Perspectives on label-free microscopy of heterogeneous and dynamic biological systems.

Significance: Advancements in label-free microscopy could provide real-time, non-invasive imaging with unique sources of contrast and automated standardized analysis to characterize heterogeneous and dynamic biological processes. These tools would overcome challenges with widely used methods that are destructive (e.g., histology, flow cytometry) or lack cellular resolution (e.g., plate-based assays, whole animal bioluminescence imaging). Aim: This perspective aims to (1) justify the need for label-free microscopy to track heterogeneous cellular functions over time and space within unperturbed systems and (2) recommend improvements regarding instrumentation, image analysis, and image interpretation to address these needs. Approach: Three key research areas (cancer research, autoimmune disease, and tissue and cell engineering) are considered to support the need for label-free microscopy to characterize heterogeneity and dynamics within biological systems. Based on the strengths (e.g., multiple sources of molecular contrast, non-invasive monitoring) and weaknesses (e.g., imaging depth, image interpretation) of several label-free microscopy modalities, improvements for future imaging systems are recommended. Conclusion: Improvements in instrumentation including strategies that increase resolution and imaging speed, standardization and centralization of image analysis tools, and robust data validation and interpretation will expand the applications of label-free microscopy to study heterogeneous and dynamic biological systems.

Artificial intelligence coronary computed tomography, coronary computed tomography angiography using fractional flow reserve, and physician visual interpretation in the per-vessel prediction of abnormal invasive adenosine fractional flow reserve.

Aims: A comparison of diagnostic performance comparing AI-QCTISCHEMIA, coronary computed tomography angiography using fractional flow reserve (CT-FFR), and physician visual interpretation on the prediction of invasive adenosine FFR have not been evaluated. Furthermore, the coronary plaque characteristics impacting these tests have not been assessed. Methods and results: In a single centre, 43-month retrospective review of 442 patients referred for coronary computed tomography angiography and CT-FFR, 44 patients with CT-FFR had 54 vessels assessed using intracoronary adenosine FFR within 60 days. A comparison of the diagnostic performance among these three techniques for the prediction of FFR ≤ 0.80 was reported. The mean age of the study population was 65 years, 76.9% were male, and the median coronary artery calcium was 654. When analysing the per-vessel ischaemia prediction, AI-QCTISCHEMIA had greater specificity, positive predictive value (PPV), diagnostic accuracy, and area under the curve (AUC) vs. CT-FFR and physician visual interpretation CAD-RADS. The AUC for AI-QCTISCHEMIA was 0.91 vs. 0.76 for CT-FFR and 0.62 for CAD-RADS ≥ 3. Plaque characteristics that were different in false positive vs. true positive cases for AI-QCTISCHEMIA were max stenosis diameter % (54% vs. 67%, P < 0.01); for CT-FFR were maximum stenosis diameter % (40% vs. 65%, P < 0.001), total non-calcified plaque (9% vs. 13%, P < 0.01); and for physician visual interpretation CAD-RADS ≥ 3 were total non-calcified plaque (8% vs. 12%, P < 0.01), lumen volume (681 vs. 510 mm3, P = 0.02), maximum stenosis diameter % (40% vs. 62%, P < 0.001), total plaque (19% vs. 33%, P = 0.002), and total calcified plaque (11% vs. 22%, P = 0.003). Conclusion: Regarding per-vessel prediction of FFR ≤ 0.8, AI-QCTISCHEMIA revealed greater specificity, PPV, accuracy, and AUC vs. CT-FFR and physician visual interpretation CAD-RADS ≥ 3.

Can machine learning predict the accuracy of preoperative planning for total hip arthroplasty, basing on patient-related factors? An explorative investigation on Supervised machine learning classification models.

Background: The success of Total Hip Arthroplasty (THA) is influenced by preoperative planning, with traditional 2D approaches displaying varied reliability as well. The present study investigates the use of Supervised Machine Learning (SML) models with patient-related features to improve accuracy. Methods: Preoperative and perioperative data, as well as planning and final implant information, were obtained from 800 consecutive cementless primary THA, which was performed uniformly by a specialized surgical team. Six Supervised Machine Learning models were trained and validated using patient characteristics and implant data: Logistic Regression (LR), Linear Discriminant Analysis (LDA), K-Nearest Neighbors (KNN), Decision Tree (CART), Gaussian Naive Bayes (GN), and Support Vector Classifier (SVC). The models' ability to predict planning reliability and leg length disparity was evaluated. Results: KNN performed better on the cup model (97.9 %), femur model (96.7 %), and femur size (99.2 %). SVM emerged as the model with the highest accuracy for cup size (60.4 %) and head size (62.1 %). CART had the best accuracy (99 %) when determining leg length discrepancy. Conclusion: The study demonstrates the utility of Supervised Machine Learning models, specifically KNN, in predicting the accuracy of preoperative planning in THA. The accuracy of these models, which are driven by patient-related characteristics, provides useful information for optimizing patients' selection and improving surgical outcome.

ChatGPT With GPT-4 Outperforms Emergency Department Physicians in Diagnostic Accuracy: Retrospective Analysis.

BACKGROUND: OpenAI's ChatGPT is a pioneering artificial intelligence (AI) in the field of natural language processing, and it holds significant potential in medicine for providing treatment advice. Additionally, recent studies have demonstrated promising results using ChatGPT for emergency medicine triage. However, its diagnostic accuracy in the emergency department (ED) has not yet been evaluated. OBJECTIVE: This study compares the diagnostic accuracy of ChatGPT with GPT-3.5 and GPT-4 and primary treating resident physicians in an ED setting. METHODS: Among 100 adults admitted to our ED in January 2023 with internal medicine issues, the diagnostic accuracy was assessed by comparing the diagnoses made by ED resident physicians and those made by ChatGPT with GPT-3.5 or GPT-4 against the final hospital discharge diagnosis, using a point system for grading accuracy. RESULTS: The study enrolled 100 patients with a median age of 72 (IQR 58.5-82.0) years who were admitted to our internal medicine ED primarily for cardiovascular, endocrine, gastrointestinal, or infectious diseases. GPT-4 outperformed both GPT-3.5 (P<.001) and ED resident physicians (P=.01) in diagnostic accuracy for internal medicine emergencies. Furthermore, across various disease subgroups, GPT-4 consistently outperformed GPT-3.5 and resident physicians. It demonstrated significant superiority in cardiovascular (GPT-4 vs ED physicians: P=.03) and endocrine or gastrointestinal diseases (GPT-4 vs GPT-3.5: P=.01). However, in other categories, the differences were not statistically significant. CONCLUSIONS: In this study, which compared the diagnostic accuracy of GPT-3.5, GPT-4, and ED resident physicians against a discharge diagnosis gold standard, GPT-4 outperformed both the resident physicians and its predecessor, GPT-3.5. Despite the retrospective design of the study and its limited sample size, the results underscore the potential of AI as a supportive diagnostic tool in ED settings.

CT-based artificial intelligence prediction model for ocular motility score of thyroid eye disease.

PURPOSE: Thyroid eye disease (TED) is the most common orbital disease in adults. Ocular motility restriction is the primary complaint of patients, while its evaluation is quite difficult. The present study aimed to introduce an artificial intelligence (AI) model based on orbital computed tomography (CT) images for ocular motility score. METHODS: A total of 410 sets of CT images and clinical data were obtained from the hospital. To build a triple classification predictive model for ocular motility score, multiple deep learning models were employed to extract features of images and clinical data. Subgroup analyses based on pertinent clinical features were performed to test the efficacy of models. RESULTS: The ResNet-34 network outperformed Alex-Net and VGG16-Net in prediction of ocular motility score, with the optimal accuracy (ACC) of 0.907, 0.870, and 0.890, respectively. Subgroup analyses indicated no significant difference in ACC between active or inactive phase, functional visual field diplopia or peripheral visual field diplopia (p > 0.05). However, in the gender subgroup, the prediction model performed more accurately in female patients than males (p = 0.02). CONCLUSION: In conclusion, the AI model based on CT images and clinical data successfully realized automatic scoring of ocular motility in TED patients. This approach potentially enhanced the efficiency and accuracy of ocular motility evaluation, thus facilitating clinical application.

Effect of Replacing Sucrose in Beverages with Nonnutritive Sweetener Sucralose on Cardiometabolic Risk Factors Among Asian Indian Adults with Type 2 Diabetes: A 12-Week Randomized Controlled Trial.

INTRODUCTION: Country-specific evidence-based research is crucial for understanding the role of nonnutritive sweeteners (NNS) in managing type 2 diabetes (T2D). The main aim of this study was to explore the effect of replacing sucrose with sucralose in coffee/tea in Asian Indians with type 2 diabetes (T2D). METHODS: This 12-week, parallel-arm randomized controlled trial included 210 participants with T2D, assigned to the intervention group, where sugar/sucrose in coffee or tea was substituted with sucralose, or the control group, where sugar/sucrose was continued. Lifestyle factors remained unchanged. The primary outcome was change in HbA1c. Secondary outcomes were changes in body weight (BW), body mass index (BMI), waist circumference (WC), lipid profiles, and inflammatory markers. RESULTS: At the end of 12 weeks, no change was observed in HbA1c, fasting plasma glucose, lipid profile, and inflammatory markers between or within groups. There was a small but significant reduction in BW (- 0.5 kg [95% CI - 1.0, - 0.1]; p = 0.02), BMI (- 0.2 kg/m2 [- 0.4, 0.0]; p = 0.03), and WC (- 0.8 cm [- 1.4, - 0.3]; p = 0.002) in the intervention group. Improvements were also observed in lipid accumulation product (p = 0.01), visceral adiposity index (p = 0.04), triglyceride/glucose index (p = 0.04), total energy intake (p = 0.04), and carbohydrate intake (p < 0.0001). CONCLUSIONS: In Asian Indians with T2D, replacing about 60 kcal of added sucrose with sucralose in coffee/ tea had no benefit on glycemia but resulted in a small reduction in body weight, body mass index, and waist circumference. TRIAL REGISTRATION: Clinical Trials Registry of India (CTRI/2021/04/032686).

Retrospective evaluation of three types of expanded polytetrafluoroethylene grafts for upper limb vascular access.

Currently, three expanded polytetrafluoroethylene (ePTFE) prosthetic graft types are most commonly used for patients with end-stage kidney disease (ESKD) who require long-term vascular access for hemodialysis. However, studies comparing the three ePTFE grafts are limited. This study compared the clinical efficacy and postoperative complications of three ePTFE prosthetic graft types used for upper limb arteriovenous graft (AVG) surgery among patients with ESKD. Patients with ESKD requiring upper limb AVG surgery admitted to our center between January 2016 and September 2019 were enrolled. Overall, 282 patients who completed the 2-year follow-up were included and classified into the following three groups according to the ePTFE graft type: the GPVG group with the PROPATEN® graft, the GAVG group with the straight-type GORE® ACUSEAL, and the BVVG group with the VENAFLO® II. The patency rate and incidence of access-related complications were analyzed and compared between groups. The patients were followed up postoperatively, and data were collected at 6, 12, 18, and 24 months postoperatively. Respective to these follow-up time points, in the GPVG group, the primary patency rates were 74.29%, 65.71%, 51.43%, and 42.86%; the assisted primary patency rates were 85.71%, 74.29%, 60.00%, and 48.57%; and the secondary patency rates were 85.71%, 80.00%, 71.43%, and 60.00%. In the GAVG group, the primary patency rates were 73.03%, 53.93%, 59.42%, and 38.20%; the assisted primary patency rates were 83.15%, 68.54%, 59.55%, and 53.93%; and the secondary patency rates were 85.39%, 77.53%, 68.54%, and 62.92%, respectively. In the BVVG group, the primary patency rates were 67.24%, 53.45%, 41.38%, and 29.31%; the assisted primary patency rates were 84.48%, 67.24%, 55.17%, and 44.83%; and the secondary patency rates were 86.21%, 81.03%, 68.97%, and 60.34%, respectively. The differences in patency rates across the three grafts were not statistically significant. Overall, 18, 4, and 12 patients in the GPVG, GAVG, and BVVG groups, respectively, experienced seroma. Among the three grafts, GORE® ACUSEAL had the shortest anastomosis hemostatic time. The first cannulation times for the three grafts were GPVG at 16 (±8.2), GAVG at 4 (±4.9), and BVVG at 18 (±12.7) days. No significant difference was found in the postoperative swelling rate between the GPVG group and the other two groups. Furthermore, no statistically significant differences were found across the three graft types regarding postoperative vascular access stenosis and thrombosis, ischemic steal syndrome, pseudoaneurysm, or infection. In conclusion, no statistically significant differences in the postoperative primary, assisted primary, or secondary graft patency rates were observed among the three groups. A shorter anastomosis hemostatic time, first cannulation time, and seroma occurrence were observed with the ACUSEAL® graft than with its counterparts. The incidence of upper extremity swelling postoperatively was greater with the PROPATEN® graft than with the other grafts. No statistically significant differences were observed among the three grafts regarding the remaining complications.

Transforming Hypertension Diagnosis and Management in The Era of Artificial Intelligence: A 2023 National Heart, Lung, and Blood Institute (NHLBI) Workshop Report.

Hypertension is among the most important risk factors for cardiovascular disease, chronic kidney disease, and dementia. The artificial intelligence (AI) field is advancing quickly, and there has been little discussion on how AI could be leveraged for improving the diagnosis and management of hypertension. AI technologies, including machine learning tools, could alter the way we diagnose and manage hypertension, with potential impacts for improving individual and population health. The development of successful AI tools in public health and health care systems requires diverse types of expertise with collaborative relationships between clinicians, engineers, and data scientists. Unbiased data sources, management, and analyses remain a foundational challenge. From a diagnostic standpoint, machine learning tools may improve the measurement of blood pressure and be useful in the prediction of incident hypertension. To advance the management of hypertension, machine learning tools may be useful to find personalized treatments for patients using analytics to predict response to antihypertension medications and the risk for hypertension-related complications. However, there are real-world implementation challenges to using AI tools in hypertension. Herein, we summarize key findings from a diverse group of stakeholders who participated in a workshop held by the National Heart, Lung, and Blood Institute in March 2023. Workshop participants presented information on communication gaps between clinical medicine, data science, and engineering in health care; novel approaches to estimating BP, hypertension risk, and BP control; and real-world implementation challenges and issues.

Dynamic task offloading edge-aware optimization framework for enhanced UAV operations on edge computing platform.

Resource optimization, timely data capture, and efficient unmanned aerial vehicle (UAV) operations are of utmost importance for mission success. Latency, bandwidth constraints, and scalability problems are the problems that conventional centralized processing architectures encounter. In addition, optimizing for robust communication between ground stations and UAVs while protecting data privacy and security is a daunting task in and of itself. Employing edge computing infrastructure, artificial intelligence-driven decision-making, and dynamic task offloading mechanisms, this research proposes the dynamic task offloading edge-aware optimization framework (DTOE-AOF) for UAV operations optimization. Edge computing and artificial intelligence (AI) algorithms integrate to decrease latency, increase mission efficiency, and conserve onboard resources. This system dynamically assigns computing duties to edge nodes and UAVs according to proximity, available resources, and the urgency of the tasks. Reduced latency, increased mission efficiency, and onboard resource conservation result from dynamic task offloading edge-aware implementation framework (DTOE-AIF)'s integration of AI algorithms with edge computing. DTOE-AOF is useful in many fields, such as precision agriculture, emergency management, infrastructure inspection, and monitoring. UAVs powered by AI and outfitted with DTOE-AOF can swiftly survey the damage, find survivors, and launch rescue missions. By comparing DTOE-AOF to conventional centralized methods, thorough simulation research confirms that it improves mission efficiency, response time, and resource utilization.

Optimization and evaluation of modified release solid dosage forms using artificial neural network.

This study aims to optimize and evaluate drug release kinetics of Modified-Release (MR) solid dosage form of Quetiapine Fumarate MR tablets by using the Artificial Neural Networks (ANNs). In training the neural network, the drug contents of Quetiapine Fumarate MR tablet such as Sodium Citrate, Eudragit® L100 55, Eudragit® L30 D55, Lactose Monohydrate, Dicalcium Phosphate (DCP), and Glyceryl Behenate were used as variable input data and Drug Substance Quetiapine Fumarate, Triethyl Citrate, and Magnesium Stearate were used as constant input data for the formulation of the tablet. The in-vitro dissolution profiles of Quetiapine Fumarate MR tablets at ten different time points were used as a target data. Several layers together build the neural network by connecting the input data with the output data via weights, these weights show importance of input nodes. The training process optimises the weights of the drug product excipients to achieve the desired drug release through the simulation process in MATLAB software. The percentage drug release of predicted formulation matched with the manufactured formulation using the similarity factor (f2), which evaluates network efficiency. The ANNs have enormous potential for rapidly optimizing pharmaceutical formulations with desirable performance characteristics.

Identification of novel immune-related signatures for keloid diagnosis and treatment: insights from integrated bulk RNA-seq and scRNA-seq analysis.

BACKGROUND: Keloid is a disease characterized by proliferation of fibrous tissue after the healing of skin tissue, which seriously affects the daily life of patients. However, the clinical treatment of keloids still has limitations, that is, it is not effective in controlling keloids, resulting in a high recurrence rate. Thus, it is urgent to identify new signatures to improve the diagnosis and treatment of keloids. METHOD: Bulk RNA seq and scRNA seq data were downloaded from the GEO database. First, we used WGCNA and MEGENA to co-identify keloid/immune-related DEGs. Subsequently, we used three machine learning algorithms (Randomforest, SVM-RFE, and LASSO) to identify hub immune-related genes of keloid (KHIGs) and investigated the heterogeneous expression of KHIGs during fibroblast subpopulation differentiation using scRNA-seq. Finally, we used HE and Masson staining, quantitative reverse transcription-PCR, western blotting, immunohistochemical, and Immunofluorescent assay to investigate the dysregulated expression and the mechanism of retinoic acid in keloids. RESULTS: In the present study, we identified PTGFR, RBP5, and LIF as KHIGs and validated their diagnostic performance. Subsequently, we constructed a novel artificial neural network molecular diagnostic model based on the transcriptome pattern of KHIGs, which is expected to break through the current dilemma faced by molecular diagnosis of keloids in the clinic. Meanwhile, the constructed IG score can also effectively predict keloid risk, which provides a new strategy for keloid prevention. Additionally, we observed that KHIGs were also heterogeneously expressed in the constructed differentiation trajectories of fibroblast subtypes, which may affect the differentiation of fibroblast subtypes and thus lead to dysregulation of the immune microenvironment in keloids. Finally, we found that retinoic acid may treat or alleviate keloids by inhibiting RBP5 to differentiate pro-inflammatory fibroblasts (PIF) to mesenchymal fibroblasts (MF), which further reduces collagen secretion. CONCLUSION: In summary, the present study provides novel immune signatures (PTGFR, RBP5, and LIF) for keloid diagnosis and treatment, and identifies retinoic acid as potential anti-keloid drugs. More importantly, we provide a new perspective for understanding the interactions between different fibroblast subtypes in keloids and the remodeling of their immune microenvironment.

Survival prediction landscape: an in-depth systematic literature review on activities, methods, tools, diseases, and databases.

Survival prediction integrates patient-specific molecular information and clinical signatures to forecast the anticipated time of an event, such as recurrence, death, or disease progression. Survival prediction proves valuable in guiding treatment decisions, optimizing resource allocation, and interventions of precision medicine. The wide range of diseases, the existence of various variants within the same disease, and the reliance on available data necessitate disease-specific computational survival predictors. The widespread adoption of artificial intelligence (AI) methods in crafting survival predictors has undoubtedly revolutionized this field. However, the ever-increasing demand for more sophisticated and effective prediction models necessitates the continued creation of innovative advancements. To catalyze these advancements, it is crucial to bring existing survival predictors knowledge and insights into a centralized platform. The paper in hand thoroughly examines 23 existing review studies and provides a concise overview of their scope and limitations. Focusing on a comprehensive set of 90 most recent survival predictors across 44 diverse diseases, it delves into insights of diverse types of methods that are used in the development of disease-specific predictors. This exhaustive analysis encompasses the utilized data modalities along with a detailed analysis of subsets of clinical features, feature engineering methods, and the specific statistical, machine or deep learning approaches that have been employed. It also provides insights about survival prediction data sources, open-source predictors, and survival prediction frameworks.

Toward AI-driven neuroepigenetic imaging biomarker for alcohol use disorder: A proof-of-concept study.

Alcohol use disorder (AUD) is a disorder of clinical and public health significance requiring novel and improved therapeutic solutions. Both environmental and genetic factors play a significant role in its pathophysiology. However, the underlying epigenetic molecular mechanisms that link the gene-environment interaction in AUD remain largely unknown. In this proof-of-concept study, we showed, for the first time, the neuroepigenetic biomarker capability of non-invasive imaging of class I histone deacetylase (HDAC) epigenetic enzymes in the in vivo brain for classifying AUD patients from healthy controls using a machine learning approach in the context of precision diagnosis. Eleven AUD patients and 16 age- and sex-matched healthy controls completed a simultaneous positron emission tomography-magnetic resonance (PET/MR) scan with the HDAC-binding radiotracer [11C]Martinostat. Our results showed lower HDAC expression in the anterior cingulate region in AUD. Furthermore, by applying a genetic algorithm feature selection, we identified five particular brain regions whose combined [11C]Martinostat relative standard uptake value (SUVR) features could reliably classify AUD vs. controls. We validate their promising classification reliability using a support vector machine classifier. These findings inform the potential of in vivo HDAC imaging biomarkers coupled with machine learning tools in the objective diagnosis and molecular translation of AUD that could complement the current diagnostic and statistical manual of mental disorders (DSM)-based intervention to propel precision medicine forward.

Advancements in rice disease detection through convolutional neural networks: A comprehensive review.

This review paper addresses the critical need for advanced rice disease detection methods by integrating artificial intelligence, specifically convolutional neural networks (CNNs). Rice, being a staple food for a large part of the global population, is susceptible to various diseases that threaten food security and agricultural sustainability. This research is significant as it leverages technological advancements to tackle these challenges effectively. Drawing upon diverse datasets collected across regions including India, Bangladesh, Türkiye, China, and Pakistan, this paper offers a comprehensive analysis of global research efforts in rice disease detection using CNNs. While some rice diseases are universally prevalent, many vary significantly by growing region due to differences in climate, soil conditions, and agricultural practices. The primary objective is to explore the application of AI, particularly CNNs, for precise and early identification of rice diseases. The literature review includes a detailed examination of data sources, datasets, and preprocessing strategies, shedding light on the geographic distribution of data collection and the profiles of contributing researchers. Additionally, the review synthesizes information on various algorithms and models employed in rice disease detection, highlighting their effectiveness in addressing diverse data complexities. The paper thoroughly evaluates hyperparameter optimization techniques and their impact on model performance, emphasizing the importance of fine-tuning for optimal results. Performance metrics such as accuracy, precision, recall, and F1 score are rigorously analyzed to assess model effectiveness. Furthermore, the discussion section critically examines challenges associated with current methodologies, identifies opportunities for improvement, and outlines future research directions at the intersection of machine learning and rice disease detection. This comprehensive review, analyzing a total of 121 papers, underscores the significance of ongoing interdisciplinary research to meet evolving agricultural technology needs and enhance global food security.

Improved automatic segmentation of brain metastasis gross tumor volume in computed tomography images for radiotherapy: a position attention module for U-Net architecture.

Background: Brain metastases present significant challenges in radiotherapy due to the need for precise tumor delineation. Traditional methods often lack the efficiency and accuracy required for optimal treatment planning. This paper proposes an improved U-Net model that uses a position attention module (PAM) for automated segmentation of gross tumor volumes (GTVs) in computed tomography (CT) simulation images of patients with brain metastases to improve the efficiency and accuracy of radiotherapy planning and segmentation. Methods: We retrospectively collected CT simulation imaging datasets of patients with brain metastases from two centers, which were designated as the training and external validation datasets. The U-Net architecture was enhanced by incorporating a PAM into the transition layer, which improved the automated segmentation capability of the U-Net model. With cross-entropy loss employed as the loss function, the samples from the training dataset underwent training. The model's segmentation performance on the external validation dataset was assessed using metrics including the Dice similarity coefficient (DSC), intersection over union (IoU), accuracy, sensitivity, specificity, Matthews correlation coefficient (MCC), and Hausdorff distance (HD). Results: The proposed automated segmentation model demonstrated promising performance on the external validation dataset, achieving a DSC of 0.753±0.172. In terms of evaluation metrics (including the DSC, IoU, accuracy, sensitivity, MCC, and HD), the model outperformed the standard U-Net, which had a DSC of 0.691±0.142. The proposed model produced segmentation results that were closer to the ground truth and could reveal more detailed features of brain metastases. Conclusions: The PAM-improved U-Net model offers considerable advantages in the automated segmentation of the GTV in CT simulation images for patients with brain metastases. Its superior performance in comparison with the standard U-Net model supports its potential for streamlining and improving the accuracy of radiotherapy. With its ability to produce segmentation results consistent with the ground truth, the proposed model holds promise for clinical adoption and provides a reference for radiation oncologists to make more informed GTV segmentation decisions.

Construction and validation of a risk score system for diagnosing invasive adenocarcinoma presenting as pulmonary pure ground-glass nodules: a multi-center cohort study in China.

Background: Anxiety-driven clinical interventions have been queried due to the nondeterminacy of pure ground-glass nodules (pGGNs). Although radiomics and radiogenomics aid diagnosis, standardization and reproducibility challenges persist. We aimed to assess a risk score system for invasive adenocarcinoma in pGGNs. Methods: In a retrospective, multi-center study, 772 pGGNs from 707 individuals in The Affiliated Cancer Hospital of Zhengzhou University & Henan Cancer Hospital were grouped into training (509 patients with 558 observations) and validation (198 patients with 214 observations) sets consecutively from January 2017 to November 2021. An additional test set of 143 observations in Hainan Cancer Hospital was analyzed in the same period. Computed tomography (CT) signs and clinical features were manually collected, and the quantitative parameters were achieved by artificial intelligence (AI). The positive cutoff score was ≥3. Risk scores system 3 combined carcinoma history, chronic obstructive pulmonary disease (COPD), maximum diameters, nodule volume, mean CT values, type II or III vascular supply signs, and other radiographic characteristics. The evaluation included the area under the curves (AUCs), accuracy, sensitivity, specificity, positive predictive values (PPV), and negative predictive values (NPV) for both the risk score systems 1, 2, 3 and the AI model. Results: The risk score system 3 [AUC, 0.840; 95% confidence interval (CI): 0.789-0.890] outperformed the AI model (AUC, 0.553; 95% CI: 0.487-0.619), risk score system 1 (AUC, 0.802; 95% CI: 0.754-0.851), and risk score system 2 (AUC, 0.816; 95% CI: 0.766-0.867), with 88.0% (0.850-0.904) accuracy, 95.6% (0.932-0.972) PPV, 0.620 (0.535-0.702) NPV, 89.6% (0.864-0.920) sensitivity, and 80.6% (0.717-0.872) specificity in the training sets. In the validation and test sets, risk score system 3 performed best with AUCs of 0.769 (0.678-0.860) and 0.801 (0.669-0.933). Conclusions: An AI-based risk scoring system using quantitative image parameters, clinical features, and radiographic characteristics effectively predicts invasive adenocarcinoma in pulmonary pGGNs.

The Fourth Industrial Revolution: Its Impact on Artificial Intelligence and Medicine in Developing Countries.

Artificial intelligence (AI) is the ability of a digital computer or computer-controlled robot to perform tasks commonly associated with intelligent beings. Artificial intelligence can be both a blessing and a curse, and potentially a double-edged sword if not carefully wielded. While it holds massive potential benefits to humans-particularly in healthcare by assisting in treatment of diseases, surgeries, record keeping, and easing the lives of both patients and doctors, its misuse has potential for harm through impact of biases, unemployment, breaches of privacy, and lack of accountability to mention a few. In this article, we discuss the fourth industrial revolution, through a focus on the core of this phenomenon, artificial intelligence. We outline what the fourth industrial revolution is, its basis around AI, and how this infiltrates human lives and society, akin to a transcendence. We focus on the potential dangers of AI and the ethical concerns it brings about particularly in developing countries in general and conflict zones in particular, and we offer potential solutions to such dangers. While we acknowledge the importance and potential of AI, we also call for cautious reservations before plunging straight into the exciting world of the future, one which we long have heard of only in science fiction movies.

How the EU AI Act Seeks to Establish an Epistemic Environment of Trust.

With focus on the development and use of artificial intelligence (AI) systems in the digital health context, we consider the following questions: How does the European Union (EU) seek to facilitate the development and uptake of trustworthy AI systems through the AI Act? What does trustworthiness and trust mean in the AI Act, and how are they linked to some of the ongoing discussions of these terms in bioethics, law, and philosophy? What are the normative components of trustworthiness? And how do the requirements of the AI Act relate to these components? We first explain how the EU seeks to create an epistemic environment of trust through the AI Act to facilitate the development and uptake of trustworthy AI systems. The legislation establishes a governance regime that operates as a socio-epistemological infrastructure of trust which enables a performative framing of trust and trustworthiness. The degree of success that performative acts of trust and trustworthiness have achieved in realising the legislative goals may then be assessed in terms of statutorily defined proxies of trustworthiness. We show that to be trustworthy, these performative acts should be consistent with the ethical principles endorsed by the legislation; these principles are also manifested in at least four key features of the governance regime. However, specified proxies of trustworthiness are not expected to be adequate for applications of AI systems within a regulatory sandbox or in real-world testing. We explain why different proxies of trustworthiness for these applications may be regarded as 'special' trust domains and why the nature of trust should be understood as participatory.

Regulating AI-Based Medical Devices in Saudi Arabia: New Legal Paradigms in an Evolving Global Legal Order.

This paper examines the Saudi Food and Drug Authority's (SFDA) Guidance on Artificial Intelligence (AI) and Machine Learning (ML) technologies based Medical Devices (the MDS-G010). The SFDA has pioneered binding requirements designed for manufacturers to obtain Medical Device Marketing Authorization. The regulation of AI in health is at an early stage worldwide. Therefore, it is critical to examine the scope and nature of the MDS-G010, its influences, and its future directions. It is argued that the guidance is a patchwork of existing international best practices concerning AI regulation, incorporates adapted forms of non-AI-based guidelines, and builds on existing legal requirements in the SFDA's existing regulatory architecture. There is particular congruence with the approaches of the US Food and Drug Administration (FDA) and the International Medical Device Regulators Forum (IMDRF), but the SFDA goes beyond those approaches to incorporate other best practices into its guidance. Additionally, the binding nature of the MDS-G010 is complex. There are binding 'components' within the guidance, but the incorporation of non-binding international best practices which are subordinate to national law results in a lack of clarity about how penalties for non-compliance will operate.

Using Artificial Intelligence in Patient Care-Some Considerations for Doctors and Medical Regulators.

This paper discusses the key role medical regulators have in setting standards for doctors who use artificial intelligence (AI) in patient care. Given their mandate to protect public health and safety, it is incumbent on regulators to guide the profession on emerging and vexed areas of practice such as AI. However, formulating effective and robust guidance in a novel field is challenging particularly as regulators are navigating unfamiliar territory. As such, regulators themselves will need to understand what AI is and to grapple with its ethical and practical challenges when doctors use AI in their care of patients. This paper will also argue that effective regulation of AI extends beyond devising guidance for the profession. It includes keeping abreast of developments in AI-based technology and considering the implications for regulation and the practice of medicine. On that note, medical regulators should encourage the profession to evaluate how AI may exacerbate existing issues in medicine and create unintended consequences so that doctors (and patients) are realistic about AI's potential and pitfalls when it is used in health care delivery.