Single-Response Electronic Tongue and Machine Learning Enable the Multidetermination of Extracellular Vesicle Biomarkers for Cancer Diagnostics Without Recognition Elements

Platforms based on impedimetric electronic tongue (nonselective sensor) and machine learning are promising to bring disease screening biosensors into mainstream use toward straightforward, fast, and accurate analyses at the point-of-care, thus contributing to rationalize and decentralize laboratory tests with social and economic impacts being achieved. By combining a low-cost and scalable electronic tongue with machine learning, in this chapter, we describe the simultaneous determination of two extracellular vesicle (EV) biomarkers, i.e., the concentrations of EV and carried proteins, in mice blood with Ehrlich tumor from a single impedance spectrum without using biorecognizing elements. This tumor shows primary features of mammary tumor cells. Pencil HB core electrodes are integrated into polydimethylsiloxane (PDMS) microfluidic chip. The platform shows the highest throughput in comparison with the methods addressed in the literature to determine EV biomarkers.

Classification of fungal genera from microscopic images using artificial intelligence

Microscopic image examination is fundamental to clinical microbiology and often used as the first step to diagnose fungal infections. In this study, we present classification of pathogenic fungi from microscopic images using deep convolutional neural networks (CNN). We trained well-known CNN architectures such as DenseNet, Inception ResNet, InceptionV3, Xception, ResNet50, VGG16, and VGG19 to identify fungal species, and compared their performances. We collected 1079 images of 89 fungi genera and split our data into training, validation, and test datasets by 7:1:2 ratio. The DenseNet CNN model provided the best performance among other CNN architectures with overall accuracy of 65.35% for top 1 prediction and 75.19% accuracy for top 3 predictions for classification of 89 genera. The performance is further improved (>80%) after excluding rare genera with low sample occurrence and applying data augmentation techniques. For some particular fungal genera, we obtained 100% prediction accuracy. In summary, we present a deep learning approach that shows promising results in prediction of filamentous fungi identification from culture, which could be used to enhance diagnostic accuracy and decrease turnaround time to identification.

AI-AIF: artificial intelligence-based arterial input function for quantitative stress perfusion cardiac magnetic resonance

Aims

One of the major challenges in the quantification of myocardial blood flow (MBF) from stress perfusion cardiac magnetic resonance (CMR) is the estimation of the arterial input function (AIF). This is due to the non-linear relationship between the concentration of gadolinium and the MR signal, which leads to signal saturation. In this work, we show that a deep learning model can be trained to predict the unsaturated AIF from standard images, using the reference dual-sequence acquisition AIFs (DS-AIFs) for training.

Methods and results

A 1D U-Net was trained, to take the saturated AIF from the standard images as input and predict the unsaturated AIF, using the data from 201 patients from centre 1 and a test set comprised of both an independent cohort of consecutive patients from centre 1 and an external cohort of patients from centre 2 (n = 44). Fully-automated MBF was compared between the DS-AIF and AI-AIF methods using the Mann-Whitney U test and Bland-Altman analysis. There was no statistical difference between the MBF quantified with the DS-AIF [2.77 mL/min/g (1.08)] and predicted with the AI-AIF (2.79 mL/min/g (1.08), P = 0.33. Bland-Altman analysis shows minimal bias between the DS-AIF and AI-AIF methods for quantitative MBF (bias of -0.11 mL/min/g). Additionally, the MBF diagnosis classification of the AI-AIF matched the DS-AIF in 669/704 (95%) of myocardial segments.

Conclusion

Quantification of stress perfusion CMR is feasible with a single-sequence acquisition and a single contrast injection using an AI-based correction of the AIF.

Stature estimation by semi-automatic measurements of 3D CT images of the femur

Stature estimation is one of the most basic and important methods of personal identification. The long bones of the limbs provide the most accurate stature estimation, with the femur being one of the most useful. In all the previously reported methods of stature estimation using computed tomography (CT) images of the femur, laborious manual measurement was necessary. A semi-automatic bone measuring method can simplify this process, so we firstly reported a stature estimation process using semi-automatic bone measurement software equipped with artificial intelligence. Multiple measurements of femurs of adult Japanese cadavers were performed using automatic three-dimensional reconstructed CT images of femurs. After manually setting four points on the femur, an automatic measurement was acquired. The relationships between stature and five femoral measurements, with acceptable intraobserver and interobserver errors, were analyzed with single regression analysis using the standard error of the estimate (SEE) and the coefficient of determination (R²). The maximum length of the femur (MLF) provided the lowest SEE and the highest R²; the SEE and R² in all cadavers, males and females, respectively, were 3.913 cm (R² = 0.842), 3.664 cm (R² = 0.705), and 3.456 cm (R² = 0.686) for MLF on the right femur, and 3.837 cm (R² = 0.848), 3.667 cm (R² = 0.705), and 3.384 cm (R² = 0.699) for MLF on the left femur. These results were non-inferior to those of previous reports regarding stature estimation using the MLF. Stature estimation with this simple and time-saving method would be useful in forensic medical practice.

Artificial intelligence in lung cancer: current applications and perspectives

Artificial intelligence (AI) has been a very active research topic over the last years and thoracic imaging has particularly benefited from the development of AI and in particular deep learning. We have now entered a phase of adopting AI into clinical practice. The objective of this article was to review the current applications and perspectives of AI in thoracic oncology. For pulmonary nodule detection, computer-aided detection (CADe) tools have been commercially available since the early 2000s. The more recent rise of deep learning and the availability of large annotated lung nodule datasets have allowed the development of new CADe tools with fewer false-positive results per examination. Classical machine learning and deep-learning methods were also used for pulmonary nodule segmentation allowing nodule volumetry and pulmonary nodule characterization. For pulmonary nodule characterization, radiomics and deep-learning approaches were used. Data from the National Lung Cancer Screening Trial (NLST) allowed the development of several computer-aided diagnostic (CADx) tools for diagnosing lung cancer on chest computed tomography. Finally, AI has been used as a means to perform virtual biopsies and to predict response to treatment or survival. Thus, many detection, characterization and stratification tools have been proposed, some of which are commercially available.

Artificial Intelligence for Detection of Dementia Using Motion Data: A Scoping Review

Background

Dementia is a neurodegenerative disease resulting in the loss of cognitive and psychological functions. Artificial intelligence (AI) may help in detection and screening of dementia; however, little is known in this area.

Objectives

The objective of this study was to identify and evaluate AI interventions for detection of dementia using motion data.

Method

The review followed the framework proposed by O'Malley's and Joanna Briggs Institute methodological guidance for scoping reviews. We adhered to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews (PRISMA-ScR) checklist for reporting the results. An information specialist performed a comprehensive search from the date of inception until November 2020, in five bibliographic databases: MEDLINE, EMBASE, Web of Science Core Collection, CINAHL, and IEEE Xplore. We included studies aimed at the deployment and testing or implementation of AI interventions using motion data for the detection of dementia among a diverse population, encompassing varying age, sex, gender, economic backgrounds, and ethnicity, extending to their health care providers across multiple health care settings. Studies were excluded if they focused on Parkinson's or Huntington's disease. Two independent reviewers screened the abstracts, titles, and then read the full-texts. Disagreements were resolved by consensus, and if this was not possible, the opinion of a third reviewer was sought. The reference lists of included studies were also screened.

Results

After removing duplicates, 2,632 articles were obtained. After title and abstract screening and full-text screening, 839 articles were considered for categorization. The authors categorized the papers into six categories, and data extraction and synthesis was performed on 20 included papers from the motion tracking data category. The included studies assessed cognitive performance (n = 5, 25%); screened dementia and cognitive decline (n = 8, 40%); investigated visual behaviours (n = 4, 20%); and analyzed motor behaviors (n = 3, 15%).

Conclusions

We presented evidence of AI systems being employed in the detection of dementia, showcasing the promising potential of motion tracking within this domain. Although some progress has been made in this field recently, there remain notable research gaps that require further exploration and investigation. Future endeavors need to compare AI interventions using motion data with traditional screening methods or other tech-enabled dementia detection mechanisms. Besides, future works should aim at understanding how gender and sex, and ethnic and cultural sensitivity can contribute to refining AI interventions, ensuring they are accessible, equitable, and beneficial across all society.

Artificial intelligence-based computer-aided system for knee osteoarthritis assessment increases experienced orthopaedic surgeons' agreement rate and accuracy

PURPOSE

The aims of this study were to (1) analyze the impact of an artificial intelligence (AI)-based computer system on the accuracy and agreement rate of board-certified orthopaedic surgeons (= senior readers) to detect X-ray features indicative of knee OA in comparison to unaided assessment and (2) compare the results to those of senior residents (= junior readers).

METHODS

One hundred and twenty-four unilateral knee X-rays from the OAI study were analyzed regarding Kellgren-Lawrence grade, joint space narrowing (JSN), sclerosis and osteophyte OARSI grade by computerized methods. Images were rated for these parameters by three senior readers using two modalities: plain X-ray (unaided) and X-ray presented alongside reports from a computer-assisted detection system (aided). After exclusion of nine images with incomplete annotation, intraclass correlations between readers were calculated for both modalities among 115 images, and reader performance was compared to ground truth (OAI consensus). Accuracy, sensitivity and specificity were also calculated and the results were compared to those from a previous study on junior readers.

RESULTS

With the aided modality, senior reader agreement rates for KL grade (2.0-fold), sclerosis (1.42-fold), JSN (1.37-fold) and osteophyte OARSI grades (3.33-fold) improved significantly. Reader specificity and accuracy increased significantly for all features when using the aided modality compared to the gold standard. On the other hand, sensitivity only increased for OA diagnosis, whereas it decreased (without statistical significance) for all other features. With aided analysis, senior readers reached similar agreement and accuracy rates as junior readers, with both surpassing AI performance.

CONCLUSION

The introduction of AI-based computer-aided assessment systems can increase the agreement rate and overall accuracy for knee OA diagnosis among board-certified orthopaedic surgeons. Thus, use of this software may improve the standard of care for knee OA detection and diagnosis in the future.

LEVEL OF EVIDENCE

Level II.

Toy story or children story? Putting children and their rights at the forefront of the artificial intelligence revolution

Policymakers need to start considering the impact smart connected toys (SCTs) have on children. Equipped with sensors, data processing capacities, and connectivity, SCTs targeting children increasingly penetrate pervasively personal environments. The network of SCTs forms the Internet of Toys (IoToys) and often increases children's engagement and playtime experience. Unfortunately, this young part of the population and, most of the time, their parents are often unaware of SCTs' far-reaching capacities and limitations. The capabilities and constraints of SCTs create severe side effects at the technical, individual, and societal level. These side effects are often unforeseeable and unexpected. They arise from the technology's use and the interconnected nature of the IoToys, without necessarily involving malevolence from their creators. Although existing regulations and new ethical guidelines for artificial intelligence provide remedies to address some of the side effects, policymakers did not develop these redress mechanisms having children and SCTs in mind. This article provides an analysis of the arising side effects of SCTs and contrasts them with current regulatory redress mechanisms. We thereby highlight misfits and needs for further policymaking efforts.

Artificial intelligence is an oxymoron: The importance of an organic body when facing unknown situations as they unfold in the present moment

Departing from popular imaginations around artificial intelligence (AI), this article engages in the I in the AI acronym but from perspectives outside of mathematics, computer science and machine learning. When intelligence is attended to here, it most often refers to narrow calculating tasks. This connotation to calculation provides AI an image of scientificity and objectivity, particularly attractive in societies with a pervasive desire for numbers. However, as is increasingly apparent today, when employed in more general areas of our messy socio-cultural realities, AI- powered automated systems often fail or have unintended consequences. This article will contribute to this critique of AI by attending to Nicholas of Cusa and his treatment of intelligence. According to him, intelligence is equally dependent on an ability to handle the unknown as it unfolds in the present moment. This suggests that intelligence is organic which ties Cusa to more contemporary discussions in tech philosophy, neurology, evolutionary biology, and cognitive sciences in which it is argued that intelligence is dependent on having-and acting through-an organic body. Understanding intelligence as organic thus suggests an oxymoronic relationship to artificial.

Global bibliometric mapping of the frontier of knowledge in the field of artificial intelligence for the period 1990-2019

Artificial Intelligence (AI) has emerged as a field of knowledge that is displacing and disrupting technologies, leading to changes in human life. Therefore, the purpose of this study is to scientifically map this topic and its ramifications, in order to analyze its growth. The study was developed under the bibliometric approach and considered the period 1990-2019. The steps followed were (i) Identification and selection of keyword terms in three methodological layers by a panel of experts. (ii) Design and application of an algorithm to identify these selected keywords in titles, abstracts, and keywords using terms in Web of Science to contrast them. (iii) Performing data processing based on the Journals of the Journal Citation Report during 2020. Knowing the evolution of a field of knowledge such as AI from a bibliometric study and subsequently establishing the ramifications of new research streams is in itself a relevant finding. Addressing a broad field of knowledge as AI from a multidisciplinary approach given the convergence it generates with other disciplines and specialties is of high strategic value for decision makers such as governments, academics, scientists, and entrepreneurs.

[New technologies and robotics]

The development of increasingly more complex computer and electromotor technologies enables the increasing use and expansion of robot-assisted systems in trauma surgery rehabilitation; however, the currently available devices are rarely comprehensively applied but are often used within pilot projects and studies. Different technological approaches, such as exoskeletal systems, functional electrical stimulation, soft robotics, neurorobotics and brain-machine interfaces are used and combined to read and process the communication between, e.g., residual musculature or brain waves, to transfer them to the executing device and to enable the desired execution.Currently, the greatest amount of evidence exists for the use of exoskeletal systems with different modes of action in the context of gait and stance rehabilitation in paraplegic patients; however, their use also plays a role in the rehabilitation of fractures close to the hip joint and endoprosthetic care. So-called single joint systems are also being tested in the rehabilitation of functionally impaired extremities, e.g., after knee prosthesis implantation. At this point, however, the current data situation is still too limited to be able to make a clear statement about the use of these technologies in the trauma surgery "core business" of rehabilitation after fractures and other joint injuries.For rehabilitation after limb amputation, in addition to the further development of myoelectric prostheses, the current development of "sentient" prostheses is of great interest. The use of 3D printing also plays a role in the production of individualized devices.Due to the current progress of artificial intelligence in all fields, ground-breaking further developments and widespread application possibilities in the rehabilitation of trauma patients are to be expected.

Personality construct as a biomarker in fibromyalgia: A narrative review from an autonomic rehabilitation perspective

BACKGROUND

The heterogeneity of symptoms and ineffective treatment raise questions about the current diagnostic criteria of fibromyalgia (FM). Misdiagnosis of FM often leads to less than efficacious treatment and poor quality of life.

OBJECTIVE

This article reviews relevant evidence-based literature on personality traits in FM patients with an autonomic dysfunction perspective based on a hierarchical model to explain the utility of considering the personality trait in FM diagnosis.

METHODS

A narrative review of articles concerning chronic pain, FM, and personality traits with respect to autonomic dysfunction in FM was conducted after extensive relevant literature searches.

RESULTS

Reports discussing the predisposing factors, including coping styles, anger, suicide risk, a lack of physical activity and social support, in maintaining persistent pain in FM exist. Relationships between pain duration and severity and personality traits like neuroticism and extraversion have been reported. Coexisting clinical manifestations of FM like sleep disorders, anxiety, and intestinal irritability indicate autonomic dysfunction.

CONCLUSIONS

This article lays out a constructive framework for individualized and personalized medicine for the effective rehabilitation of FM patients. The quest to find a definitive diagnosis of FM should include personality biomarkers that might translate into personalized medicine. An individualistic approach may bank upon artificial intelligence algorithms for both diagnostic as well as prognostic purposes in FM.

SWOT analysis of noninvasive tests for diagnosing NAFLD with severe fibrosis: an expert review by the JANIT Forum

Nonalcoholic fatty liver disease (NAFLD) is the most common chronic liver disease. Nonalcoholic steatohepatitis (NASH) is an advanced form of NAFLD can progress to liver cirrhosis and hepatocellular carcinoma (HCC). Recently, the prognosis of NAFLD/NASH has been reported to be dependent on liver fibrosis degree. Liver biopsy remains the gold standard, but it has several issues that must be addressed, including its invasiveness, cost, and inter-observer diagnosis variability. To solve these issues, a variety of noninvasive tests (NITs) have been in development for the assessment of NAFLD progression, including blood biomarkers and imaging methods, although the use of NITs varies around the world. The aim of the Japan NASH NIT (JANIT) Forum organized in 2020 is to advance the development of various NITs to assess disease severity and/or response to treatment in NAFLD patients from a scientific perspective through multi-stakeholder dialogue with open innovation, including clinicians with expertise in NAFLD/NASH, companies that develop medical devices and biomarkers, and professionals in the pharmaceutical industry. In addition to conventional NITs, artificial intelligence will soon be deployed in many areas of the NAFLD landscape. To discuss the characteristics of each NIT, we conducted a SWOT (strengths, weaknesses, opportunities, and threats) analysis in this study with the 36 JANIT Forum members (16 physicians and 20 company representatives). Based on this SWOT analysis, the JANIT Forum identified currently available NITs able to accurately select NAFLD patients at high risk of NASH for HCC surveillance/therapeutic intervention and evaluate the effectiveness of therapeutic interventions.

Artificial intelligence in healthcare: Complementing, not replacing, doctors and healthcare providers

The utilization of artificial intelligence (AI) in clinical practice has increased and is evidently contributing to improved diagnostic accuracy, optimized treatment planning, and improved patient outcomes. The rapid evolution of AI, especially generative AI and large language models (LLMs), have reignited the discussions about their potential impact on the healthcare industry, particularly regarding the role of healthcare providers. Concerning questions, "can AI replace doctors?" and "will doctors who are using AI replace those who are not using it?" have been echoed. To shed light on this debate, this article focuses on emphasizing the augmentative role of AI in healthcare, underlining that AI is aimed to complement, rather than replace, doctors and healthcare providers. The fundamental solution emerges with the human-AI collaboration, which combines the cognitive strengths of healthcare providers with the analytical capabilities of AI. A human-in-the-loop (HITL) approach ensures that the AI systems are guided, communicated, and supervised by human expertise, thereby maintaining safety and quality in healthcare services. Finally, the adoption can be forged further by the organizational process informed by the HITL approach to improve multidisciplinary teams in the loop. AI can create a paradigm shift in healthcare by complementing and enhancing the skills of healthcare providers, ultimately leading to improved service quality, patient outcomes, and a more efficient healthcare system.

Comparisons between artificial intelligence computer-aided detection synthesized mammograms and digital mammograms when used alone and in combination with tomosynthesis images in a virtual screening setting

PURPOSE

To compare the reader performance of artificial intelligence computer-aided detection synthesized mammograms (AI CAD SM) with that of digital mammograms (DM) when used alone or in combination with digital breast tomosynthesis (DBT) images.

MATERIALS AND METHODS

This retrospective multireader (n = 4) study compared the reader performances in 388 cases (84 cancer, 83 benign, and 221 normal or benign cases). The overall accuracy of the breast-based assessment was determined by four radiologists using two sequential reading modes: DM followed by DM + DBT; and AI CAD SM followed by AI CAD SM + DBT. Each breast was rated by each reader using five-category ratings, where 3 or higher was considered positive. The area under the receiver-operating characteristic curve (AUC) and reading time were evaluated.

RESULTS

The mean AUC values for DM, AI CAD SM, DM + DBT, and AI CAD SM + DBT were 0.863, 0.895, 0.886, and 0.902, respectively. The mean AUC of AI CAD SM was significantly higher (P < 0.0001) than that of DM. The mean AUC of AI CAD SM + DBT was higher than that of DM + DBT (P = 0.094). A significant reduction in the reading time was observed after using AI CAD SM + DBT when compared with that after using DM + DBT (P < 0.001).

CONCLUSION

AI CAD SM + DBT might prove more effective than DM + DBT in a screening setting because of its lower radiation dose, noninferiority, and shorter reading time compared to DM + DBT.

Improving accessibility of scientific research by artificial intelligence-An example for lay abstract generation

The role of scientific research in modern society is essential for driving innovation, informing policy decisions, and shaping public opinion. However, communicating scientific findings to the general public can be challenging due to the technical and complex nature of scientific research. Lay abstracts are written summaries of scientific research that are designed to be easily understandable and provide a concise and clear overview of key findings and implications. Artificial intelligence language models have the potential to generate lay abstracts that are consistent and accurate while reducing the potential for misinterpretation or bias. This study presents examples of artificial intelligence-generated lay abstracts of recently published articles, which were produced using different currently available artificial intelligence tools. The generated abstracts were of high linguistic quality and accurately represented the findings of the original articles. Adopting lay summaries can increase the visibility, impact, and transparency of scientific research, and enhance scientists' reputation among peers, while currently, available artificial intelligence models offer solutions to produce lay abstracts. However, the coherence and accuracy of artificial intelligence language models must be validated before they can be used for this purpose without restrictions.

Online public discourse on artificial intelligence and ethics in China: context, content, and implications

The societal and ethical implications of artificial intelligence (AI) have sparked discussions among academics, policymakers and the public around the world. What has gone unnoticed so far are the likewise vibrant discussions in China. We analyzed a large sample of discussions about AI ethics on two Chinese social media platforms. Findings suggest that participants were diverse, and included scholars, IT industry actors, journalists, and members of the general public. They addressed a broad range of concerns associated with the application of AI in various fields. Some even gave recommendations on how to tackle these issues. We argue that these discussions are a valuable source for understanding the future trajectory of AI development in China as well as implications for global dialogue on AI governance.

Development of Internet suicide message identification and the Monitoring-Tracking-Rescuing model in Taiwan

BACKGROUND

Suicide messages can be transmitted infinitely online; the Internet is influential in suicide prevention. Identifying suicide risks online via artificial technological advances may help predict suicide.

METHODS

We built a classifier that detects open messages containing suicidal ideation or behavior-related words in social media via text mining methods and developed the Monitoring-Tracking-Rescuing model, which links data monitoring and tracking to high-risk suicide rescues. Natural language processing (NLP) techniques such as Long Short-Term Memory and Bidirectional Encoder Representations from Transformers were applied to online posts of common social media sites in Taiwan. This model uses a two-step high-risk identification procedure: an automatic prediction process using NLP to classify suicide-risk levels, followed by professional validation by a senior psychiatrist and a nursing faculty specialized in suicidology.

RESULTS

From a dataset containing 404 high-risk and 2226 no- or low-risk articles, the sensitivity and specificity of our model reached 80 %.

LIMITATIONS

The model is limited to data platforms that can be "crawled" and excludes suicide-risk content from graphics, video and audio files. Additionally, machine learning does not provide the best recognition rate from complex online messages. Keywords for high-risk suicide in long articles are difficult to interpret using this model. Finally, the model lacks keywords for suicide-protective factors.

CONCLUSIONS

Artificial intelligence techniques may help detect and monitor high-risk suicide posts and inform mental health professionals of these posts. Periodic tracking plus manual validation to determine risk levels are recommended to enhance the reliability and effectiveness of Internet suicide-prevention tasks.

[Development and validation of an automatic diagnostic tool for lumbar stability based on deep learning]

Objective

To develop an automatic diagnostic tool based on deep learning for lumbar spine stability and validate diagnostic accuracy.

Methods

Preoperative lumbar hyper-flexion and hyper-extension X-ray films were collected from 153 patients with lumbar disease. The following 5 key points were marked by 3 orthopedic surgeons: L₄ posteroinferior, anterior inferior angles as well as L₅ posterosuperior, anterior superior, and posterior inferior angles. The labeling results of each surgeon were preserved independently, and a total of three sets of labeling results were obtained. A total of 306 lumbar X-ray films were randomly divided into training (n=156), validation (n=50), and test (n=100) sets in a ratio of 3∶1∶2. A new neural network architecture, Swin-PGNet was proposed, which was trained using annotated radiograph images to automatically locate the lumbar vertebral key points and calculate L_{4, 5} intervertebral Cobb angle and L₄ lumbar sliding distance through the predicted key points. The mean error and intra-class correlation coefficient (ICC) were used as an evaluation index, to compare the differences between surgeons' annotations and Swin-PGNet on the three tasks (key point positioning, Cobb angle measurement, and lumbar sliding distance measurement). Meanwhile, the change of Cobb angle more than 11° was taken as the criterion of lumbar instability, and the lumbar sliding distance more than 3 mm was taken as the criterion of lumbar spondylolisthesis. The accuracy of surgeon annotation and Swin-PGNet in judging lumbar instability was compared.

Results

① Key point: The mean error of key point location by Swin-PGNet was (1.407±0.939) mm, and by different surgeons was (3.034±2.612) mm. ② Cobb angle: The mean error of Swin-PGNet was (2.062±1.352)° and the mean error of surgeons was (3.580±2.338)°. There was no significant difference between Swin-PGNet and surgeons (P>0.05), but there was a significant difference between different surgeons (P<0.05). ③ Lumbar sliding distance: The mean error of Swin-PGNet was (1.656±0.878) mm and the mean error of surgeons was (1.884±1.612) mm. There was no significant difference between Swin-PGNet and surgeons and between different surgeons (P>0.05). The accuracy of lumbar instability diagnosed by surgeons and Swin-PGNet was 75.3% and 84.0%, respectively. The accuracy of lumbar spondylolisthesis diagnosed by surgeons and Swin-PGNet was 70.7% and 71.3%, respectively. There was no significant difference between Swin-PGNet and surgeons, as well as between different surgeons (P>0.05). ④ Consistency of lumbar stability diagnosis: The ICC of Cobb angle among different surgeons was 0.913 [95%CI (0.898, 0.934)] (P<0.05), and the ICC of lumbar sliding distance was 0.741 [95%CI (0.729, 0.796)] (P<0.05). The result showed that the annotating of the three surgeons were consistent. The ICC of Cobb angle between Swin-PGNet and surgeons was 0.922 [95%CI (0.891, 0.938)] (P<0.05), and the ICC of lumbar sliding distance was 0.748 [95%CI(0.726, 0.783)] (P<0.05). The result showed that the annotating of Swin-PGNet were consistent with those of surgeons.

Conclusion

The automatic diagnostic tool for lumbar instability constructed based on deep learning can realize the automatic identification of lumbar instability and spondylolisthesis accurately and conveniently, which can effectively assist clinical diagnosis.

An ECG-based machine learning model for predicting new-onset atrial fibrillation is superior to age and clinical features in identifying patients at high stroke risk

BACKGROUND

Several large trials have employed age or clinical features to select patients for atrial fibrillation (AF) screening to reduce strokes. We hypothesized that a machine learning (ML) model trained to predict AF risk from 12‑lead electrocardiogram (ECG) would be more efficient than criteria based on clinical variables in indicating a population for AF screening to potentially prevent AF-related stroke.

METHODS

We retrospectively included all patients with clinical encounters in Geisinger without a prior history of AF. Incidence of AF within 1 year and AF-related strokes within 3 years of the encounter were identified. AF-related stroke was defined as a stroke where AF was diagnosed at the time of stroke or within a year after the stroke. The efficiency of five methods was evaluated for selecting a cohort for AF screening. The methods were selected from four clinical trials (mSToPS, GUARD-AF, SCREEN-AF and STROKESTOP) and the ECG-based ML model. We simulated patient selection for the five methods between the years 2011 and 2014 and evaluated outcomes for 1 year intervals between 2012 and 2015, resulting in a total of twenty 1-year periods. Patients were considered eligible if they met the criteria before the start of the given 1-year period or within that period. The primary outcomes were numbers needed to screen (NNS) for AF and AF-associated stroke.

RESULTS

The clinical trial models indicated large proportions of the population with a prior ECG for AF screening (up to 31%), coinciding with NNS ranging from 14 to 18 for AF and 249-359 for AF-associated stroke. At comparable sensitivity, the ECG ML model indicated a modest number of patients for screening (14%) and had the highest efficiency in NNS for AF (7.3; up to 60% reduction) and AF-associated stroke (223; up to 38% reduction).

CONCLUSIONS

An ECG-based ML risk prediction model is more efficient than contemporary AF-screening criteria based on age alone or age and clinical features at indicating a population for AF screening to potentially prevent AF-related strokes.

Review of Artificial Intelligence-Based Signal Processing in Dialysis: Challenges for Machine-Embedded and Complementary Applications

Artificial intelligence technology is trending in nearly every medical area. It offers the possibility for improving analytics, therapy outcome, and user experience during therapy. In dialysis, the application of artificial intelligence as a therapy-individualization tool is led more by start-ups than consolidated players, and innovation in dialysis seems comparably stagnant. Factors such as technical requirements or regulatory processes are important and necessary but can slow down the implementation of artificial intelligence due to missing data infrastructure and undefined approval processes. Current research focuses mainly on analyzing health records or wearable technology to add to existing health data. It barely uses signal data from treatment devices to apply artificial intelligence models. This article, therefore, discusses requirements for signal processing through artificial intelligence in health care and compares these with the status quo in dialysis therapy. It offers solutions for given barriers to speed up innovation with sensor data, opening access to existing and untapped sources, and shows the unique advantage of signal processing in dialysis compared to other health care domains. This research shows that even though the combination of different data is vital for improving patients' therapy, adding signal-based treatment data from dialysis devices to the picture can benefit the understanding of treatment dynamics, improving and individualizing therapy.

Contemporary Advances in Computer-Assisted Bone Histomorphometry and Identification of Bone Cells in Culture

Static and dynamic bone histomorphometry and identification of bone cells in culture are labor-intensive and highly repetitive tasks. Several computer-assisted methods have been proposed to ease these tasks and to take advantage of the increased computational power available today. The present review aimed to provide an overview of contemporary methods utilizing specialized computer software to perform bone histomorphometry or identification of bone cells in culture. In addition, a brief historical perspective on bone histomorphometry is included. We identified ten publications using five different computer-assisted approaches (1) ImageJ and BoneJ; (2) Histomorph: OsteoidHisto, CalceinHisto, and TrapHisto; (3) Fiji/ImageJ2 and Trainable Weka Segmentation (TWS); (4) Visiopharm and artificial intelligence (AI); and (5) Osteoclast identification using deep learning with Single Shot Detection (SSD) architecture, Darknet and You Only Look Once (YOLO), or watershed algorithm (OC_Finder). The review also highlighted a substantial need for more validation studies that evaluate the accuracy of the new computational methods to the manual and conventional analyses of histological bone specimens and cells in culture using microscopy. However, a substantial evolution has occurred during the last decade to identify and separate bone cells and structures of interest. Most early studies have used simple image segmentation to separate structures of interest, whereas the most recent studies have utilized AI and deep learning. AI has been proposed to substantially decrease the amount of time needed for analyses and enable unbiased assessments. Despite the clear advantages of highly sophisticated computational methods, the limited nature of existing validation studies, particularly those that assess the accuracy of the third-generation methods compared to the second-generation methods, appears to be an important reason that these techniques have failed to gain wide acceptance.

Mapping the forest fire risk zones using artificial intelligence with risk factors data

Geographical information system data has been used in forest fire risk zone mapping studies commonly. However, forest fires are caused by many factors, which cannot be explained only by geographical and meteorological reasons. Human-induced factors also play an important role in occurrence of forest fires, and these factors depend on various social and economic conditions. This article aims to prepare a fire risk zone map by using a data set consisting of 11 human-induced factors, a natural factor, and temperature, which is one of the risk factors that determine the conditions for the occurrence of forest fires. Moreover, k-means clustering algorithm, which is an artificial intelligence method, was employed in preparation of the fire risk zone map. Turkey was selected as the study area because there are social and economic variations among its regions. Thus, the regional forest directorates in Turkey were separated into four clusters as extreme-risk zone, high-risk zone, moderate-risk zone, and low-risk zone. Also, a map presenting these risk zones were provided. The map reveals that, in general, the western and southwestern coastal areas of Turkey are at high risk of forest fires. On the other hand, the fire risk is relatively low in the northern, central, and eastern areas.

An artificial intelligence-based chatbot for prostate cancer education: Design and patient evaluation study

Introduction

Artificial intelligence (AI) is increasingly used in healthcare. AI-based chatbots can act as automated conversational agents, capable of promoting health and providing education at any time. The objective of this study was to develop and evaluate a user-friendly medical chatbot (prostate cancer communication assistant (PROSCA)) for provisioning patient information about early detection of prostate cancer (PC).

Methods

The chatbot was developed to provide information on prostate diseases, diagnostic tests for PC detection, stages, and treatment options. Ten men aged 49 to 81 years with suspicion of PC were enrolled in this study. Nine of ten patients used the chatbot during the evaluation period and filled out the questionnaires on usage and usability, perceived benefits, and potential for improvement.

Results

The chatbot was straightforward to use, with 78% of users not needing any assistance during usage. In total, 89% of the chatbot users in the study experienced a clear to moderate increase in knowledge about PC through the chatbot. All study participants who tested the chatbot would like to re-use a medical chatbot in the future and support the use of chatbots in the clinical routine.

Conclusions

Through the introduction of the chatbot PROSCA, we created and evaluated an innovative evidence-based health information tool in the field of PC, allowing targeted support for doctor-patient communication and offering great potential in raising awareness, patient education, and support. Our study revealed that a medical chatbot in the field of early PC detection is readily accepted and benefits patients as an additional informative tool.

Radiogenomic markers enable risk stratification and inference of mutational pathway states in head and neck cancer

PURPOSE

Head and neck squamous cell carcinomas (HNSCCs) are a molecularly, histologically, and clinically heterogeneous set of tumors originating from the mucosal epithelium of the oral cavity, pharynx, and larynx. This heterogeneous nature of HNSCC is one of the main contributing factors to the lack of prognostic markers for personalized treatment. The aim of this study was to develop and identify multi-omics markers capable of improved risk stratification in this highly heterogeneous patient population.

METHODS

In this retrospective study, we approached this issue by establishing radiogenomics markers to identify high-risk individuals in a cohort of 127 HNSCC patients. Hybrid in vivo imaging and whole-exome sequencing were employed to identify quantitative imaging markers as well as genetic markers on pathway-level prognostic in HNSCC. We investigated the deductibility of the prognostic genetic markers using anatomical and metabolic imaging using positron emission tomography combined with computed tomography. Moreover, we used statistical and machine learning modeling to investigate whether a multi-omics approach can be used to derive prognostic markers for HNSCC.

RESULTS

Radiogenomic analysis revealed a significant influence of genetic pathway alterations on imaging markers. A highly prognostic radiogenomic marker based on cellular senescence was identified. Furthermore, the radiogenomic biomarkers designed in this study vastly outperformed the prognostic value of markers derived from genetics and imaging alone.

CONCLUSION

Using the identified markers, a clinically meaningful stratification of patients is possible, guiding the identification of high-risk patients and potentially aiding in the development of effective targeted therapies.