Advancing LGBTQ+ inclusion in STEM education and AI research.

The authors emphasize diversity, equity, and inclusion in STEM education and artificial intelligence (AI) research, focusing on LGBTQ+ representation. They discuss the challenges faced by queer scientists, educational resources, the implementation of National AI Campus, and the notion of intersectionality. The authors hope to ensure supportive and respectful engagement across all communities.

Evaluating the effects of comprehensive simulation on central venous catheterization training: a comparative observational study.

BACKGROUND: Simulation-based training (SBT) is vital to complex medical procedures such as ultrasound guided central venous catheterization (US-IJCVC), where the experience level of the physician impacts the likelihood of incurring complications. The Dynamic Haptic Robotic Trainer (DHRT) was developed to train residents in CVC as an improvement over manikin trainers, however, the DHRT and manikin trainer both only provide training on one specific portion of CVC, needle insertion. As such, CVC SBT would benefit from more comprehensive training. An extended version of the DHRT was created, the DHRT + , to provide hands-on training and automated feedback on additional steps of CVC. The DHRT + includes a full CVC medical kit, a false vein channel, and a personalized, reactive interface. When used together, the DHRT and DHRT + systems provide comprehensive training on needle insertion and catheter placement for CVC. This study evaluates the impact of the DHRT + on resident self-efficacy and CVC skill gains as compared to training on the DHRT alone. METHODS: Forty-seven medical residents completed training on the DHRT and 59 residents received comprehensive training on the DHRT and the DHRT + . Each resident filled out a central line self-efficacy (CLSE) survey before and after undergoing training on the simulators. After simulation training, each resident did one full CVC on a manikin while being observed by an expert rater and graded on a US-IJCVC checklist. RESULTS: For two items on the US-IJCVC checklist, "verbalizing consent" and "aspirating blood through the catheter", the DHRT + group performed significantly better than the DHRT only group. Both training groups showed significant improvements in self-efficacy from before to after training. However, type of training received was a significant predictor for CLSE items "using the proper equipment in the proper order", and "securing the catheter with suture and applying dressing" with the comprehensive training group that received additional training on the DHRT + showing higher post training self-efficacy. CONCLUSIONS: The integration of comprehensive training into SBT has the potential to improve US-IJCVC education for both learning gains and self-efficacy.

Identifying diversity of patient anatomy through automated image analysis of clinical ultrasounds.

PURPOSE: Central venous catheterization (CVC) carries inherent risks which can be mitigated through the use of appropriate ultrasound-guidance during needle insertion. This study aims to comprehensively understand patient anatomy as it is visualized during CVC by employing a semi-automated image analysis method to track the internal jugular vein and carotid artery throughout recorded ultrasound videos. METHODS: The ultrasound visualization of 50 CVC procedures were recorded at Penn State Health Milton S. Hershey Medical Center. The developed algorithm was used to detect the vessel edges, calculating metrics such as area, position, and eccentricity. RESULTS: Results show typical anatomical variations of the vein and artery, with the artery being more circular and posterior to the vein in most cases. Notably, two cases revealed atypical artery positions, emphasizing the algorithm's precision in detecting anomalies. Additionally, dynamic vessel properties were analyzed, with the vein compressing on average to 13.4% of its original size and the artery expanding by 13.2%. CONCLUSION: This study provides valuable insights which can be used to increase the accuracy of training simulations, thus enhancing medical education and procedural expertise. Furthermore, the novel approach of employing automated data analysis techniques to clinical recordings showcases the potential for continual assessment of patient anatomy, which could be useful in future advancements.

Comparison of the Trapping Efficacy of Locally Modified Gravid Aedes Trap and Autocidal Gravid Ovitrap for the Monitoring and Surveillance of Aedes aegypti Mosquitoes in Tanzania.

The study assessed the trapping efficacy of locally modified (1) Gravid Aedes Trap (GAT) lined with insecticide-treated net (ITN) as a killing agent and (2) Autocidal Gravid Ovitrap (AGO) with sticky board in the semi-field system (SFS) and field setting. Fully balanced Latin square experiments were conducted to compare GAT lined with ITN vs. AGO, both with either yeast or grass infusion. Biogent-Sentinel (BGS) with BG-Lure and no CO2 was used as a standard trap for Aedes mosquitoes. In the SFS, GAT outperformed AGO in collecting both nulliparous (65% vs. 49%, OR = 2.22, [95% CI: 1.89-2.60], p < 0.001) and gravid mosquitoes (73% vs. 64%, OR = 1.67, [95% CI: 1.41-1.97], p < 0.001). Similar differences were observed in the field. Yeast and grass infusion did not significantly differ in trapping gravid mosquitoes (OR = 0.91, [95% CI: 0.77-1.07], p = 0.250). The use of ITN improved mosquito recapture from 11% to 70% in the SFS. The same trend was observed in the field. Yeast was chosen for further evaluation in the optimized GAT due to its convenience and bifenthrin net for its resistance management properties. Mosquito density was collected when using 4× GATs relative to BGS-captured gravid mosquitoes 64 vs. 58 (IRR = 0.82, [95% CI: 0.35-1.95], p = 0.658) and showed no density dependence. Deployment of multiple yeast-baited GAT lined with bifenthrin net is cost-effective (single GAT < $8) compared to other traps such as BGS ($160).

Distinct Network Patterns Emerge from Cartesian and XOR Epistasis Models: A Comparative Network Science Analysis.

Background: Epistasis, the phenomenon where the effect of one gene (or variant) is masked or modified by one or more other genes, can significantly contribute to the observed phenotypic variance of complex traits. To date, it has been generally assumed that genetic interactions can be detected using a Cartesian, or multiplicative, interaction model commonly utilized in standard regression approaches. However, a recent study investigating epistasis in obesity-related traits in rats and mice has identified potential limitations of the Cartesian model, revealing that it only detects some of the genetic interactions occurring in these systems. By applying an alternative approach, the exclusive-or (XOR) model, the researchers detected a greater number of epistatic interactions and identified more biologically relevant ontological terms associated with the interacting loci. This suggests that the XOR model may provide a more comprehensive understanding of epistasis in these species and phenotypes. To further explore these findings and determine if different interaction models also make up distinct epistatic networks, we leverage network science to provide a more comprehensive view into the genetic interactions underlying BMI in this system. Results: Our comparative analysis of networks derived from Cartesian and XOR interaction models in rats (Rattus norvegicus) uncovers distinct topological characteristics for each model-derived network. Notably, we discover that networks based on the XOR model exhibit an enhanced sensitivity to epistatic interactions. This sensitivity enables the identification of network communities, revealing novel trait-related biological functions through enrichment analysis. Furthermore, we identify triangle network motifs in the XOR epistatic network, suggestive of higher-order epistasis, based on the topology of lower-order epistasis. Conclusions: These findings highlight the XOR model's ability to uncover meaningful biological associations as well as higher-order epistasis from lower-order epistatic networks. Additionally, our results demonstrate that network approaches not only enhance epistasis detection capabilities but also provide more nuanced understandings of genetic architectures underlying complex traits. The identification of community structures and motifs within these distinct networks, especially in XOR, points to the potential for network science to aid in the discovery of novel genetic pathways and regulatory networks. Such insights are important for advancing our understanding of phenotype-genotype relationships.

Sex classification of 3D skull images using deep neural networks.

Determining the fundamental characteristics that define a face as "feminine" or "masculine" has long fascinated anatomists and plastic surgeons, particularly those involved in aesthetic and gender-affirming surgery. Previous studies in this area have relied on manual measurements, comparative anatomy, and heuristic landmark-based feature extraction. In this study, we collected retrospectively at Cedars Sinai Medical Center (CSMC) a dataset of 98 skull samples, which is the first dataset of this kind of 3D medical imaging. We then evaluated the accuracy of multiple deep learning neural network architectures on sex classification with this dataset. Specifically, we evaluated methods representing three different 3D data modeling approaches: Resnet3D, PointNet++, and MeshNet. Despite the limited number of imaging samples, our testing results show that all three approaches achieve AUC scores above 0.9 after convergence. PointNet++ exhibits the highest accuracy, while MeshNet has the lowest. Our findings suggest that accuracy is not solely dependent on the sparsity of data representation but also on the architecture design, with MeshNet's lower accuracy likely due to the lack of a hierarchical structure for progressive data abstraction. Furthermore, we studied a problem related to sex determination, which is the analysis of the various morphological features that affect sex classification. We proposed and developed a new method based on morphological gradients to visualize features that influence model decision making. The method based on morphological gradients is an alternative to the standard saliency map, and the new method provides better visualization of feature importance. Our study is the first to develop and evaluate deep learning models for analyzing 3D facial skull images to identify imaging feature differences between individuals assigned male or female at birth. These findings may be useful for planning and evaluating craniofacial surgery, particularly gender-affirming procedures, such as facial feminization surgery.

Using GPT-4 to write a scientific review article: a pilot evaluation study.

GPT-4, as the most advanced version of OpenAI's large language models, has attracted widespread attention, rapidly becoming an indispensable AI tool across various areas. This includes its exploration by scientists for diverse applications. Our study focused on assessing GPT-4's capabilities in generating text, tables, and diagrams for biomedical review papers. We also assessed the consistency in text generation by GPT-4, along with potential plagiarism issues when employing this model for the composition of scientific review papers. Based on the results, we suggest the development of enhanced functionalities in ChatGPT, aiming to meet the needs of the scientific community more effectively. This includes enhancements in uploaded document processing for reference materials, a deeper grasp of intricate biomedical concepts, more precise and efficient information distillation for table generation, and a further refined model specifically tailored for scientific diagram creation.

KRAGEN: a knowledge graph-enhanced RAG framework for biomedical problem solving using large language models.

MOTIVATION: Answering and solving complex problems using a large language model (LLM) given a certain domain such as biomedicine is a challenging task that requires both factual consistency and logic, and LLMs often suffer from some major limitations, such as hallucinating false or irrelevant information, or being influenced by noisy data. These issues can compromise the trustworthiness, accuracy, and compliance of LLM-generated text and insights. RESULTS: Knowledge Retrieval Augmented Generation ENgine (KRAGEN) is a new tool that combines knowledge graphs, Retrieval Augmented Generation (RAG), and advanced prompting techniques to solve complex problems with natural language. KRAGEN converts knowledge graphs into a vector database and uses RAG to retrieve relevant facts from it. KRAGEN uses advanced prompting techniques: namely graph-of-thoughts (GoT), to dynamically break down a complex problem into smaller subproblems, and proceeds to solve each subproblem by using the relevant knowledge through the RAG framework, which limits the hallucinations, and finally, consolidates the subproblems and provides a solution. KRAGEN's graph visualization allows the user to interact with and evaluate the quality of the solution's GoT structure and logic. AVAILABILITY AND IMPLEMENTATION: KRAGEN is deployed by running its custom Docker containers. KRAGEN is available as open-source from GitHub at: https://github.com/EpistasisLab/KRAGEN.

The neuron as a direct data-driven controller.

In the quest to model neuronal function amid gaps in physiological data, a promising strategy is to develop a normative theory that interprets neuronal physiology as optimizing a computational objective. This study extends current normative models, which primarily optimize prediction, by conceptualizing neurons as optimal feedback controllers. We posit that neurons, especially those beyond early sensory areas, steer their environment toward a specific desired state through their output. This environment comprises both synaptically interlinked neurons and external motor sensory feedback loops, enabling neurons to evaluate the effectiveness of their control via synaptic feedback. To model neurons as biologically feasible controllers which implicitly identify loop dynamics, infer latent states, and optimize control we utilize the contemporary direct data-driven control (DD-DC) framework. Our DD-DC neuron model explains various neurophysiological phenomena: the shift from potentiation to depression in spike-timing-dependent plasticity with its asymmetry, the duration and adaptive nature of feedforward and feedback neuronal filters, the imprecision in spike generation under constant stimulation, and the characteristic operational variability and noise in the brain. Our model presents a significant departure from the traditional, feedforward, instant-response McCulloch-Pitts-Rosenblatt neuron, offering a modern, biologically informed fundamental unit for constructing neural networks.

PFERM: A Fair Empirical Risk Minimization Approach with Prior Knowledge.

Fairness is crucial in machine learning to prevent bias based on sensitive attributes in classifier predictions. However, the pursuit of strict fairness often sacrifices accuracy, particularly when significant prevalence disparities exist among groups, making classifiers less practical. For example, Alzheimer's disease (AD) is more prevalent in women than men, making equal treatment inequitable for females. Accounting for prevalence ratios among groups is essential for fair decision-making. In this paper, we introduce prior knowledge for fairness, which incorporates prevalence ratio information into the fairness constraint within the Empirical Risk Minimization (ERM) framework. We develop the Prior-knowledge-guided Fair ERM (PFERM) framework, aiming to minimize expected risk within a specified function class while adhering to a prior-knowledge-guided fairness constraint. This approach strikes a flexible balance between accuracy and fairness. Empirical results confirm its effectiveness in preserving fairness without compromising accuracy.

Enhancing fall risk assessment: instrumenting vision with deep learning during walks.

BACKGROUND: Falls are common in a range of clinical cohorts, where routine risk assessment often comprises subjective visual observation only. Typically, observational assessment involves evaluation of an individual's gait during scripted walking protocols within a lab to identify deficits that potentially increase fall risk, but subtle deficits may not be (readily) observable. Therefore, objective approaches (e.g., inertial measurement units, IMUs) are useful for quantifying high resolution gait characteristics, enabling more informed fall risk assessment by capturing subtle deficits. However, IMU-based gait instrumentation alone is limited, failing to consider participant behaviour and details within the environment (e.g., obstacles). Video-based eye-tracking glasses may provide additional insight to fall risk, clarifying how people traverse environments based on head and eye movements. Recording head and eye movements can provide insights into how the allocation of visual attention to environmental stimuli influences successful navigation around obstacles. Yet, manual review of video data to evaluate head and eye movements is time-consuming and subjective. An automated approach is needed but none currently exists. This paper proposes a deep learning-based object detection algorithm (VARFA) to instrument vision and video data during walks, complementing instrumented gait. METHOD: The approach automatically labels video data captured in a gait lab to assess visual attention and details of the environment. The proposed algorithm uses a YoloV8 model trained on with a novel lab-based dataset. RESULTS: VARFA achieved excellent evaluation metrics (0.93 mAP50), identifying, and localizing static objects (e.g., obstacles in the walking path) with an average accuracy of 93%. Similarly, a U-NET based track/path segmentation model achieved good metrics (IoU 0.82), suggesting that the predicted tracks (i.e., walking paths) align closely with the actual track, with an overlap of 82%. Notably, both models achieved these metrics while processing at real-time speeds, demonstrating efficiency and effectiveness for pragmatic applications. CONCLUSION: The instrumented approach improves the efficiency and accuracy of fall risk assessment by evaluating the visual allocation of attention (i.e., information about when and where a person is attending) during navigation, improving the breadth of instrumentation in this area. Use of VARFA to instrument vision could be used to better inform fall risk assessment by providing behaviour and context data to complement instrumented e.g., IMU data during gait tasks. That may have notable (e.g., personalized) rehabilitation implications across a wide range of clinical cohorts where poor gait and increased fall risk are common.

Radiomics-Based Analysis of Intestinal Ultrasound Images for Inflammatory Bowel Disease: A Feasibility Study.

Background: The increasing adoption of intestinal ultrasound (IUS) for monitoring inflammatory bowel diseases (IBD) by IBD providers has uncovered new challenges regarding standardized image interpretation and limitations as a research tool. Artificial intelligence approaches can help address these challenges. We aim to determine the feasibility of radiomic analysis of IUS images and to determine if a radiomics-based classification model can accurately differentiate between normal and abnormal IUS images. We will also compare the radiomic-based model's performance to a convolutional neural network (CNN)-based classification model to understand which method is more effective for extracting meaningful information from IUS images. Methods: Retrospectively analyzing IUS images obtained during routine outpatient visits, we developed and tested radiomic-based and CNN-based models to distinguish between normal and abnormal images, with abnormal images defined as bowel wall thickness > 3 mm or bowel hyperemia with modified Limberg score ≥ 1 (both are surrogate markers for inflammation). Model performances were measured by area under the receiver operator curve (AUC). Results: For this feasibility study, 125 images (33% abnormal) were analyzed. A radiomic-based model using XG boost yielded the best classifier model with average test AUC 0.98%, 93.8% sensitivity, 93.8% specificity, and 93.7% accuracy. The CNN-based classification model yielded an average testing AUC of 0.75. Conclusions: Radiomic analysis of IUS images is feasible, and a radiomic-based classification model could accurately differentiate abnormal from normal images. Our findings establish methods to facilitate future radiomic-based IUS studies that can help standardize image interpretation and expand IUS research capabilities.

Interpretable deep clustering survival machines for Alzheimer's disease subtype discovery.

Alzheimer's disease (AD) is a complex neurodegenerative disorder that has impacted millions of people worldwide. The neuroanatomical heterogeneity of AD has made it challenging to fully understand the disease mechanism. Identifying AD subtypes during the prodromal stage and determining their genetic basis would be immensely valuable for drug discovery and subsequent clinical treatment. Previous studies that clustered subgroups typically used unsupervised learning techniques, neglecting the survival information and potentially limiting the insights gained. To address this problem, we propose an interpretable survival analysis method called Deep Clustering Survival Machines (DCSM), which combines both discriminative and generative mechanisms. Similar to mixture models, we assume that the timing information of survival data can be generatively described by a mixture of parametric distributions, referred to as expert distributions. We learn the weights of these expert distributions for individual instances in a discriminative manner by leveraging their features. This allows us to characterize the survival information of each instance through a weighted combination of the learned expert distributions. We demonstrate the superiority of the DCSM method by applying this approach to cluster patients with mild cognitive impairment (MCI) into subgroups with different risks of converting to AD. Conventional clustering measurements for survival analysis along with genetic association studies successfully validate the effectiveness of the proposed method and characterize our clustering findings.

Centralized and Federated Models for the Analysis of Clinical Data.

The progress of precision medicine research hinges on the gathering and analysis of extensive and diverse clinical datasets. With the continued expansion of modalities, scales, and sources of clinical datasets, it becomes imperative to devise methods for aggregating information from these varied sources to achieve a comprehensive understanding of diseases. In this review, we describe two important approaches for the analysis of diverse clinical datasets, namely the centralized model and federated model. We compare and contrast the strengths and weaknesses inherent in each model and present recent progress in methodologies and their associated challenges. Finally, we present an outlook on the opportunities that both models hold for the future analysis of clinical data.

FDA Approval Summary: Fruquintinib for the Treatment of Refractory Metastatic Colorectal Cancer.

On November 8, 2023, the FDA approved fruquintinib, an inhibitor of vascular endothelial growth factor receptors (VEGFR)-1, -2, and -3, for the treatment of patients with metastatic colorectal cancer (mCRC) who have been previously treated with fluoropyrimidine­, oxaliplatin­, and irinotecan­based chemotherapy, an anti­VEGF therapy, and, if RAS wild­type and medically appropriate, an anti EGFR therapy. Approval was based on Study FRESCO-2, a globally-conducted, double-blind, placebo-controlled randomized trial. The primary endpoint was overall survival (OS). The key secondary endpoint was progression-free survival (PFS). A total of 691 patients were randomized (461 and 230 into the fruquintinib and placebo arms, respectively). Fruquintinib provided a statistically significant improvement in OS with a hazard ratio (HR) of 0.66 (95% CI: 0.55, 0.80; p<0.001). The median OS was 7.4 months (95% CI: 6.7, 8.2) in the fruquintinib arm and 4.8 months (95% CI: 4.0, 5.8) for the placebo arm. Adverse events observed were generally consistent with the known safety profile associated with inhibition of the VEGFR. The results of FRESCO-2 were supported by the FRESCO study, a double-blind, single country, placebo-controlled, randomized trial in patients with refractory mCRC who have been previously treated with fluoropyrimidine­, oxaliplatin­, and irinotecan­based chemotherapy. In FRESCO, the OS HR was 0.65 (95% CI: 0.51, 0.83; p<0.001). FDA concluded that the totality of the evidence from FRESCO-2 and FRESCO supported an indication for patients with mCRC with prior treatment with fluoropyrimidine, oxaliplatin-, and irinotecan-based chemotherapy, an anti-VEGF biological therapy, and if RAS wild­type and medically appropriate, an anti-EGFR therapy.

Evaluating human landing catches as a measure of mosquito biting and the importance of considering additional modes of action.

Entomological evaluations of vector control tools often use human landing catches (HLCs) as a standard measure of a direct human-vector contact. However, some tools have additional characteristics, such as mortality, and HLCS are not sensitive for measuring other effects beyond landing inhibition. Therefore, additional measures may need to be considered when evaluating these tools for public health use. This study has two main aims (1) the evaluate the accuracy of HLCs as a proxy for feeding and (2) to compare the predicted reduction in vectorial capacity when we do and do not consider these additional characteristics. To achieve this, we analyse previously published semi-field data from an experiment which used HLCs and another where mosquitoes were allowed to feed in the presence of different dosages of the volatile pyrethroid spatial repellent, transfluthrin. We compare results for two mathematical models: one which only considers the reduction in feeding effect and one which also considers mortality before and after feeding (using data gathered by the aspiration of mosquitoes after the semi-field feeding/landing period and 24 h survival monitoring). These Bayesian hierarchical models are parameterised using Bayesian inference. We observe that, for susceptible mosquitoes, reduction in landing is underestimated by HLCs. For knockdown resistant mosquitoes the relationship is less clear; with HLCs sometimes appearing to overestimate this characteristic. We find HLCs tend to under-predict the relative reduction in vectorial capacity in susceptible mosquitoes while over-predicting this impact in knockdown-resistant mosquitoes. Models without secondary effects have lower predicted relative reductions in vectorial capacities. Overall, this study highlights the importance of considering additional characteristics to reduction in biting of volatile pyrethroid spatial repellents. We recommend that these are considered when evaluating novel vector control tools.

The Alzheimer's Knowledge Base: A Knowledge Graph for Alzheimer Disease Research.

BACKGROUND: As global populations age and become susceptible to neurodegenerative illnesses, new therapies for Alzheimer disease (AD) are urgently needed. Existing data resources for drug discovery and repurposing fail to capture relationships central to the disease's etiology and response to drugs. OBJECTIVE: We designed the Alzheimer's Knowledge Base (AlzKB) to alleviate this need by providing a comprehensive knowledge representation of AD etiology and candidate therapeutics. METHODS: We designed the AlzKB as a large, heterogeneous graph knowledge base assembled using 22 diverse external data sources describing biological and pharmaceutical entities at different levels of organization (eg, chemicals, genes, anatomy, and diseases). AlzKB uses a Web Ontology Language 2 ontology to enforce semantic consistency and allow for ontological inference. We provide a public version of AlzKB and allow users to run and modify local versions of the knowledge base. RESULTS: AlzKB is freely available on the web and currently contains 118,902 entities with 1,309,527 relationships between those entities. To demonstrate its value, we used graph data science and machine learning to (1) propose new therapeutic targets based on similarities of AD to Parkinson disease and (2) repurpose existing drugs that may treat AD. For each use case, AlzKB recovers known therapeutic associations while proposing biologically plausible new ones. CONCLUSIONS: AlzKB is a new, publicly available knowledge resource that enables researchers to discover complex translational associations for AD drug discovery. Through 2 use cases, we show that it is a valuable tool for proposing novel therapeutic hypotheses based on public biomedical knowledge.

AI-luminating Artificial Intelligence in Inflammatory Bowel Diseases: A Narrative Review on the Role of AI in Endoscopy, Histology, and Imaging for IBD.

Endoscopy, histology, and cross-sectional imaging serve as fundamental pillars in the detection, monitoring, and prognostication of inflammatory bowel disease (IBD). However, interpretation of these studies often relies on subjective human judgment, which can lead to delays, intra- and interobserver variability, and potential diagnostic discrepancies. With the rising incidence of IBD globally coupled with the exponential digitization of these data, there is a growing demand for innovative approaches to streamline diagnosis and elevate clinical decision-making. In this context, artificial intelligence (AI) technologies emerge as a timely solution to address the evolving challenges in IBD. Early studies using deep learning and radiomics approaches for endoscopy, histology, and imaging in IBD have demonstrated promising results for using AI to detect, diagnose, characterize, phenotype, and prognosticate IBD. Nonetheless, the available literature has inherent limitations and knowledge gaps that need to be addressed before AI can transition into a mainstream clinical tool for IBD. To better understand the potential value of integrating AI in IBD, we review the available literature to summarize our current understanding and identify gaps in knowledge to inform future investigations.

Contextualizing remote fall risk: Video data capture and implementing ethical AI.

Wearable inertial measurement units (IMUs) are being used to quantify gait characteristics that are associated with increased fall risk, but the current limitation is the lack of contextual information that would clarify IMU data. Use of wearable video-based cameras would provide a comprehensive understanding of an individual's habitual fall risk, adding context to clarify abnormal IMU data. Generally, there is taboo when suggesting the use of wearable cameras to capture real-world video, clinical and patient apprehension due to ethical and privacy concerns. This perspective proposes that routine use of wearable cameras could be realized within digital medicine through AI-based computer vision models to obfuscate/blur/shade sensitive information while preserving helpful contextual information for a comprehensive patient assessment. Specifically, no person sees the raw video data to understand context, rather AI interprets the raw video data first to blur sensitive objects and uphold privacy. That may be more routinely achieved than one imagines as contemporary resources exist. Here, to showcase/display the potential an exemplar model is suggested via off-the-shelf methods to detect and blur sensitive objects (e.g., people) with an accuracy of 88%. Here, the benefit of the proposed approach includes a more comprehensive understanding of an individual's free-living fall risk (from free-living IMU-based gait) without compromising privacy. More generally, the video and AI approach could be used beyond fall risk to better inform habitual experiences and challenges across a range of clinical cohorts. Medicine is becoming more receptive to wearables as a helpful toolbox, camera-based devices should be plausible instruments.

Class-Balanced Deep Learning with Adaptive Vector Scaling Loss for Dementia Stage Detection.

Alzheimer's disease (AD) leads to irreversible cognitive decline, with Mild Cognitive Impairment (MCI) as its prodromal stage. Early detection of AD and related dementia is crucial for timely treatment and slowing disease progression. However, classifying cognitive normal (CN), MCI, and AD subjects using machine learning models faces class imbalance, necessitating the use of balanced accuracy as a suitable metric. To enhance model performance and balanced accuracy, we introduce a novel method called VS-Opt-Net. This approach incorporates the recently developed vector-scaling (VS) loss into a machine learning pipeline named STREAMLINE. Moreover, it employs Bayesian optimization for hyperparameter learning of both the model and loss function. VS-Opt-Net not only amplifies the contribution of minority examples in proportion to the imbalance level but also addresses the challenge of generalization in training deep networks. In our empirical study, we use MRI-based brain regional measurements as features to conduct the CN vs MCI and AD vs MCI binary classifications. We compare the balanced accuracy of our model with other machine learning models and deep neural network loss functions that also employ class-balanced strategies. Our findings demonstrate that after hyperparameter optimization, the deep neural network using the VS loss function substantially improves balanced accuracy. It also surpasses other models in performance on the AD dataset. Moreover, our feature importance analysis highlights VS-Opt-Net's ability to elucidate biomarker differences across dementia stages.