Uncertainty estimation in healthcare involves quantifying and understanding the inherent uncertainty or variability associated with medical predictions, diagnoses, and treatment outcomes. In this era of Artificial Intelligence (AI) models, uncertainty estimation becomes vital to ensure safe decision-making in the medical field. Therefore, this review focuses on the application of uncertainty techniques to machine and deep learning models in healthcare. A systematic literature review was conducted using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. Our analysis revealed that Bayesian methods were the predominant technique for uncertainty quantification in machine learning models, with Fuzzy systems being the second most used approach. Regarding deep learning models, Bayesian methods emerged as the most prevalent approach, finding application in nearly all aspects of medical imaging. Most of the studies reported in this paper focused on medical images, highlighting the prevalent application of uncertainty quantification techniques using deep learning models compared to machine learning models. Interestingly, we observed a scarcity of studies applying uncertainty quantification to physiological signals. Thus, future research on uncertainty quantification should prioritize investigating the application of these techniques to physiological signals. Overall, our review highlights the significance of integrating uncertainty techniques in healthcare applications of machine learning and deep learning models. This can provide valuable insights and practical solutions to manage uncertainty in real-world medical data, ultimately improving the accuracy and reliability of medical diagnoses and treatment recommendations.

The process of linking an offender to a crime scene via their fingerprints has historically required significant human effort to compare latent fingerprints recovered from the scene with known fingerprints of a suspect. Increasing the speed of such comparisons, whilst maintaining accuracy and reliability and minimising error, is crucial for providing rapid intelligence to police investigators. One major opportunity for streamlining fingerprint examination is the adaptation of \'lights-out\' technology to the comparison and matching of latent fingerprints. Here, we review the development, trial and validation process undertaken by the Queensland Police Service (QPS), Australia, to support implementation of a lights-out latent (LOL) workflow for automated latent fingerprint searching that is fully integrated with the existing case management systems. Targeted trials were undertaken using random selections of previously identified latent fingerprints that were searched using the LOL workflow against a local 10-print database. The results suggested that the LOL workflow could identify up to 44% of latent fingerprints with minimal human intervention and supported its implementation for all latent fingerprint comparisons in QPS casework. Review of LOL casework comparison outcomes for 2019 revealed that LOL-based identifications contributed approximately one quarter of all fingerprint identifications. Several procedural and technical factors that influenced the speed and efficiency of the LOL workflow are discussed, along with opportunities for improvement and future validation as an expert system.

BACKGROUND: Overconcern with food and shape/weight stimuli are central to eating disorder maintenance with attentional biases seen towards these images not present in healthy controls. These stimuli trigger changes in the physiological, emotional, and neural responses in people with eating disorders, and are regularly used in research and clinical practice. However, selection of stimuli for these treatments is frequently based on self-reported emotional ratings alone, and whether self-reports reflect objective responses is unknown.
UNASSIGNED: This review assessed the associations across emotional self-report, physiological, and neural responses to both food and body-shape/weight stimuli in people with anorexia nervosa (AN), bulimia nervosa (BN) and binge eating disorder (BED). For food stimuli, either an aversive or lack of physiological effect was generated in people with AN, together with a negative emotional response on neuroimaging, and high subjective anxiety ratings. People with BN showed a positive self-rating, an aversive physiological reaction, and a motivational neural response. In BED, an aversive physiological reaction was found in contrast to motivational/appetitive neural responses, with food images rated as pleasant. The results for shape/weight stimuli showed aversive responses in some physiological modalities, which was reflected in both the emotional and neural responses, but this aversive response was not consistent across physiological studies.
CONCLUSIONS: Shape/weight stimuli are more reliable for use in therapy or research than food stimuli as the impact of these images is more consistent across subjective and objective responses. Care should be taken when using food stimuli due to the disconnect reported in this review.

Dental caries is the most prevalent dental disease worldwide, and neural networks and artificial intelligence are increasingly being used in the field of dentistry. This systematic review aims to identify the state of the art of neural networks in caries detection and diagnosis. A search was conducted in PubMed, Institute of Electrical and Electronics Engineers (IEEE) Xplore, and ScienceDirect. Data extraction was performed independently by two reviewers. The quality of the selected studies was assessed using the Cochrane Handbook tool. Thirteen studies were included. Most of the included studies employed periapical, near-infrared light transillumination, and bitewing radiography. The image databases ranged from 87 to 3000 images, with a mean of 669 images. Seven of the included studies labeled the dental caries in each image by experienced dentists. Not all of the studies detailed how caries was defined, and not all detailed the type of carious lesion detected. Each study included in this review used a different neural network and different outcome metrics. All this variability complicates the conclusions that can be made about the reliability or not of a neural network to detect and diagnose caries. A comparison between neural network and dentist results is also necessary.

Convolutional neural networks (CNNs) are increasingly applied for medical image diagnostics. We performed a scoping review, exploring (1) use cases, (2) methodologies and (3) findings of studies applying CNN on dental image material.
Medline via PubMed, IEEE Xplore, arXiv were searched.
Full-text articles and conference-proceedings reporting CNN application on dental imagery were included.
Thirty-six studies, published 2015-2019, were included, mainly from four countries (South Korea, United States, Japan, China). Studies focussed on general dentistry (n = 15 studies), cariology (n = 5), endodontics (n = 2), periodontology (n = 3), orthodontics (n = 3), dental radiology (2), forensic dentistry (n = 2) and general medicine (n = 4). Most often, the detection, segmentation or classification of anatomical structures, including teeth (n = 9), jaw bone (n = 2) and skeletal landmarks (n = 4) was performed. Detection of pathologies focused on caries (n = 3). The most commonly used image type were panoramic radiographs (n = 11), followed by periapical radiographs (n = 8), Cone-Beam CT or conventional CT (n = 6). Dataset sizes varied between 10-5,166 images (mean 1,053). Most studies used medical professionals to label the images and constitute the reference test. A large range of outcome metrics was employed, hampering comparisons across studies. A comparison of the CNN performance against an independent test group of dentists was provided by seven studies; most studies found the CNN to perform similar to dentists. Applicability or impact on treatment decision was not assessed at all.
CNNs are increasingly employed for dental image diagnostics in research settings. Their usefulness, safety and generalizability should be demonstrated using more rigorous, replicable and comparable methodology.
CNNs may be used in diagnostic-assistance systems, thereby assisting dentists in a more comprehensive, systematic and faster evaluation and documentation of dental images. CNNs may become applicable in routine care; however, prior to that, the dental community should appraise them against the rules of evidence-based practice.

Sleep and emotion are closely linked, however the effects of sleep on socio-emotional task performance have only recently been investigated. Sleep loss and insomnia have been found to affect emotional reactivity and social functioning, although results, taken together, are somewhat contradictory. Here we review this advancing literature, aiming to 1) systematically review the relevant literature on sleep and socio-emotional functioning, with reference to the extant literature on emotion and social interactions, 2) summarize results and outline ways in which emotion, social interactions, and sleep may interact, and 3) suggest key limitations and future directions for this field. From the reviewed literature, sleep deprivation is associated with diminished emotional expressivity and impaired emotion recognition, and this has particular relevance for social interactions. Sleep deprivation also increases emotional reactivity; results which are most apparent with neuro-imaging studies investigating amygdala activity and its prefrontal regulation. Evidence of emotional dysregulation in insomnia and poor sleep has also been reported. In general, limitations of this literature include how performance measures are linked to self-reports, and how results are linked to socio-emotional functioning. We conclude by suggesting some possible future directions for this field.