AI-Dentify: deep learning for proximal caries detection on bitewing x-ray - HUNT4 Oral Health Study

BACKGROUND

Dental caries diagnosis requires the manual inspection of diagnostic bitewing images of the patient, followed by a visual inspection and probing of the identified dental pieces with potential lesions. Yet the use of artificial intelligence, and in particular deep-learning, has the potential to aid in the diagnosis by providing a quick and informative analysis of the bitewing images.

METHODS

A dataset of 13,887 bitewings from the HUNT4 Oral Health Study were annotated individually by six different experts, and used to train three different object detection deep-learning architectures: RetinaNet (ResNet50), YOLOv5 (M size), and EfficientDet (D0 and D1 sizes). A consensus dataset of 197 images, annotated jointly by the same six dental clinicians, was used for evaluation. A five-fold cross validation scheme was used to evaluate the performance of the AI models.

RESULTS

The trained models show an increase in average precision and F1-score, and decrease of false negative rate, with respect to the dental clinicians. When compared against the dental clinicians, the YOLOv5 model shows the largest improvement, reporting 0.647 mean average precision, 0.548 mean F1-score, and 0.149 mean false negative rate. Whereas the best annotators on each of these metrics reported 0.299, 0.495, and 0.164 respectively.

CONCLUSION

Deep-learning models have shown the potential to assist dental professionals in the diagnosis of caries. Yet, the task remains challenging due to the artifacts natural to the bitewing images.

Exploring the impact of information and communication technologies on loneliness and social isolation in community-dwelling older adults: a scoping review of reviews

BACKGROUND

Recognizing the escalating public health concerns of loneliness and social isolation in aging populations, this study seeks to comprehensively explore the potential of information and communication technology (ICT)-based interventions to address these issues among older adults. This scoping review of reviews aims to map and synthesize existing evidence on the effectiveness and scope of ICT interventions targeting loneliness and social isolation in community-dwelling older adults, elucidating types of technology, impacts, facilitators, barriers, and research gaps.

METHODS

Following the Joanna Briggs Institute framework, we systematically searched eight diverse databases identifying relevant published reviews. We included English-written, peer-reviewed reviews of all types, with no limits regarding time of publication about ICTs targeting loneliness and/or social isolation for community-dwelling older adults. Eligible reviews were analysed and summarized, offering a holistic narrative of the reported types of ICTs and their impact, the identified facilitators and barriers influencing the implementation and adoption of ICT interventions, and the research gaps identified in the literature.

RESULTS

The review included 39 publications published between 2012 and 2024, spanning systematic, scoping, and reviews of reviews. Various ICTs were reported, primarily social media virtual communities, followed by video-mediated friendly visits, conversational agents, social robots, exergames and online gameplay. Predominantly positive impacts on mitigating social isolation and loneliness were evident for these ICTs, although methodological diversity and contradictory findings complicated definite conclusions. Facilitators and barriers encompassed individual competencies, access and usage, and intervention design and implementation. Research gaps involved targeting specific subgroups, exploring innovative technologies, incorporating diverse study designs, improving research methodologies, and addressing usability and accessibility. Future research should focus on identifying elderly individuals who can benefit the most from ICT use, exploring novel technologies, using a wider range of study designs, and enhancing usability and accessibility considerations.

CONCLUSIONS

This review sheds light on the diverse range of ICTs, their impact, and the facilitators and barriers associated with their use. Future investigations should prioritize refining outcome measures, addressing gender differences, and enhancing the usability and accessibility of interventions. The involvement of older adults in the design process and the exploration of technological training interventions hold promise in overcoming barriers.

Sleep pathology and use of anabolic androgen steroids among male weightlifters in Norway

Use of anabolic androgenic steroids (AAS) causes drastic changes in hormonal milieu and is associated with a range of medical and psychological consequences. Sleep pathology is a common side-effect of AAS use but few have studied these relations. This study examined the relationship between AAS use, psychological distress and sleep quality, and how phases of heavy use and abstinence influence sleep. The Pittsburgh-Sleep-Quality-Index (PSQI) and Jenkins Sleep Scale (JSS) were used to assess sleep quality, and psychological distress was measured with the Hopkins Symptoms Checklist (HSCL). Participants comprised men who have previous or current long-term use of AAS (n = 68) and non-using weightlifting controls (WLC) (n = 58), where a subgroup of participants (n = 22) was monitored over ~ 6 months during phases of AAS use and withdrawal. Group differences on PSQI and JSS were evaluated with Kruskal-Wallis H tests, and the mediating role of psychological distress was evaluated using structural equation modeling. Linear mixed models were used to assess the role of AAS use and withdrawal on sleep quality. Among the AAS group, 66% reported sleep problems as a side effect, and 38% had used sleep medication. PSQI scores showed significantly lower sleep quality in the AAS group compared to WLC (p < 0.001) on all subscales except "sleep latency". Furthermore, sleep quality was significantly poorer during withdrawal-phases than periods with AAS use (p < .001). Our findings provide key insight into sleep disturbances among men who use AAS, suggesting a link between sleep disturbances and hormone levels that deviate from physiologically normal levels in both directions.

Analyzing SDG interlinkages: identifying trade-offs and synergies for a responsible innovation

This paper responds to recent calls to address the indivisible nature of the Sustainable Development Goal (SDG) framework and the related knowledge gap on how SDG targets interlink with each other. It examines how SDG targets interact in the context of a specific technology, point of care (PoC) microfluidics, and how this relates to the concept of responsible innovation (RI). The novel SDG interlinkages methodology developed here involves several steps to filter the relevant interlinkages and a focus group of experts for discussing these interlinkages. The main findings indicate that several social synergies occur when deploying PoC microfluidics, but that the environmental trade-offs may jeopardize the total progress toward the SDGs. More specifically, the environmental sacrifices (use of plastics and lack of recyclability) resulted in the product being cheaper and, thus, better accessible. This work suggests that attention should be given (and prioritized) to the use of renewable and recyclable materials without jeopardizing the accessibility of the product. This should minimize the identified trade-offs. These findings inform how analyzing SDG interlinkages relates to the responsibilities and dimensions of RI in several ways. First, analyzing SDG interlinkages helps to execute the governance responsibility by using the RI dimensions (anticipation, reflexivity, inclusion and responsiveness). Second, analyzing SDG interlinkages gives insights into if and how a technology relates to the do-good and avoid-harm responsibility. This is important to assess the responsiveness of the technology to ensure that the technology can become truly sustainable and leaves no one behind.

Addressing uncertainty in genome-scale metabolic model reconstruction and analysis

The reconstruction and analysis of genome-scale metabolic models constitutes a powerful systems biology approach, with applications ranging from basic understanding of genotype-phenotype mapping to solving biomedical and environmental problems. However, the biological insight obtained from these models is limited by multiple heterogeneous sources of uncertainty, which are often difficult to quantify. Here we review the major sources of uncertainty and survey existing approaches developed for representing and addressing them. A unified formal characterization of these uncertainties through probabilistic approaches and ensemble modeling will facilitate convergence towards consistent reconstruction pipelines, improved data integration algorithms, and more accurate assessment of predictive capacity.

A machine vision system for tracking population behavior of zooplankton in small-scale experiments: a case study on salmon lice (Lepeophtheirus salmonis Krøyer, 1838) copepodite population responses to different light stimuli

To achieve efficient and preventive measures against salmon lice (Lepeophtheirus salmonis Krøyer, 1838) infestation, a better understanding of behavioral patterns of the planktonic life stages is key. To investigate light responses in L. salmonis copepodites, a non-intrusive experimental system was designed to measure behavioral responses in a 12.5-l volume using machine vision technology and methodology. The experimental system successfully tracked the collective movement patterns of the sea lice population during exposure to different light stimuli emitted from alternating zones in the system. This system could further be used to study behavioral responses to different physical cues of various developmental stages of sea lice or other zooplankton.

Mechanical Properties of Ca-Saturated Hydrogels with Functionalized Alginate

In this work, the mechanical properties and stability of alginate hydrogels containing functionalized alginates (peptide and β-cyclodextrin) were studied. There is an increasing interest in the modification of alginates to add functions such as cell attachment and increased solubility of hydrophobic drugs, for better performance in tissue engineering and drug release, respectively. Functionalization was achieved in this study via periodate oxidation followed by reductive amination, previously shown to give a high and controllable degree of substitution. Young's modulus and the stress at rupture of the hydrogels were in general lowered when exchanging native alginate with the modified alginate. Still, the gel strength could be adjusted by the fraction of modified alginate in the mixed hydrogels as well as the degree of oxidation. No notable difference in deformation at rupture was observed while syneresis was influenced by the degree of oxidation and possibly by the nature and amount of the grafted molecules. The mixed hydrogels were less stable than hydrogels with only native alginate, and modified alginate was released from the hydrogels. Furthermore, the hydrogels in general rather disintegrated than swelled upon saline treatments.