic drugs (AADs) are effective for the maintenance of sinus rhythm (SR) in subjects with atrial fibrillation (AF). However, several require initial hospitalization for QT interval monitoring using the 12-lead ECG. Purpose The purpose of this study was to evaluate the feasibility of using a smartwatch single lead ECG combined with a deep learning algorithm for routine QT interval determination in the context of AAD initiation. Methods A deep learning model was developed using smartwatch and Holter ECG recordings to estimate corrected QT intervals. To evaluate the performance of this model, we carried out a prospective study on subjects hospitalized for initiation of sotalol and/or dofetilide. Subjects recorded near simultaneous (maximal 2 minutes apart) smartwatch ECGs (Apple Watch Series 6) and 12-lead ECG (Mac 5500 HD ECG or GE Carescape B450) right before and 2-3 hours after drug administration twice a day for 2-3 days. Blinded double annotation followed by adjudication of disagreement provided a reference heart rhythm (NSR or AF) and QTc interval. The tangent method was used for QTc interval determination. Bland-Altman analysis was performed to assess the agreement between QTc measures. Results Fifty subjects (mean age 67.4±10.9 years, 64% male) were enrolled in the study from February 2022 to October 2022. Out of 386 monitoring visits, 321 near simultaneous pairs of ECGs were collected with a mean delay of +15.0±41.1s for the smartwatch ECG compared to the 12-lead ECG. Overall, a mean QTcF reference value of 419.9±34.0 ms was observed (435.2±38.4 ms for QTcB, r=0.83 between annotators[BL2] ). Among the 139 pairs with 12-lead ECG found in NSR, we observed a mean QTcF difference of +19.7 ms and limits of agreements equal to -21.5 ms and 60.8 ms, with AI-facilitated measurement. In comparison, a mean QTcF difference of +22.5 ms and limits of agreements equal to -23.8 ms and 68.8 ms were observed for manual readings of smartwatch ECGs instead. Conclusion(s): Our findings suggest that a smartwatch ECG deep learning approach can estimate the QT interval with a fair agreement compared to standard 12-lead monitoring during AAD initiation. This measurement method appears to be at least as accurate as manual measurements on smartwatch ECGs. With further validation, the smartwatch-based automatic detection of QT interval prolongation, could be used for a faster, safe, and extended outpatient QT interval monitoring.Bland-Altman plots