Additional Tasks Research Articles

Is the Mannheim Multicomponent Stress Test a viable alternative to the Trier Social Stress Test?

BackgroundThe Trier Social Stress Test (TSST) is a widely used laboratory protocol to study acute stress reactivity, a hallmark of which is a meaningful increase in saliva cortisol (> 2.5 nmol/L) in most individuals, reflecting hypothalamic-pituitary-adrenal (HPA) axis activation. The Mannheim Multicomponent Stress Test (MMST) has potential as a low staff burden alternative to the TSST, with one study showing statistically significant increases in subjective stress, heart rate and saliva cortisol; however, uncertainty remains about the meaningfulness of these psychobiological responses. ObjectiveTo assess whether the MMST is a viable alternative to the TSST. MethodsUsing a between subjects design, 31 healthy adults were randomised to the standard TSST or the MMST using stratified block randomisation accounting for sex and trait anxiety. The standard TSST consisted of an anticipation phase, followed by a free speech and mental arithmetic task performed in front of a panel of trained actors. The MMST consisted of a computer based Paced Auditory Serial Addition Task (cognitive stressor) with additional motivational, emotional, and acoustic stressors in the presence of one unresponsive observer. ResultsGroup x time interactions showed that the MMST induced smaller psychobiological responses compared with the TSST (mixed model ANCOVA, P < 0.05). Post-hoc analyses revealed that the MMST induced a significant yet smaller state anxiety response (score range 20–80, MMST: 47 ± 12 vs. TSST: 57 ± 9; P < 0.01, Cohens d = 0.9) and peak heart rate response (MMST: 98 ± 17 vs. TSST: 110 ± 21 bpm; P < 0.05, Cohens d = 0.6) compared with the TSST. Despite observing stereotypical neuroendocrine responses to the TSST, the MMST did not increase saliva α-amylase or cortisol (Δ saliva cortisol, 0.1 ± 1.1 vs. TSST: 10.3 ± 12.8 nmol/L; between group difference P < 0.01, Cohens d = 1.1). Moreover, meaningful increases in saliva cortisol (> 2.5 nmol/L) were observed in 80% of participants after the TSST but in no participant after the MMST. ConclusionThe Mannheim Multicomponent Stress Test increased state anxiety and heart rate but not saliva cortisol. As such, the present results do not support the utility of the Mannheim Multicomponent Stress Test as a viable alternative to The Trier Social Stress Test.

Online interventions for the mental health and well-being of parents of children with additional needs: Systematic review and meta-analysis.

Parents of children with additional needs experience compromised physical and mental health and higher stress, and their ability to engage in meaningful occupations is impacted by their additional caregiving tasks. Online interventions targeting mental health, stress, and well-being for parents of children with additional needs have potential to increase supports alongside occupational therapy direct services. The aims of this review are to systematically identify and synthesise evidence of effectiveness of online interventions aimed at improving mental health, stress, and well-being of parents of children with additional needs. Eight databases were searched up to July 2024 to identify online interventions for parents of children with additional needs. Studies were appraised for methodological quality. Standardised effect sizes were calculated, and meta-analyses of randomised control trials (RCTs) were conducted on outcomes of mental health, well-being, and stress. There was no consumer or community involvement. Systematic screening identified 30 papers that met inclusion criteria. Most were RCTs or controlled clinical trials (CCTs) with 'moderate' quality ratings: Three were designed by occupational therapists. There was substantial variation in intervention types, methods of delivery, outcomes, and outcome measures used. The pooled standardised effect size estimates (ES) and the lower and upper confidence intervals (CI) of online interventions from RCTs post-interventions were significant for mental health ES = 0.47, 95% CI (0.18, 0.77), p = 0.002; stress ES = 1.27, 95% CI (0.56, 1.98), p = 0.000; and well-being ES = 0.65, 95% CI (1.2, 0.06), p = 0.03, respectively. The online interventions that aimed to improve mental health, stress, and well-being included in this meta-analysis were effective. Occupational therapists supporting families play an important role in guiding parents of children with additional needs to evidence-based interventions to support them with addressing their own mental health and well-being needs.

Initiating systemic capacity development for leadership from the bottom-up: a realist evaluation of a leadership innovation in a South African health district.

The need for leadership in and of district health systems is critical for the effective delivery of services and for inter-sectoral collaboration for health. Leadership capacity development has not, however, been prioritised within health systems and the systemic capacity (i.e. roles, structures, and processes) that is needed to develop managers who can lead is not always in place. This paper aims to contribute to understanding how to build such capacity, considering a relevant bottom-up innovation. We observed, in the period 2013 - 2015, the emergent implementation of this innovation (a 'Leadership Commission') in a South African health district. What started out as an effort to train individual leaders evolved into the development of systemic capacity for leadership capacity development (LCD). We adopted realist evaluation as the main methodological approach, as well as case study design; and we first developed a programme theory of the internally driven LCD initiative, through a round of interviews with senior managers. We then tested the programme theory drawing on fourteen in-depth interviews and field notes of meetings and processes. Our analysis suggests that building systemic capacity for LCD requires leadership to be expressed as a strategic priority by those with positional authority; and that bottom-up LCD requires institutional commitment through strengthening routine structures or creating new ones. The ability to leverage existing resources is another key element of systemic capacity. The mechanisms that enable bottom-up capacity development include tacit and experiential knowledge, sensemaking, systems thinking, and trust between, and motivation of, those tasked with leading LCD. Leadership development is constrained by increased workloads for those involved if the prioritisation of leadership becomes simply an additional task, and sustainability challenges are likely in the absence of additional resources for bottom-up innovation.

Task shifting to improve practice efficiency: A survey among general practitioners in non-urban Baden-Wuerttemberg, Germany

Background Germany is challenged by an increasing shortage in general practice services, especially in non-urban areas. Task shifting from general practitioners (GPs) to other health professionals may improve practice efficiency to address this mismatch. Objectives Exploring GPs’ motives and beliefs towards task shifting in non-urban Germany and identifying potential factors influencing these. Methods The cross-sectional survey was disseminated by mail in three waves between July 2021 and August 2022 among all GPs in non-urban Baden-Wuerttemberg, Germany. It included items on demographics and practice characteristics as well as 15 Likert-scale items addressing motives and beliefs towards task shifting, based on the Theoretical Domain Framework. Likert-scale items were analysed descriptively, influencing factors on motives and beliefs were identified using multiple linear regression. Results Response rate was 24.2% (281/1162), with respondents comparable in age and gender to all GPs in Baden-Wuerttemberg. GPs’ motives and beliefs towards task shifting are positive overall. The majority expects task shifting to reduce their workload (87.9%) and increase practice efficiency (74.7%). They are open to shift additional tasks to other professionals (69.1%), even in the currently prohibited form of substitution (51.2%). Motives and beliefs were significantly more positive among younger GPs and those participating in the GP-centred care programme. Conclusion This study describes GPs’ motives and beliefs towards task shifting in non-urban Germany. Identifying younger GPs and those participating in the GP-centred care programme as particularly endorsing may help design future interventions aiming to improve efficiency in general practice in non-urban Germany.

Out-of-pocket costs for patients diagnosed with high-grade glioma and their carers

Abstract Background This study aimed to describe the out-of-pocket costs incurred by patients diagnosed with high-grade glioma and their carers in the standard care arm of the Care-IS trial in the six to eight months following their diagnosis. Methods Carers completed monthly cost surveys detailing the out-of-pocket costs incurred by patients and carers over a six-month period. Seventy carers reported out-of-pocket costs at baseline (within two months following patient diagnosis), and a maximum of 50% of participants reported costs in any subsequent month. Costs were adjusted to 2023 AUD and reported as medians with interquartile range. Demographic factors were assessed to determine if any were significantly associated with being in the first or fourth quartile of total out-of-pocket costs at baseline. Results Median monthly costs for patient-carer dyads were highest at baseline ($535(IQR:$170-$930)), and two months post-recruitment ($314 (IQR:$150-$772)). The largest contributors to patient-carer costs were patient health service use and patient medications. Patient and carer health service use and medication costs varied over time. The median health service use and medication out-of-pocket costs for patients and carers were mostly below $100 per month, however, there was large variance in the upper 75th percentile for these cost categories. No factors were significantly associated with higher baseline out-of-pocket costs. Conclusion A HGG diagnosis has a significant and sustained financial impact on people who are diagnosed and their carers. Patients experience significant additional costs relating to their diagnosis and travel to receive care, and their carers also continue to experience sustained costs whilst managing the additional tasks associated with informal caregiving.

Preliminary Exploration of Variations in Measures of Pharyngeal Area During Nonswallowing Tasks.

Age- and disease-related changes in oropharyngeal anatomy and physiology may be identified through quantitative videofluoroscopic measures of pharyngeal area and dynamics. Pixel-based measures of nonconstricted pharyngeal area (PhAR) are typically taken during oral bolus hold tasks or on postswallow rest frames. A recent study in 87 healthy adults reported mean postswallow PhAR of 62%(C2-4)2, (range: 25%-135%), and significantly larger PhAR in males. The fact that measures were taken after initial bolus swallows without controlling for the presence of subsequent clearing swallows was identified as a potential source of variation. A subset of study participants had completed a protocol including additional static nonswallowing tasks, enabling us to explore variability across those tasks, taking sex differences into account. Videofluoroscopy still shots were analyzed for 20 healthy adults (10 males, 10 females, Mage = 26 years) in head-neutral position, chin-down and chin-up positions, a sustained /a/ vowel vocalization, and oral bolus hold tasks (1-cc, 5-cc). Trained raters used ImageJ software to measure PhAR in %(C2-4)2 units. Measures were compared to previously reported mean postswallow PhAR for the same participants: (a) explorations of sex differences; (b) pairwise linear mixed-model analyses of variance (ANOVAs) of PhAR for each nonswallowing task versus postswallow measures, controlling for sex; and (c) a combined mixed-model ANOVA to confirm comparability of the subset of tasks showing no significant differences from postswallow measures in Step 2. Overall, PhAR measures were significantly larger in male participants; however, most pairwise task comparisons did not differ by sex. No significant differences from postswallow measures were seen for 5-cc bolus hold, chin-down and chin-up postures, and the second (but not the first) of two repeated head neutral still shots. PhAR during a 5-cc bolus hold was most similar to postswallow measures: mean ± standard deviation of 51 ± 13%(C2-4)2 in females and 64 ± 16%(C2-4)2 in males. PhAR is larger in men than in women. Oral bolus hold tasks with a 5-cc liquid bolus yield similar measures to those obtained from postswallow rest frames.

Transparent Coating Systems Applied on Spruce Wood and Their Colour Stability on Exposure to an Accelerated Ageing Process

The objective of this study was to investigate the colour stability of spruce wood surfaces treated with coating systems (CS) and exposed to accelerated ageing. The tested CSs were transparent and three-layered; the top layer was modified with ultraviolet (UV) absorbers, while the base layer was modified with lignin stabiliser. Spruce wood surfaces treated with unmodified CSs were not colour-stable during the accelerated ageing process, with the surface exhibiting colour change after just 100 ageing hours. Adding specific UV absorbers into the top layer and lignin stabiliser into the base layer significantly improved the colour stability of the surface-treated wood. In all cases, however, the colour variation associated with ongoing ageing was significant. An additional study task was to determine whether the discolouration of surface-treated wood is caused by the discolouration of the wood substrate alone or also by the CS discolouration. Consequently, there was also the examination of discolouration of the individual coating materials or coating systems applied to glass slides. This testing proved that in the case of wood surface-treated with CS, without lignin stabiliser, the discolouration was the same as that of the substrate, and this was true throughout the whole ageing process. In the case of wood surface-treated with CS, but with lignin stabiliser, there were, in some cases, significant differences in discolouration between surface-treated wood and the wood substrate. These variations were especially evident during the initial 300 ageing hours.

Research Data Management in German Academia from a Multiple Logic Perspective

The requirements for research data management (RDM) have increased. Due to academia’s neoliberalization, however, researchers already face a high workload within a hypercompetitive environment. The demand to integrate RDM as an additional task into academics’ day-today actions seems to be quixotic. To deepen our understanding of early career researchers’ (ECRs) daily work arbitrage, we need to know more about their behavior, actions, and decisions in relation to RDM. Drawing on a multiple institutional logics perspective at the micro-level, we conducted 40 semistructured interviews at German higher education institutions (HEIs) to investigate how ECRs respond to institutional logics in the context of RDM. Our findings revealed three profiles – the conformist, the waverer, and the resister – that make use of different response strategies to the state, market, professional, and community logic. We contribute to institutional logic research at the micro-level and, in addition, broaden prior research on HEIs and RDM by taking neoliberal academia into account.

Effects of Motor and Cognitive Dual-Task Demands on Ankle Dorsiflexor and Plantarflexor Force Control in Older Adults

ABSTRACT Background Force steadiness can be impaired under dual-task conditions in older adults. Since this impairment is attributed to their limited attentional resources, we hypothesized that the degree of cortical activity involved in muscle contraction would affect force steadiness under dual-task conditions. To test this hypothesis, based on the premise that dorsiflexion requires more cortical resources than plantarflexion, we compared the effects of additional motor and cognitive task demands on force steadiness between dorsiflexion and plantarflexion contractions in young and older adults. Method Eighteen young and eighteen older adults performed a force tracking task by applying either isometric dorsiflexion or plantarflexion force concurrently with and without (control) secondary upper-limb motor or cognitive task. Results Force steadiness was impaired by both secondary upper-limb motor and cognitive tasks for the dorsiflexors and plantarflexors in older adults. While force steadiness was impaired similarly by additional task demands regardless of the secondary task type for the dorsiflexors, the impairment effect was larger in the secondary cognitive than motor task for the plantarflexors. Conclusion The effects of dual-task demand on force steadiness could depend on the degree of cortical activity involved in muscle contraction in older adults.

Prediction of Individual Learning Experience in Terms of “Number Of Steps” as Solution Components of Arithmetic Tasks

The paper is devoted to the study of learning in solving arithmetic problems in the conditions of digital learning. Learning is considered as a functional system, the level of differentiation of which can be related to the number of steps in problem solving. The goal of the paper is to find out the model that could more accurately describe the relationships between the number of steps and task types on Addition data and predict the number of steps on Multiplication data. The hypothesis is that with a given similarity, there is a correlation between the number of steps in solution of addition and multiplication tasks. We have created two experimental courses, “Addition” and “Multiplication” to make participants learn optimal methods of calculation of arithmetic tasks. The courses have the same structure and belong to a common domain (arithmetic tasks). It is a condition for similarity of learning. We have found out significant positive correlation between the number of steps in solution of addition and multiplication tasks on average for the sample. We have used a regression-based classification. Few models have been built for each individual personally and trained on the Addition data, then applied on the Multiplication data. The best of these models correctly predict the number of steps in 33–40% of tasks (SD = 17–22%, max = 88%), in other tasks they give a prediction with a small error of 1–2 units, which indicates its medium predictive ability.

Creating window applications in Python using the PyQt5 library tools

The section "Programming" at the advanced level of studying the informatics course in high school includes consideration of issues related to the design of the user interface. If the study of the basics of programming is carried out using the Python language, it is reasonable to develop window applications using this language. Recently, the PyQt library has become increasingly popular, which makes it relevant to create methodological materials to familiarize schoolchildren with the capabilities of this library.It is advisable to carry out training in accordance with the reverse engineering technology, which consists in the fact that students do not write program code from scratch, but explore the finished product. At the first stage, you can organize the activities of schoolchildren by completing tasks to study the finished program; at the next step, offer to analyze the appearance of the finished application, highlight its elements and select tools for their creation; finally, provide additional tasks that involve independent study by students of the class features not considered earlier.The article offers reference material for familiarizing schoolchildren with the main capabilities of the library, tasks for lab sessions and home assignment.

Enhancing precision in 3D printing for highly functional printing with high-speed vision

3D printing has revolutionized product design and manufacturing across various industries by enabling the creation of complex geometries with minimal waste. Despite its advancements, 3D printing still faces significant challenges, including spatial constraints and process control limitations. This paper introduces novel approaches to improve the functionality and precision of material extrusion 3D printers for the fused deposition modeling method, particularly for additional printing tasks such as printing on existing objects or continuing a print on a relocated object without prior knowledge of its position or even the environment is changed. We introduce a compensation system integrating a high-speed vision system for robot arms to address these challenges. Our system employs a three-step pose estimation process—fast point feature histograms (FPFH)-based, corner-based, and sub-pixel edge-based methods—to ensure high accuracy in restoring the position of printed pieces for additional printing tasks on a given object. Experimental results demonstrate substantial improvements in printing precision, with the system achieving sub-millimeter and sub-pixel accuracy. These advancements not only eliminate work area constraints but also enhance the adaptability and reliability of 3D printing processes.

Altering prosthetic alignment does not affect hip and low back joint loading during sit-to-stand in people with a transtibial amputation

People with a transtibial amputation (TTA) have greater prevalence of low back and hip joint pain compared to the general population. Altered movement, loading patterns, and neuromuscular activation during daily tasks like sit-to-stand likely contribute to these high rates of pain. In addition, muscle activation, ground reaction forces, and trunk range of motion can be affected by prosthetic alignment during sit-to-stand. However, it is unclear how prosthetic alignment affects joint contact forces during this task. The purpose of this study was to investigate the effect of prosthetic alignment on hip and low-back joint loading in people with TTA during sit-to-stand. Kinematics, ground reaction forces, and muscle activity data were collected from 10 people with TTA and 10 age- and sex- matched individuals without limb loss during five self-paced sit-to-stand trials. Participants with TTA completed the sit-to-stand task with their prescribed alignment and six altered alignment conditions (±10 mm anterior/posterior, medial/lateral, and ± 20 mm short/tall). A musculoskeletal model was used to calculate hip and L4-L5 joint loading. There were no differences in hip or L4-L5 joint loading between alignments. Participants with TTA had a greater peak hip joint contact force on the intact side hip compared to the amputated side hip across all alignments. Participants with TTA had greater L4-L5 joint contact force compared to those without amputation. While prosthetic alignment did not affect joint loading during sit-to-stand, future work on additional dynamic tasks is needed to better understand the potential role of prosthetic alignment on joint loading.

The importance of revenues from spa fee in financing municipalities in Poland

Motivation: The subject of interest presented in this study is the problem of spa fee and the resulting municipal revenues. In accordance with the international and constitutional standard of financial adequacy, including this fee in the revenue catalogue of only some municipalities should result from their specificity, i.e. generating additional budgetary expenditure not incurred by other municipalities. Aim: The purpose of this paper is to address the systemic differences of spa municipalities, and primarily the additional tasks imposed on them, as well as to analyse and assess the importance of spa fee in the financial management of municipalities. Based on the analysis of this fee legal structure, and in particular its subject, an attempt was made to indicate the factors influencing its fiscal efficiency and significance. Results: The fiscal efficiency of the discussed fee, as compared to other revenue categories, and its importance in the municipal financing structure are small (approx. 0.028% of the total municipal revenues and 1.41% of the total revenues generated by spa municipalities). The main factor influencing the amount of revenues from the fee and its share in the revenue structure is related to tourist activity in the municipality, mainly referring to a therapeutic treatment of natural persons. In the municipalities characterized by high tourist traffic, which results in an extensive accommodation offer corresponding to the demand, the importance of the fee in terms of financing is at a significant level, reaching even 6.8% of total revenues in the entire analysed period, i.e. 2017-2021 and over 8.8% in 2017. The occurrence of such cases is an argument proving the significant revenue potential of the fee. Increasing its use, in addition to developing both therapeutic and accommodation infrastructure in a municipality also requires taking action aimed at ensuring better efficiency of the spa fee collection.

Empirical evidence of the role of executive functions in tolerance of emotional distress

ABSTRACT Executive functions are domain general and therefore coordinate other processes, such as emotion regulation. One emotion regulation skill that has gained interest in the last decade is distress tolerance (DT), but its relationship with executive functions has been poorly explored. The aim of this study is to investigate the relationships between executive functions and self-perceived and behavioural DT. A total of 196 university students (age: M = 22.63 years; SD = 3.26) completed a Reading Span Task, the Five Digits Test, the Paced Auditory Serial Addition Task, and the Distress Tolerance Scale. Better executive functioning was related to higher self-perceived DT. Regarding behavioural DT, students with high DT showed greater cognitive flexibility and greater inhibition than students with low behavioural DT (no differences were found for working memory). The study contribute to the knowledge of the relationships between cognitive and emotional self-regulatory processes and provides a starting point for future research.

Suicidality, perceived chronic stress, and stress-induced cortisol changes of individuals with schizophrenia.

The associations of suicidality with stress are poorly studied in schizophrenia. The study aimed to determine whether suicidality was correlated with perceived chronic stress and the cortisol fluctuations under stress tasks in schizophrenia. High suicidality was defined as a lifetime history of suicide attempts or suicidal ideation in the past 2weeks. Individuals with schizophrenia and high suicidality (SZ-HS, n=59), with low suicidality (SZ-LS, n=207), and healthy controls (HC, n=196) finished the Perceived Stress Scale. Then, they participated in an experiment that induced stress using the Paced Auditory Serial Addition Task and the Mirror Tracing Persistence Task. Negative affect was measured at baseline and after finishing each task. The salivary cortisol was collected before-, after 20min, and after 40min of the tasks. SZ-HS had elevated perceived stress than SZ-LS and HC. Mixed effect models showed that stress tasks induced cortisol changes in all groups; cortisol of SZ-LS was reduced more than HC, but SZ-HS and SZ-LS did not differ in cortisol fluctuations. SZ-HS and SZ-LS experienced similar negative affect changes during tasks and the difference in withdrawal rates was nonsignificant. SZ-HS had an increased error rate than SZ-LS. In conclusion, suicidality was correlated with high-level perceived stress but did not result in differences in cortisol reactivities under stress tasks. It suggests the inconsistency between appraisal of stress and biological stress system disturbance among SZ-HS compared to SZ-LS.

Assessing cost and cost savings of teleconsultation in long-term care facilities: a time-driven activity-based costing analysis within a value-based healthcare framework

BackgroundQuebec’s healthcare system faces significant challenges due to labour shortage, particularly in long-term care facilities (CHSLDs). The aging population and increasing demand for services compound this issue. Teleconsultation presents a promising solution to mitigate labour shortage, especially in small CHSLDs outside urban centers. This study aims to evaluate the cost and cost savings associated with teleconsultation in CHSLDs, utilizing the Time-Driven Activity-Based Costing (TDABC) model within the framework of Value-Based Healthcare (VBHC).MethodsThis study focuses on CHSLDs with fewer than 50 beds in remote regions of Quebec, where teleconsultation for nighttime nursing care was implemented. Time and cost data were collected from three CHSLDs over varying periods. The TDABC model, aligned with VBHC principles, was applied through five steps, including process mapping, estimating activity times, calculating resource costs, and determining total costs.ResultsTeleconsultation increased the cost per minute for nursing care compared to traditional care, attributed to additional tasks during remote consultations and potential technical challenges. However, cost savings were realized due to reduced need for onsite nursing staff during non-eventful nights. Overall, substantial savings were observed over the project duration, aligning with VBHC’s focus on delivering high-value healthcare.ConclusionsThis study contributes both theoretically and practically by demonstrating the application of TDABC within the VBHC framework in CHSLDs. The findings support the cost savings from the use of teleconsultation in small CHSLDs. Further research should explore the long-term sustainability and scalability of teleconsultation across different CHSLD sizes and settings within the VBHC context to ensure high-value healthcare delivery.

Underwater variable zoom: Depth-guided perception network for underwater image enhancement

The underwater images often suffer from color deviations and blurred details. To address these issues, many methods employ networks with an encoder/decoder structure to enhance the images. However, the direct skip connection overlooks the differences between pre- and post-features, and deep network learning introduces information loss. This paper presents an underwater image enhancement network that focuses on pre-post differences. The network utilizes a multi-scale input and output framework to facilitate the underwater image enhancement process. A novel cross-wise transformer module (CTM) is introduced to guide the interactive learning of features from different periods, thereby enhancing the emphasis on detail-degraded regions. To compensate for the information loss within the deep network, a feature supplement module (FSM) is devised for each learning stage. FSM merges the multi-scale input features, effectively enhancing the visibility of underwater images. Experimental results across several datasets demonstrate that the integrated modules yield significant enhancements in network performance. The proposed network exhibits outstanding performance in both visual comparisons and quantitative metrics. Furthermore, the network also exhibits good adaptability in additional visual tasks without the need for parameter tuning. The code and results are released in https://github.com/WindySprint/UVZ.

Brainchop: Providing an Edge Ecosystem for Deployment of Neuroimaging Artificial Intelligence Models.

Deep learning has proven highly effective in various medical imaging scenarios, yet the lack of an efficient distribution platform hinders developers from sharing models with end-users. Here, we describe brainchop, a fully functional web application that allows users to apply deep learning models developed with Python to local neuroimaging data from within their browser. While training artificial intelligence models is computationally expensive, applying existing models to neuroimaging data can be very fast; brainchop harnesses the end user's graphics card such that brain extraction, tissue segmentation, and regional parcellation require only seconds and avoids privacy issues that impact cloud-based solutions. The integrated visualization allows users to validate the inferences, and includes tools to annotate and edit the resulting segmentations. Our pure JavaScript implementation includes optimized helper functions for conforming volumes and filtering connected components with minimal dependencies. Brainchop provides a simple mechanism for distributing models for additional image processing tasks, including registration and identification of abnormal tissue, including tumors, lesions and hyperintensities. We discuss considerations for other AI model developers to leverage this open-source resource.

Multi-task deep latent spaces for cancer survival and drug sensitivity prediction.

Cancer is a very heterogeneous disease that can be difficult to treat without addressing the specific mechanisms driving tumour progression in a given patient. High-throughput screening and sequencing data from cancer cell-lines has driven many developments in drug development, however, there are important aspects crucial to precision medicine that are often overlooked, namely the inherent differences between tumours in patients and the cell-lines used to model them in vitro. Recent developments in transfer learning methods for patient and cell-line data have shown progress in translating results from cell-lines to individual patients in silico. However, transfer learning can be forceful and there is a risk that clinically relevant patterns in the omics profiles of patients are lost in the process. We present MODAE, a novel deep learning algorithm to integrate omics profiles from cell-lines and patients for the purposes of exploring precision medicine opportunities. MODAE implements patient survival prediction as an additional task in a drug-sensitivity transfer learning schema and aims to balance autoencoding, domain adaptation, drug-sensitivity prediction, and survival prediction objectives in order to better preserve the heterogeneity between patients that is relevant to survival. While burdened with these additional tasks, MODAE performed on par with baseline survival models, but struggled in the drug-sensitivity prediction task. Nevertheless, these preliminary results were promising and show that MODAE provides a novel AI-based method for prioritizing drug treatments for high-risk patients. https://github.com/UEFBiomedicalInformaticsLab/MODAE.