GANDALF: Graph-based transformer and Data Augmentation Active Learning Framework with interpretable features for multi-label chest Xray classification

Informative sample selection in an active learning (AL) setting helps a machine learning system attain optimum performance with minimum labeled samples, thus reducing annotation costs and boosting performance of computer-aided diagnosis systems in the presence of limited labeled data. Another effective technique to enlarge datasets in a small labeled data regime is data augmentation. An intuitive active learning approach thus consists of combining informative sample selection and data augmentation to leverage their respective advantages and improve the performance of AL systems. In this paper, we propose a novel approach called GANDALF (Graph-based TrANsformer and Data Augmentation Active Learning Framework) to combine sample selection and data augmentation in a multi-label setting. Conventional sample selection approaches in AL have mostly focused on the single-label setting where a sample has only one disease label. These approaches do not perform optimally when a sample can have multiple disease labels (e.g., in chest X-ray images). We improve upon state-of-the-art multi-label active learning techniques by representing disease labels as graph nodes and use graph attention transformers (GAT) to learn more effective inter-label relationships. We identify the most informative samples by aggregating GAT representations. Subsequently, we generate transformations of these informative samples by sampling from a learned latent space. From these generated samples, we identify informative samples via a novel multi-label informativeness score, which beyond the state of the art, ensures that (i) generated samples are not redundant with respect to the training data and (ii) make important contributions to the training stage. We apply our method to two public chest X-ray datasets, as well as breast, dermatology, retina and kidney tissue microscopy MedMNIST datasets, and report improved results over state-of-the-art multi-label AL techniques in terms of model performance, learning rates, and robustness.

In silico drug repurposing by combining machine learning classification model and molecular dynamics to identify a potential OGT inhibitor

O-linked N-acetylglucosamine (O-GlcNAc) is a unique intracellular post-translational glycosylation at the hydroxyl group of serine or threonine residues in nuclear, cytoplasmic and mitochondrial proteins. The enzyme O-GlcNAc transferase (OGT) is responsible for adding GlcNAc, and anomalies in this process can lead to the development of diseases associated with metabolic imbalance, such as diabetes and cancer. Repurposing approved drugs can be an attractive tool to discover new targets reducing time and costs in the drug design. This work focuses on drug repurposing to OGT targets by virtual screening of FDA-approved drugs through consensus machine learning (ML) models from an imbalanced dataset. We developed a classification model using docking scores and ligand descriptors. The SMOTE approach to resampling the dataset showed excellent statistical values in five of the seven ML algorithms to create models from the training set, with sensitivity, specificity and accuracy over 90% and Matthew's correlation coefficient greater than 0.8. The pose analysis obtained by molecular docking showed only H-bond interaction with the OGT C-Cat domain. The molecular dynamics simulation showed the lack of H-bond interactions with the C- and N-catalytic domains allowed the drug to exit the binding site. Our results showed that the non-steroidal anti-inflammatory celecoxib could be a potentially OGT inhibitor.

Using classification trees to identify psychotherapy patients at risk for poor treatment adherence

To determine the relative importance of a wide variety of personality and psychopathology variables in influencing patients' adherence to psychotherapy treatment.

Two classification trees were trained to predict patients' (1) treatment utilization (i.e., their likelihood of missing a given appointment) and (2) termination status (i.e., their likelihood of dropping out of therapy prematurely). Each tree was then validated in an external dataset to examine performance accuracy.

Patients' social detachment was most influential in predicting their treatment utilization, followed by affective instability and activity/energy levels. Patients' interpersonal warmth was most influential in predicting their termination status, followed by levels of disordered thought and resentment. The overall accuracy rating for the tree for termination status was 71.4%, while the tree for treatment utilization had a 38.7% accuracy rating.

Classification trees are a practical tool for clinicians to determine patients at risk of premature termination. More research is needed to develop trees that predict treatment utilization with high accuracy across different types of patients and settings.

Early Detection of Oral Potentially Malignant Disorders: A Review on Prospective Screening Methods with Regard to Global Challenges

Oral cancer is a cancer type that is widely prevalent in low-and middle-income countries with a high mortality rate, and poor quality of life for patients after treatment. Early treatment of cancer increases patient survival, improves quality of life and results in less morbidity and a better prognosis. To reach this goal, early detection of malignancies using technologies that can be used in remote and low resource areas is desirable. Such technologies should be affordable, accurate, and easy to use and interpret. This review surveys different technologies that have the potentials of implementation in primary health and general dental practice, considering global perspectives and with a focus on the population in India, where oral cancer is highly prevalent. The technologies reviewed include both sample-based methods, such as saliva and blood analysis and brush biopsy, and more direct screening of the oral cavity including fluorescence, Raman techniques, and optical coherence tomography. Digitalisation, followed by automated artificial intelligence based analysis, are key elements in facilitating wide access to these technologies, to non-specialist personnel and in rural areas, increasing quality and objectivity of the analysis while simultaneously reducing the labour and need for highly trained specialists.

Environmental-Driven Approach towards Level 5 Self-Driving

As technology advances in almost all areas of life, many companies and researchers are working to develop fully autonomous vehicles. Such level 5 autonomous driving, unlike levels 0 to 4, is a driverless vehicle stage and so the leap from level 4 to level 5 autonomous driving requires much more research and experimentation. For autonomous vehicles to safely drive in complex environments, autonomous cars should ensure end-to-end delay deadlines of sensor systems and car-controlling algorithms including machine learning modules, which are known to be very computationally intensive. To address this issue, we propose a new framework, i.e., an environment-driven approach for autonomous cars. Specifically, we identify environmental factors that we cannot control at all, and controllable internal factors such as sensing frequency, image resolution, prediction rate, car speed, and so on. Then, we design an admission control module that allows us to control internal factors such as image resolution and detection period to determine whether given parameters are acceptable or not for supporting end-to-end deadlines in the current environmental scenario while maintaining the accuracy of autonomous driving. The proposed framework has been verified with an RC car and a simulator.

Affect and stress detection based on feature fusion of LSTM and 1DCNN

The impact of emotions on health, especially stress, is receiving increasing attention. It is important to provide a non-invasive affect detection system that can be continuously monitored for a long period of time. Multi-sensor fusion strategies can better improve the performance of affect detection models, but there are also problems such as insufficient feature extraction and poor spatiotemporal feature fusion. Therefore, this study proposes a feature-level fusion method based on long short-term memory and one-dimensional convolutional neural network to extract temporal and spatial features of electrocardiogram, electromyogram, electrical activity, temperature, accelerator and response data, respectively, and then fuse them in a summation fashion for affect and stress detection. In particular, we added the tanh activation function before feature fusion, which can improve the model's performance. We used the wearable affect and stress detection dataset to train the model, which includes three different emotion states (neutral, stress, and amusement) for three-class emotion classification with accuracy and F1-scores of 87.82% and 86.68%, respectively. Due to the importance of stress, we also studied binary classification for stress detection, where neutral and amusement were combined as non-stress, with accuracy and F1-scores of 94.9% and 94.98%, respectively. The performance of the proposed model outperforms other control models and can effectively improve the performance of affect and stress detection, and promote medical care, health care and elderly care.

Computer-aided craniofacial superimposition validation study: the identification of the leaders and participants of the Polish-Lithuanian January Uprising (1863-1864)

In 2017, a series of human remains corresponding to the executed leaders of the "January Uprising" of 1863-1864 were uncovered at the Upper Castle of Vilnius (Lithuania). During the archeological excavations, 14 inhumation pits with the human remains of 21 individuals were found at the site. The subsequent identification process was carried out, including the analysis and cross-comparison of post-mortem data obtained in situ and in the lab with ante-mortem data obtained from historical archives. In parallel, three anthropologists with diverse backgrounds in craniofacial identification and two students without previous experience attempted to identify 11 of these 21 individuals using the craniofacial superimposition technique. To do this, the five participants had access to 18 3D scanned skulls and 14 photographs of 11 different candidates. The participants faced a cross-comparison problem involving 252 skull-face overlay scenarios. The methodology follows the main agreements of the European project MEPROCS and uses the software Skeleton-ID™. Based on MEPROCS standard, a final decision was provided within a scale, assigning a value in terms of strong, moderate, or limited support to the claim that the skull and the facial image belonged (or not) to the same person for each case. The problem of binary classification, positive/negative, with an identification rate for each participant was revealed. The results obtained in this study make the authors think that both the quality of the materials used and the previous experience of the analyst play a fundamental role when reaching conclusions using the CFS technique.

Multi-classification of national fitness test grades based on statistical analysis and machine learning

Physical fitness is a key element of a healthy life, and being overweight or lacking physical exercise will lead to health problems. Therefore, assessing an individual's physical health status from a non-medical, cost-effective perspective is essential. This paper aimed to evaluate the national physical health status through national physical examination data, selecting 12 indicators to divide the physical health status into four levels: excellent, good, pass, and fail. The existing challenge lies in the fact that most literature on physical fitness assessment mainly focuses on the two major groups of sports athletes and school students. Unfortunately, there is no reasonable index system has been constructed. The evaluation method has limitations and cannot be applied to other groups. This paper builds a reasonable health indicator system based on national physical examination data, breaks group restrictions, studies national groups, and hopes to use machine learning models to provide helpful health suggestions for citizens to measure their physical status. We analyzed the significance of the selected indicators through nonparametric tests and exploratory statistical analysis. We used seven machine learning models to obtain the best multi-classification model for the physical fitness test level. Comprehensive research showed that MLP has the best classification effect, with macro-precision reaching 74.4% and micro-precision reaching 72.8%. Furthermore, the recall rates are also above 70%, and the Hamming loss is the smallest, i.e., 0.272. The practical implications of these findings are significant. Individuals can use the classification model to understand their physical fitness level and status, exercise appropriately according to the measurement indicators, and adjust their lifestyle, which is an important aspect of health management.

Detection and explanation of anomalies in healthcare data

The growth of databases in the healthcare domain opens multiple doors for machine learning and artificial intelligence technology. Many medical devices are available in the medical field; however, medical errors remain a severe challenge. Different algorithms are developed to identify and solve medical errors, such as detecting anomalous readings, anomalous health conditions of a patient, etc. However, they fail to answer why those entries are considered an anomaly. This research gap leads to an outlying aspect mining problem. The problem of outlying aspect mining aims to discover the set of features (a.k.a subspace) in which the given data point is dramatically different than others. In this paper, we present a framework that detects anomalies in healthcare data and then provides an explanation of anomalies. This paper aims to effectively and efficiently detect anomalies and explain why they are considered anomalies by detecting outlying aspects. First, we re-introduced four anomaly detection techniques and outlying aspect mining algorithms. Then, we evaluate the performance of anomaly detection techniques and choose the best anomaly detection algorithm. Later, we detect the top k anomaly as a query and detect their outlying aspect. Lastly, we evaluate their performance on 16 real-world healthcare datasets. The experimental results show that the latest isolation-based outlying aspect mining measure, SiNNE, has outstanding performance on this task and has promising results.

How do researchers perceive research misbehaviors? A case study of Indian researchers

Despite ample evidence of increasing research misconduct in India, little attention has been paid to understanding researchers' perception of research integrity and research misconduct among young Indian researchers. Interviews among 30 research scholars were conducted at Pondicherry University in India to understand their experience and perception of research misconduct. The top three influencing factors for scientific misconduct, according to the participants, were unavailability of adequate funds (35%), pressure from research supervisors (29%), and desperation to publish articles (25%). The participants had witnessed research misconduct in different forms i.e., data fabrication, falsification, and plagiarism. However, plagiarism was the most often cited cause of misbehavior in our interviews. Majority of participants have witnessed or personally encountered multiple instances where authorship conflicts occurred. The other questionable research practices highlighted in the study were improper citations, authorship disputes like gift and ghost authorships, misrepresentation of statistical data, failure to publish negative results. In an increasingly diverse and changing research environment, our research calls for practical research guidelines based on honesty, openness, and accountability that can help articulate and strengthen scientists' core values. More importantly, scientific misconduct can only be prevented by using a multifaceted strategy that includes identifying instances of scientific misconduct and implementing suitable deterrents and treatments that could change the behavior associated with such misconduct.

Embedding-based link predictions to explore latent comorbidity of chronic diseases

Purpose

Comorbidity is a term used to describe when a patient simultaneously has more than one chronic disease. Comorbidity is a significant health issue that affects people worldwide. This study aims to use machine learning and graph theory to predict the comorbidity of chronic diseases.

Methods

A patient-disease bipartite graph is constructed based on the administrative claim data. The bipartite graph projection approach was used to create the comorbidity network. For the link prediction task, three graph machine learning embedding-based models (node2vec, graph neural networks and hand-crafted approach) with different variants were used on the comorbidity network to compare their performance. This study also considered three commonly used similarity-based link prediction approaches (Jaccard coefficient, Adamic-Adar index and Resource allocation index) for performance comparison.

Results

The results showed that the embedding-based hand-crafted features technique achieved outstanding performance compared with the remaining similarity-based and embedding-based models. Especially, the hand-crafted technique with the extreme gradient boosting classifier achieved the highest accuracy (91.67%), followed by the same technique with the Logistic regression classifier (90.26%). For this shallow embedding method, the Jaccard coefficient and the degree centrality of the original chronic disease were the most important features for comorbidity prediction.

Conclusion

The proposed framework can be used to predict the comorbidity of chronic disease at an early stage of hospital admission. Thus, the prediction outcome could be valuable for medical practice, giving healthcare providers more control over their services and lowering expenses.

MHA: a multimodal hierarchical attention model for depression detection in social media

As a serious mental disease, depression causes great harm to the physical and mental health of individuals, and becomes an important cause of suicide. Therefore, it is necessary to accurately identify and treat depressed patients. Compared with traditional clinical diagnosis methods, a large amount of real and different types of data on social media provides new ideas for depression detection research. In this paper, we construct a depression detection data set based on Weibo, and propose a Multimodal Hierarchical Attention (MHA) model for social media depression detection. Multimodal data is fed into the model and the attention mechanism is applied within and between modalities at the same time. Experimental results show that the proposed model achieves the best classification performance. In addition, we propose a distribution normalization method, which can optimize the data distribution and improve the accuracy of depression detection.

Donor sibling relations among adult offspring conceived via insemination by lesbian parents

STUDY QUESTION

How do adult offspring in planned lesbian-parent families feel about and relate to their donor (half) sibling(s) (DS)?

SUMMARY ANSWER

A majority of offspring had found DS and maintained good ongoing relationships, and all offspring (regardless of whether a DS had been identified) were satisfied with their knowledge of and contact level with the DS.

WHAT IS KNOWN ALREADY

The first generation of donor insemination offspring of intended lesbian-parent families is now in their 30s. Coincident with this is an increased use of DNA testing and genetic ancestry websites, facilitating the discovery of donor siblings from a common sperm donor. Few studies of offspring and their DS include sexual minority parent (SMP) families, and only sparse data separately analyze the offspring of SMP families or extend the analyses to established adult offspring.

STUDY DESIGN, SIZE, DURATION

This cohort study included 75 adult offspring, longitudinally followed since conception in lesbian-parent families. Quantitative analyses were performed from online surveys of the offspring in the seventh wave of the 36-year study, with a 90% family retention rate. The data were collected from March 2021 to November 2022.

PARTICIPANTS/MATERIALS, SETTING, METHODS

Participants were 30- to 33-year-old donor insemination offspring whose lesbian parents enrolled in a US prospective longitudinal study when these offspring were conceived. Offspring who knew of a DS were asked about their numbers found, characteristics or motivations for meeting, DS terminology, relationship quality and maintenance, and impact of the DS contact on others. All offspring (with or without known DS) were asked about the importance of knowing if they have DS and their terminology, satisfaction with information about DS, and feelings about future contact.

MAIN RESULTS AND THE ROLE OF CHANCE

Of offspring, 53% (n = 40) had found DS in modest numbers, via a DS or sperm bank registry in 45% of cases, and most of these offspring had made contact. The offspring had their meeting motivations fulfilled, viewed the DS as acquaintances more often than siblings or friends, and maintained good relationships via meetings, social media, and cell phone communication. They disclosed their DS meetings to most relatives with neutral impact. The offspring, whether with known or unknown DS, felt neutral about the importance of knowing if they had DS, were satisfied with what they knew (or did not know) of the DS, and were satisfied with their current level of DS contact. This study is the largest, longest-running longitudinal study of intended lesbian-parent families and their offspring, and due to its prospective nature, is not biased by over-sampling offspring who were already satisfied with their DS.

LIMITATIONS, REASONS FOR CAUTION

The sample was from the USA, and mostly White, highly educated individuals, not representative of the diversity of donor insemination offspring of lesbian-parent families.

WIDER IMPLICATIONS OF THE FINDINGS

While about half of the offspring found out about DS, the other half did not. Regardless of knowing of a DS, these adult offspring of lesbian parents were satisfied with their level of DS contact. Early disclosure and identity formation about being donor-conceived in a lesbian-parent family may distinguish these study participants from donor insemination offspring and adoptees in the general population, who may be more compelled to seek genetic relatives. The study participants who sought DS mostly found a modest number of them, in contrast to reports in studies that have found large numbers of DS. This may be because one-third of study offspring had donors known to the families since conception, who may have been less likely to participate in commercial sperm banking or internet donation sites, where quotas are difficult to enforce or nonexistent. The study results have implications for anyone considering gamete donation, gamete donors, donor-conceived offspring, and/or gamete banks, as well as the medical and public policy professionals who advise them.

STUDY FUNDING/COMPETING INTEREST(S)

No funding was provided for this project. The authors have no competing interests.

TRIAL REGISTRATION NUMBER

N/A.

(Why) Is Misinformation a Problem?

In the last decade there has been a proliferation of research on misinformation. One important aspect of this work that receives less attention than it should is exactly why misinformation is a problem. To adequately address this question, we must first look to its speculated causes and effects. We examined different disciplines (computer science, economics, history, information science, journalism, law, media, politics, philosophy, psychology, sociology) that investigate misinformation. The consensus view points to advancements in information technology (e.g., the Internet, social media) as a main cause of the proliferation and increasing impact of misinformation, with a variety of illustrations of the effects. We critically analyzed both issues. As to the effects, misbehaviors are not yet reliably demonstrated empirically to be the outcome of misinformation; correlation as causation may have a hand in that perception. As to the cause, advancements in information technologies enable, as well as reveal, multitudes of interactions that represent significant deviations from ground truths through people's new way of knowing (intersubjectivity). This, we argue, is illusionary when understood in light of historical epistemology. Both doubts we raise are used to consider the cost to established norms of liberal democracy that come from efforts to target the problem of misinformation.

A perspective on data sharing in digital food safety systems

In this age of data, digital tools are widely promoted as having tremendous potential for enhancing food safety. However, the potential of these digital tools depends on the availability and quality of data, and a number of obstacles need to be overcome to achieve the goal of digitally enabled "smarter food safety" approaches. One key obstacle is that participants in the food system and in food safety often lack the willingness to share data, due to fears of data abuse, bad publicity, liability, and the need to keep certain data (e.g., human illness data) confidential. As these multifaceted concerns lead to tension between data utility and privacy, the solutions to these challenges need to be multifaceted. This review outlines the data needs in digital food safety systems, exemplified in different data categories and model types, and key concerns associated with sharing of food safety data, including confidentiality and privacy of shared data. To address the data privacy issue a combination of innovative strategies to protect privacy as well as legal protection against data abuse need to be pursued. Existing solutions for maximizing data utility, while not compromising data privacy, are discussed, most notably differential privacy and federated learning.

Use of artificial intelligence to identify data elements for The Japanese Orthopaedic Association National Registry from operative records

BACKGROUND

The Japanese Orthopaedic Association National Registry (JOANR) was recently launched in Japan and is expected to improve the quality of medical care. However, surgeons must register ten detailed features for total hip arthroplasty, which is labor intensive. One possible solution is to use a system that automatically extracts information about the surgeries. Although it is not easy to extract features from an operative record consisting of free-text data, natural language processing has been used to extract features from operative records. This study aimed to evaluate the best natural language processing method for building a system that automatically detects some elements in the JOANR from the operative records of total hip arthroplasty.

METHODS

We obtained operative records of total hip arthroplasty (n = 2574) in three hospitals and targeted two items: surgical approach and fixation technique. We compared the accuracy of three natural language processing methods: rule-based algorithms, machine learning, and bidirectional encoder representations from transformers (BERT).

RESULTS

In the surgical approach task, the accuracy of BERT was superior to that of the rule-based algorithm (99.6% vs. 93.6%, p < 0.001), comparable to machine learning. In the fixation technique task, the accuracy of BERT was superior to the rule-based algorithm and machine learning (96% vs. 74%, p < 0.0001 and 94%, p = 0.0004).

CONCLUSIONS

BERT is the most appropriate method for building a system that automatically detects the surgical approach and fixation technique.

Ensuring Trust in Genomics Research

Reproducibility, transparency, representation, and privacy underpin the trust on genomics research in general and genome-wide association studies (GWAS) in particular. Concerns about these issues can be mitigated by technologies that address privacy protection, quality control, and verifiability of GWAS. However, many of the existing technological solutions have been developed in isolation and may address one aspect of reproducibility, transparency, representation, and privacy of GWAS while unknowingly impacting other aspects. As a consequence, the current patchwork of technological tools only partially and in an overlapping manner address issues with GWAS, sometimes even creating more problems. This paper addresses the progress in a field that creates technological solutions that augment the acceptance and security of population genetic analyses. The text identifies areas that are falling behind in technical implementation or where there is insufficient research. We make the case that a full understanding of the different GWAS settings, technological tools and new research directions can holistically address the requirements for the acceptance of GWAS.

Learning a simulation-based visual policy for real-world peg in unseen holes

This paper proposes a learning-based visual peg-in-hole that enables training with several shapes in simulation and adapting to arbitrary unseen shapes in the real world with minimal sim-to-real cost. The core idea is to decouple the generalization of the sensory-motor policy from the design of a fast-adaptable perception module and a simulated generic policy module. The framework consists of a segmentation network (SN), a virtual sensor network (VSN), and a controller network (CN). Concretely, the VSN is trained to measure the pose of the unseen shape from a segmented image. After that, given the shape-agnostic pose measurement, the CN is trained to achieve a generic peg-in-hole. Finally, when applying to real unseen holes, we only have to fine-tune the SN required by the simulated VSN + CN. To further minimize the transfer cost, we propose to automatically collect and annotate the data for the SN after one-minute human teaching. Simulated and real-world results are presented under the configuration of eye-to/in-hand. An electric vehicle charging system with the proposed policy inside achieves a 10/10 success rate in 2-3 s, using only hundreds of auto-labeled samples for the SN transfer.

DeepBSRPred: deep learning-based binding site residue prediction for proteins

MOTIVATION

Proteins-protein interactions (PPIs) are important to govern several cellular activities. Amino acid residues, which are located at the interface are known as the binding sites and the information about binding sites helps to understand the binding affinities and functions of protein-protein complexes.

RESULTS

We have developed a deep neural network-based method, DeepBSRPred, for predicting the binding sites using protein sequence information and predicted structures from AlphaFold2. Specific sequence and structure-based features include position-specific scoring matrix (PSSM), solvent accessible surface area, conservation score and amino acid properties, and residue depth, respectively. Our method predicted the binding sites with an average F1 score of 0.73 in a dataset of 1236 proteins. Further, we compared the performance with other existing methods in the literature using four benchmark datasets and our method outperformed those methods.

AVAILABILITY AND IMPLEMENTATION

The DeepBSRPred web server can be found at https://web.iitm.ac.in/bioinfo2/deepbsrpred/index.html , along with all datasets used in this study. The trained models, the DeepBSRPred standalone source code, and the feature computation pipeline are freely available at https://web.iitm.ac.in/bioinfo2/deepbsrpred/download.html .

Data drift in medical machine learning: implications and potential remedies

Data drift refers to differences between the data used in training a machine learning (ML) model and that applied to the model in real-world operation. Medical ML systems can be exposed to various forms of data drift, including differences between the data sampled for training and used in clinical operation, differences between medical practices or context of use between training and clinical use, and time-related changes in patient populations, disease patterns, and data acquisition, to name a few. In this article, we first review the terminology used in ML literature related to data drift, define distinct types of drift, and discuss in detail potential causes within the context of medical applications with an emphasis on medical imaging. We then review the recent literature regarding the effects of data drift on medical ML systems, which overwhelmingly show that data drift can be a major cause for performance deterioration. We then discuss methods for monitoring data drift and mitigating its effects with an emphasis on pre- and post-deployment techniques. Some of the potential methods for drift detection and issues around model retraining when drift is detected are included. Based on our review, we find that data drift is a major concern in medical ML deployment and that more research is needed so that ML models can identify drift early, incorporate effective mitigation strategies and resist performance decay.

Morphology of possible regions in elite soccer players

The popularity of spatio-temporal analyses in soccer is increasing. As many of these analyses depend on the regions a player can occupy in a certain amount of time (the possible regions), the understanding of this concepts is important for analyses to produce usable results. This study investigated how possible regions of soccer morph with varying times and running speeds. Twenty-four players from the Danish Superliga participated, and 13 players were analysed. The possible regions were analysed with times from 0.5 to 4 s (0.5 s increments) and initial velocities from 1 to 7 m/s (1 m/s increments). In this study, we showed that the possible regions can be described by ellipses (eccentricity of 0.5348 ± 0.1912). When comparing the possible region ellipses at every time and velocity pair, 1.95 % of the ellipses were not significantly different from the others. In conclusion, possible regions are unique in shape and size depending on player running speed and time available. However, as only few strikers participated, the results for this group should be interpreted with caution. Coaches can predict possible regions based on these parameters increasing precision of post-game analyses.

Artificial Intelligence for Automated Implant Identification in Total Hip Arthroplasty: A Multicenter External Validation Study Exceeding Two Million Plain Radiographs

BACKGROUND

The surgical management of complications after total hip arthroplasty (THA) necessitates accurate identification of the femoral implant manufacturer and model. Automated image processing using deep learning has been previously developed and internally validated; however, external validation is necessary prior to responsible application of artificial intelligence (AI)-based technologies.

METHODS

We trained, validated, and externally tested a deep learning system to classify femoral-sided THA implants as one of the 8 models from 2 manufacturers derived from 2,954 original, deidentified, retrospectively collected anteroposterior plain radiographs across 3 academic referral centers and 13 surgeons. From these radiographs, 2,117 were used for training, 249 for validation, and 588 for external testing. Augmentation was applied to the training set (n = 2,117,000) to increase model robustness. Performance was evaluated by area under the receiver operating characteristic curve, sensitivity, specificity, and accuracy. Implant identification processing speed was calculated.

RESULTS

The training and testing sets were drawn from statistically different populations of implants (P < .001). After 1,000 training epochs by the deep learning system, the system discriminated 8 implant models with a mean area under the receiver operating characteristic curve of 0.991, accuracy of 97.9%, sensitivity of 88.6%, and specificity of 98.9% in the external testing dataset of 588 anteroposterior radiographs. The software classified implants at a mean speed of 0.02 seconds per image.

CONCLUSION

An AI-based software demonstrated excellent internal and external validation. Although continued surveillance is necessary with implant library expansion, this software represents responsible and meaningful clinical application of AI with immediate potential to globally scale and assist in preoperative planning prior to revision THA.

Collaborative Perception-The Missing Piece in Realizing Fully Autonomous Driving

Environment perception plays a crucial role in enabling collaborative driving automation, which is considered to be the ground-breaking solution to tackling the safety, mobility, and sustainability challenges of contemporary transportation systems. Despite the fact that computer vision for object perception is undergoing an extraordinary evolution, single-vehicle systems' constrained receptive fields and inherent physical occlusion make it difficult for state-of-the-art perception techniques to cope with complex real-world traffic settings. Collaborative perception (CP) based on various geographically separated perception nodes was developed to break the perception bottleneck for driving automation. CP leverages vehicle-to-vehicle and vehicle-to-infrastructure communication to enable vehicles and infrastructure to combine and share information to comprehend the surrounding environment beyond the line of sight and field of view to enhance perception accuracy, lower latency, and remove perception blind spots. In this article, we highlight the need for an evolved version of the collaborative perception that should address the challenges hindering the realization of level 5 AD use cases by comprehensively studying the transition from classical perception to collaborative perception. In particular, we discuss and review perception creation at two different levels: vehicle and infrastructure. Furthermore, we also study the communication technologies and three different collaborative perception message-sharing models, their comparison analyzing the trade-off between the accuracy of the transmitted data and the communication bandwidth used for data transmission, and the challenges therein. Finally, we discuss a range of crucial challenges and future directions of collaborative perception that need to be addressed before a higher level of autonomy hits the roads.

Identification of Novel Biomarkers for Response to Preoperative Chemoradiation in Locally Advanced Rectal Cancer with Genetic Algorithm-Based Gene Selection

BACKGROUND

The conventional treatment for patients with locally advanced colorectal tumors is preoperative chemo-radiotherapy (PCRT) preceding surgery. This treatment strategy has some long-term side effects, and some patients do not respond to it. Therefore, an evaluation of biomarkers that may help predict patients' response to PCRT is essential.

METHODS

We took advantage of genetic algorithm to search the space of possible combinations of features to choose subsets of genes that would yield convenient performance in differentiating PCRT responders from non-responders using a logistic regression model as our classifier.

RESULTS

We developed two gene signatures; first, to achieve the maximum prediction accuracy, the algorithm yielded 39 genes, and then, aiming to reduce the feature numbers as much as possible (while maintaining acceptable performance), a 5-gene signature was chosen. The performance of the two gene signatures was (accuracy = 0.97 and 0.81, sensitivity = 0.96 and 0.83, and specificity = 86 and 0.77) using a logistic regression classifier. Through analyzing bias and variance decomposition of the model error, we further investigated the involved genes by discovering and validating another 28-gene signature which possibly points towards two different sub-systems involved in the response of the patients to treatment.

CONCLUSIONS

Using genetic algorithm as our gene selection method, we have identified two groups of genes that can differentiate PCRT responders from non-responders in patients of the studied dataset with considerable performance.

IMPACT

After passing standard requirements, our gene signatures may be applicable as a robust and effective PCRT response prediction tool for colorectal cancer patients in clinical settings and may also help future studies aiming to further investigate involved pathways gain a clearer picture for the course of their research.

Electrocardiogram-based biometrics for user identification - Using your heartbeat as a digital key

External biometrics such as thumbprint and facial recognition have become standard tools for securing our digital devices and protecting our data. These systems, however, are potentially prone to copying and cybercrime access. Researchers have therefore explored internal biometrics, such as the electrical patterns within an electrocardiogram (ECG). The heart's electrical signals carry sufficient distinctiveness to allow the ECG to be used as an internal biometric for user authentication and identification. Using the ECG in this way has many potential advantages and limitations. This article reviews the history of ECG biometrics and explores some of the technical and security considerations. It also explores current and future uses of the ECG as an internal biometric.

A Call to Action on Assessing and Mitigating Bias in Artificial Intelligence Applications for Mental Health

Advances in computer science and data-analytic methods are driving a new era in mental health research and application. Artificial intelligence (AI) technologies hold the potential to enhance the assessment, diagnosis, and treatment of people experiencing mental health problems and to increase the reach and impact of mental health care. However, AI applications will not mitigate mental health disparities if they are built from historical data that reflect underlying social biases and inequities. AI models biased against sensitive classes could reinforce and even perpetuate existing inequities if these models create legacies that differentially impact who is diagnosed and treated, and how effectively. The current article reviews the health-equity implications of applying AI to mental health problems, outlines state-of-the-art methods for assessing and mitigating algorithmic bias, and presents a call to action to guide the development of fair-aware AI in psychological science.

Twitter Perspectives on Cochlear Implantation: Sentiment and Thematic Analysis

OBJECTIVE

To identify themes that contribute to the most positive and negative perspectives of cochlear implants (CIs) on Twitter.

STUDY DESIGN

A cross-sectional qualitative study.

SETTING

Social media (Twitter).

METHODS

In this study, all English-language original tweets mentioning "cochlear implant" from 2019 to 2021 were collected from Twitter's Academic Research Database using a custom Python script. Sentiment analysis was performed using VADER, a sentiment analysis tool built to analyze the inherent positivity or negativity of social media posts. Tweets were quantitatively sorted by compound sentiment score (range -1 [most negative] to 1 [most positive]). Thematic analysis based on grounded theory was performed on the most positive, negative, and "liked" tweets.

RESULTS

Of the 19,376 tweets included, the average (standard deviation) compound sentiment score was 0.21 (0.46). A total of 10,375 (53.5%) tweets had a positive tone, 4965 (25.6%) were neutral and 4036 (20.8%) were negative. Of the 100 most negative tweets, the most prominent themes were media representation (21.9%), the controversy of CI within the Deaf community (19.8%), and unrelated to direct patient experience (16.7%). Of the 100 most positive tweets, the most prominent themes were tweets of happiness and support (25.0%), tweets unrelated to direct patient experience (18.0%), and tweets about hearing new sounds (10.0%).

CONCLUSION

While the majority of tweets on CI carried a positive tone, there are ongoing challenges with the stigma surrounding CI. Public perspectives of CI on social media may help clinicians counsel CI patients and elucidate issues that lead to newfound acceptance or ongoing stigma of CI in the general population.

An interpretable measure of semantic similarity for predicting eye movements in reading

Predictions about upcoming content play an important role during language comprehension and processing. Semantic similarity as a metric has been used to predict how words are processed in context in language comprehension and processing tasks. This study proposes a novel, dynamic approach for computing contextual semantic similarity, evaluates the extent to which the semantic similarity measures computed using this approach can predict fixation durations in reading tasks recorded in a corpus of eye-tracking data, and compares the performance of these measures to that of semantic similarity measures computed using the cosine and Euclidean methods. Our results reveal that the semantic similarity measures generated by our approach are significantly predictive of fixation durations on reading and outperform those generated by the two existing approaches. The findings of this study contribute to a better understanding of how humans process words in context and make predictions in language comprehension and processing. The effective and interpretable approach to computing contextual semantic similarity proposed in this study can also facilitate further explorations of other experimental data on language comprehension and processing.

An NLP approach to identify SDoH-related circumstance and suicide crisis from death investigation narratives

OBJECTIVES

Suicide presents a major public health challenge worldwide, affecting people across the lifespan. While previous studies revealed strong associations between Social Determinants of Health (SDoH) and suicide deaths, existing evidence is limited by the reliance on structured data. To resolve this, we aim to adapt a suicide-specific SDoH ontology (Suicide-SDoHO) and use natural language processing (NLP) to effectively identify individual-level SDoH-related social risks from death investigation narratives.

MATERIALS AND METHODS

We used the latest National Violent Death Report System (NVDRS), which contains 267 804 victim suicide data from 2003 to 2019. After adapting the Suicide-SDoHO, we developed a transformer-based model to identify SDoH-related circumstances and crises in death investigation narratives. We applied our model retrospectively to annotate narratives whose crisis variables were not coded in NVDRS. The crisis rates were calculated as the percentage of the group's total suicide population with the crisis present.

RESULTS

The Suicide-SDoHO contains 57 fine-grained circumstances in a hierarchical structure. Our classifier achieves AUCs of 0.966 and 0.942 for classifying circumstances and crises, respectively. Through the crisis trend analysis, we observed that not everyone is equally affected by SDoH-related social risks. For the economic stability crisis, our result showed a significant increase in crisis rate in 2007-2009, parallel with the Great Recession.

CONCLUSIONS

This is the first study curating a Suicide-SDoHO using death investigation narratives. We showcased that our model can effectively classify SDoH-related social risks through NLP approaches. We hope our study will facilitate the understanding of suicide crises and inform effective prevention strategies.

Comprehensive analysis of clinical data for COVID-19 outcome estimation with machine learning models

COVID-19 is a global threat for the healthcare systems due to the rapid spread of the pathogen that causes it. In such situation, the clinicians must take important decisions, in an environment where medical resources can be insufficient. In this task, the computer-aided diagnosis systems can be very useful not only in the task of supporting the clinical decisions but also to perform relevant analyses, allowing them to understand better the disease and the factors that can identify the high risk patients. For those purposes, in this work, we use several machine learning algorithms to estimate the outcome of COVID-19 patients given their clinical information. Particularly, we perform 2 different studies: the first one estimates whether the patient is at low or at high risk of death whereas the second estimates if the patient needs hospitalization or not. The results of the analyses of this work show the most relevant features for each studied scenario, as well as the classification performance of the considered machine learning models. In particular, the XGBoost algorithm is able to estimate the need for hospitalization of a patient with an AUC-ROC of 0 . 8415 ± 0 . 0217 while it can also estimate the risk of death with an AUC-ROC of 0 . 7992 ± 0 . 0104 . Results have demonstrated the great potential of the proposal to determine those patients that need a greater amount of medical resources for being at a higher risk. This provides the healthcare services with a tool to better manage their resources.

TrDosePred: A deep learning dose prediction algorithm based on transformers for head and neck cancer radiotherapy

BACKGROUND

Intensity-Modulated Radiation Therapy (IMRT) has been the standard of care for many types of tumors. However, treatment planning for IMRT is a time-consuming and labor-intensive process.

PURPOSE

To alleviate this tedious planning process, a novel deep learning based dose prediction algorithm (TrDosePred) was developed for head and neck cancers.

METHODS

The proposed TrDosePred, which generated the dose distribution from a contoured CT image, was a U-shape network constructed with a convolutional patch embedding and several local self-attention based transformers. Data augmentation and ensemble approach were used for further improvement. It was trained based on the dataset from Open Knowledge-Based Planning Challenge (OpenKBP). The performance of TrDosePred was evaluated with two mean absolute error (MAE) based scores utilized by OpenKBP challenge (i.e., Dose score and DVH score) and compared to the top three approaches of the challenge. In addition, several state-of-the-art methods were implemented and compared to TrDosePred.

RESULTS

The TrDosePred ensemble achieved the dose score of 2.426 Gy and the DVH score of 1.592 Gy on the test dataset, ranking at 3rd and 9th respectively in the leaderboard on CodaLab as of writing. In terms of DVH metrics, on average, the relative MAE against the clinical plans was 2.25% for targets and 2.17% for organs at risk.

CONCLUSIONS

A transformer-based framework TrDosePred was developed for dose prediction. The results showed a comparable or superior performance as compared to the previous state-of-the-art approaches, demonstrating the potential of transformer to boost the treatment planning procedures.

Assessing transcriptomic reidentification risks using discriminative sequence models

Gene expression data provide molecular insights into the functional impact of genetic variation, for example, through expression quantitative trait loci (eQTLs). With an improving understanding of the association between genotypes and gene expression comes a greater concern that gene expression profiles could be matched to genotype profiles of the same individuals in another data set, known as a linking attack. Prior works show such a risk could analyze only a fraction of eQTLs that is independent owing to restrictive model assumptions, leaving the full extent of this risk incompletely understood. To address this challenge, we introduce the discriminative sequence model (DSM), a novel probabilistic framework for predicting a sequence of genotypes based on gene expression data. By modeling the joint distribution over all known eQTLs in a genomic region, DSM improves the power of linking attacks with necessary calibration for linkage disequilibrium and redundant predictive signals. We show greater linking accuracy of DSM compared with existing approaches across a range of attack scenarios and data sets including up to 22,288 individuals, suggesting that DSM helps uncover a substantial additional risk overlooked by previous studies. Our work provides a unified framework for assessing the privacy risks of sharing diverse omics data sets beyond transcriptomics.

A Survey on Differential Privacy for Medical Data Analysis

Machine learning methods promote the sustainable development of wise information technology of medicine (WITMED), and a variety of medical data brings high value and convenience to medical analysis. However, the applications of medical data have also been confronted with the risk of privacy leakage that is hard to avoid, especially when conducting correlation analysis or data sharing among multiple institutions. Data security and privacy preservation have recently played an essential role in the field of secure and private medical data analysis, where many differential privacy strategies are applied to medical data publishing and mining. In this paper, we survey research work on the applications of differential privacy for medical data analysis, discussing the necessity of medical privacy-preserving, the advantages of differential privacy, and their applications to typical medical data, such as genomic data and wearable device data. Furthermore, we discuss the challenges and potential future research directions for differential privacy in medical applications.

Short: Causal structural learning of conversational engagement for socially isolated older adults

Social isolation has become a growing public health concern in older adults and older adults with mild cognitive impairment. Coping strategies must be developed to increase social contact for socially isolated older adults. In this paper, we explored the conversational strategy between trained conversation moderators and socially isolated adults during a conversational engagement clinical trial (Clinicaltrials.gov: NCT02871921). We carried out structural learning and causality analysis to investigate the conversation strategies used by the trained moderators to engage socially isolated adults in the conversation and the causal effects of the strategy on engagement. Causal relations and effects were inferred between participants' emotions, the dialogue strategies used by moderators, and participants' following emotions. The results found in this paper may be used to support the development of cost-efficient, trustworthy AI- and/or robot-based platform to promote conversational engagement for older adults to address the challenges in social interaction.

Storing paediatric genomic data for sequential interrogation across the lifespan

Genomic sequencing (GS) is increasingly used in paediatric medicine to aid in screening, research and treatment. Some health systems are trialling GS as a first-line test in newborn screening programmes. Questions about what to do with genomic data after it has been generated are becoming more pertinent. While other research has outlined the ethical reasons for storing deidentified genomic data to be used in research, the ethical case for storing data for future clinical use has not been explicated. In this paper, we examine the ethical case for storing genomic data with the intention of using it as a lifetime health resource. In this model, genomic data would be stored with the intention of reanalysis at certain points through one's life. We argue this could benefit individuals and create an important public resource. However, several ethical challenges must first be met to achieve these benefits. We explore issues related to privacy, consent, justice and equality. We conclude by arguing that health systems should be moving towards futures that allow for the sequential interrogation of genomic data throughout the lifespan.