Search

Developing spinal circuits generate patterned motor outputs while many neurons with high membrane resistances are still maturing. In the spinal cord of hatchling frog tadpoles of unknown sex, we found that the firing reliability in swimming of inhibitory interneurons with commissural and ipsilateral ascending axons was negatively correlated with their cellular membrane resistance. Further analyses showed that neurons with higher resistances had outward rectifying properties, low firing thresholds, and little delay in firing evoked by current injections. Input synaptic currents these neurons received during swimming, either compound, unitary current amplitudes, or unitary synaptic current numbers, were scaled with their membrane resistances, but their own synaptic outputs were correlated with membrane resistances of their postsynaptic partners. Analyses of neuronal dendritic and axonal lengths and their activities in swimming and cellular input resistances did not reveal a clear correlation pattern. Incorporating these electrical and synaptic properties into a computer swimming model produced robust swimming rhythms, whereas randomizing input synaptic strengths led to the breakdown of swimming rhythms, coupled with less synchronized spiking in the inhibitory interneurons. We conclude that the recruitment of these developing interneurons in swimming can be predicted by cellular input resistances, but the order is opposite to the motor-strength-based recruitment scheme depicted by Henneman’s size principle. This form of recruitment/integration order in development before the emergence of refined motor control is progressive potentially with neuronal acquisition of mature electrical and synaptic properties, among which the scaling of input synaptic strengths with cellular input resistance plays a critical role.SIGNIFICANCE STATEMENTThe mechanisms on how interneurons are recruited to participate in circuit function in developing neuronal systems are rarely investigated. In 2-d-old frog tadpole spinal cord, we found the recruitment of inhibitory interneurons in swimming is inversely correlated with cellular input resistances, opposite to the motor-strength-based recruitment order depicted by Henneman’s size principle. Further analyses showed the amplitude of synaptic inputs that neurons received during swimming was inversely correlated with cellular input resistances. Randomizing/reversing the relation between input synaptic strengths and membrane resistances in modeling broke down swimming rhythms. Therefore, the recruitment or integration of these interneurons is conditional on the acquisition of several electrical and synaptic properties including the scaling of input synaptic strengths with cellular input resistances.

Background and objective: Work-related stress affects a large part of today's workforce and is known to have detrimental effects on physical and mental health. Continuous and unobtrusive stress detection may help prevent and reduce stress by providing personalised feedback and allowing for the development of just-in-time adaptive health interventions for stress management. Previous studies on stress detection in work environments have often struggled to adequately reflect real-world conditions in controlled laboratory experiments. To close this gap, in this paper, we present a machine learning methodology for stress detection based on multimodal data collected from unobtrusive sources in an experiment simulating a realistic group office environment (N=90). Methods: We derive mouse, keyboard and heart rate variability features to detect three levels of perceived stress, valence and arousal with support vector machines, random forests and gradient boosting models using 10-fold cross-validation. We interpret the contributions of features to the model predictions with SHapley Additive exPlanations (SHAP) value plots. Results: The gradient boosting models based on mouse and keyboard features obtained the highest average F1 scores of 0.625, 0.631 and 0.775 for the multiclass prediction of perceived stress, arousal and valence, respectively. Our results indicate that the combination of mouse and keyboard features may be better suited to detect stress in office environments than heart rate variability, despite physiological signal-based stress detection being more established in theory and research. The analysis of SHAP value plots shows that specific mouse movement and typing behaviours may characterise different levels of stress. Conclusions: Our study fills different methodological gaps in the research on the automated detection of stress in office environments, such as approximating real-life conditions in a laboratory and combining physiological and behavioural data sources. Implications for field studies on personalised, interpretable ML-based systems for the real-time detection of stress in real office environments are also discussed., Journal of Biomedical Informatics, 139, ISSN:1532-0464

Heart rate variability biofeedback (HRV-BF) is frequently used for stress management. Recently, virtual reality technology has gained attention for delivery, promising higher immersion, motivation, and attention than classical screens. However, the effects of different technologies and breathing techniques are not yet understood. In this study, 107 healthy participants completed a session in one of four conditions: HRV-BF on a desktop screen, HRV-BF via head-mounted display (HMD), standardised paced breathing without feedback (sPB) on a screen, or sPB via HMD. All setups significantly reduced perceived stress and increased heart rate variability (HRV). Practising HRV-BF, however, led to significantly greater increases in the low frequency band of HRV and cardiac coherence than sPB, and using an HMD rather than a screen also led to greater increases in cardiac coherence. As for user experience, immersion adaptation and interface quality were higher for HMDs and facilitating conditions were better for screens. While all technique and technology combinations are feasible and effective for stress management, immersing oneself in virtual reality with an HMD for HRV-BF might yield increased benefits in terms of HRV target outcomes and several user experience measures. Future research is necessary to confirm any long-term effects of such a mode of delivery., Computers in Human Behavior, 141, ISSN:0747-5632, ISSN:1873-7692

BACKGROUND Work stress places a heavy economic and disease burden on society. Recent technological advances include digital health interventions for helping employees prevent and manage their stress at work effectively. Although such digital solutions come with an array of ethical risks, especially if they involve biomedical big data, the incorporation of employees’ values in their design and deployment has been widely overlooked. OBJECTIVE To bridge this gap, we used the value sensitive design (VSD) framework to identify relevant values concerning a digital stress management intervention (dSMI) at the workplace, assess how users comprehend these values, and derive specific requirements for an ethics-informed design of dSMIs. VSD is a theoretically grounded framework that front-loads ethics by accounting for values throughout the design process of a technology. METHODS We conducted a literature search to identify relevant values of dSMIs at the workplace. To understand how potential users comprehend these values and derive design requirements, we conducted a web-based study that contained closed and open questions with employees of a Swiss company, allowing both quantitative and qualitative analyses. RESULTS The values health and well-being, privacy, autonomy, accountability, and identity were identified through our literature search. Statistical analysis of 170 responses from the web-based study revealed that the intention to use and perceived usefulness of a dSMI were moderate to high. Employees’ moderate to high health and well-being concerns included worries that a dSMI would not be effective or would even amplify their stress levels. Privacy concerns were also rated on the higher end of the score range, whereas concerns regarding autonomy, accountability, and identity were rated lower. Moreover, a personalized dSMI with a monitoring system involving a machine learning-based analysis of data led to significantly higher privacy (P=.009) and accountability concerns (P=.04) than a dSMI without a monitoring system. In addition, integrability, user-friendliness, and digital independence emerged as novel values from the qualitative analysis of 85 text responses. CONCLUSIONS Although most surveyed employees were willing to use a dSMI at the workplace, there were considerable health and well-being concerns with regard to effectiveness and problem perpetuation. For a minority of employees who value digital independence, a nondigital offer might be more suitable. In terms of the type of dSMI, privacy and accountability concerns must be particularly well addressed if a machine learning-based monitoring component is included. To help mitigate these concerns, we propose specific requirements to support the VSD of a dSMI at the workplace. The results of this work and our research protocol will inform future research on VSD-based interventions and further advance the integration of ethics in digital health.

Despite the presumed value of advance directives, research to demonstrate impact has shown mixed results. For advance directives to serve their role promoting patient autonomy, it is important that patients be informed decision makers. The capacity to make decisions depends upon understanding, appreciation, reasoning, and communication. Advance directives are in part faulty because these elements are often limited. The present paper explores how the application of digital technology could be organized around a framework promoting these four elements. Given the state of digital advancements, there is great potential for advance directives to be meaningfully enhanced. The beneficial effects of incorporating digital technology would be maximized if they were organized around the aim of making advance directives not only documents for declaring preferences but also ethics-driven tools with decision aid functionality. Such advance directives would aid users in making decisions that involve complex factors with potentially far-reaching impact and would also elucidate the users' thought processes to aid those tasked with interpreting and implementing decisions based on an advance directive. Such advance directives might have embedded interactive features for learning; access to content that furthers one's ability to project oneself into possible, future scenarios; review of the logical consistency of stated preferences; and modes for effective electronic sharing. Important considerations include mitigating the introduction of bias depending on the presentation of information; optimizing interfacing with surrogate decision makers and treating clinicians; and prioritizing essential components to respect time constraints.

Ambiguous sensory information can lead to spontaneous alternations between perceptual states, recently shown to extend to tactile perception. The authors recently proposed a simplified form of tactile rivalry which evokes two competing percepts for a fixed difference in input amplitudes across antiphase, pulsatile stimulation of the left and right fingers. This study addresses the need for a tactile rivalry model that captures the dynamics of perceptual alternations and that incorporates the structure of the somatosensory system. The model features hierarchical processing with two stages; a first stage resolves perceptual competition, leading to perceptual alternations; and a second stage encodes perceptual interpretations. The first stage could be located downstream of brainstem nuclei and the second stage could be located within the primary somatosensory cortex (area 3b). The model captures dynamical features specific to the tactile rivalry percepts and produces general characteristics of perceptual rivalry: input strength dependence of dominance times (Levelt’s proposition II), short-tailed skewness of dominance time distributions and the ratio of distribution moments. The presented modelling work leads to experimentally testable predictions. The same hierarchical model could generalise to account for percept formation, competition and alternations for bistable stimuli that involve pulsatile inputs from the visual and auditory domains.Author summaryPerceptual ambiguity involving the touch sensation has seen increased recent interest. It provides interesting opportunity to explore how our perceptual experience is resolved by dynamic computations in the brain. We recently proposed a simple form of tactile rivalry where stimuli consisted of antiphase sequences of high and low intensity pulses delivered to the right and left index fingers. The stimulus can be perceived as either one simultaneous pattern of vibration on both hands, or as a pattern of vibrations that jumps from one hand to the other, giving a sensation of apparent movement. During long presentation of the stimuli, one’s perception switches every 5–20 seconds between these two interpretations, a phenomenon called tactile perceptual bistability. This study presents the first computational model for tactile bistability and is based on the structure of sensory brain areas. The model captures important characteristics of perceptual interpretations for tactile rivalry. We offer predictions in terms of how left-right tactile intensity differences are encoded and propose a location for the encoding of perceptual interpretations in sensory brain areas. The model provides a generalisable framework that can make useful predictions for future behavioural experiments with tactile and other types of stimuli.

Artificial intelligence (AI) systems are quickly gaining ground in healthcare and clinical decision-making. However, it is still unclear in what way AI can or should support decision-making that is based on incapacitated patients' values and goals of care, which often requires input from clinicians and loved ones. Although the use of algorithms to predict patients' most likely preferred treatment has been discussed in the medical ethics literature, no example has been realised in clinical practice. This is due, arguably, to the lack of a structured approach to the epistemological, ethical and pragmatic challenges arising from the design and use of such algorithms. The present paper offers a new perspective on the problem by suggesting that preference predicting AIs be viewed as sociotechnical systems with distinctive life-cycles. We explore how both known and novel challenges map onto the different stages of development, highlighting interdisciplinary strategies for their resolution., Journal of Medical Ethics, 49 (3), ISSN:0306-6800

In this paper we argue that transparency of machine learning algorithms, just as explanation, can be defined at different levels of abstraction. We criticize recent attempts to identify the explanation of black box algorithms with making their decisions (post-hoc) interpretable, focusing our discussion on counterfactual explanations. These approaches to explanation simplify the real nature of the black boxes and risk misleading the public about the normative features of a model. We propose a new form of algorithmic transparency, that consists in explaining algorithms as an intentional product, that serves a particular goal, or multiple goals (Daniel Dennet’s design stance) in a given domain of applicability, and that provides a measure of the extent to which such a goal is achieved, and evidence about the way that measure has been reached. We call such idea of algorithmic transparency “design publicity.” We argue that design publicity can be more easily linked with the justification of the use and of the design of the algorithm, and of each individual decision following from it. In comparison to post-hoc explanations of individual algorithmic decisions, design publicity meets a different demand (the demand for impersonal justification) of the explainee. Finally, we argue that when models that pursue justifiable goals (which may include fairness as avoidance of bias towards specific groups) to a justifiable degree are used consistently, the resulting decisions are all justified even if some of them are (unavoidably) based on incorrect predictions. For this argument, we rely on John Rawls’s idea of procedural justice applied to algorithms conceived as institutions.

Context: A landscape is defined as a “system of ecosystems” and this is a model in which karst areas can easily be integrated. In karst areas, much of the connectivity between the units of the landscape is underground, with aquifers and caves forming a continuous layered tissue. However, underground environments are among the least studied landscapes on Earth because of limited accessibility and the difficulty of performing surveys. Objectives: The aim of this paper is to provide a conceptual framework for applying principles of landscape ecology to research on karst environments. Methods: By adapting the standard patch-corridor-matrix model to a 3d model, the main issues that need to be addressed were identified. These include identifying the main morphological (surface and underground) karst features; determining the landscape structure through its features, composition, and configuration; and developing adequate indices. Results: The landscape spatial structure of different karst areas influences fundamental ecological functions and biodiversity patterns. Determining how structure, biodiversity, and functions relate reveals important insights into the functioning of karst systems. Emphasizing the provisioning of ecosystem services is essential in supporting the concept that karst regions are vital for human well-being because they host valuable resources and fundamental ecosystem processes. The paper discusses how this framework helps address anthropogenic impacts and conservation issues on karst. Conclusions: The potential of applying a landscape approach to karst systems lies in developing models that provide ecological information relevant to understanding karst systems and understanding their implications for natural resources management.

Undetectable measurable residual disease (uMRD) is achievable in patients with chronic lymphocytic leukemia (CLL) with the BCL2-inhibitor venetoclax alone or combined with the Bruton’s tyrosine kinase inhibitor ibrutinib. This phase 2, multicenter, MRD-driven study was designed to discontinue treatment upon reaching uMRD4 (

Immersive analytics has the potential to promote collaboration in machine learning (ML). This is desired due to the specific characteristics of ML modeling in practice, namely the complexity of ML, the interdisciplinary approach in industry, and the need for ML interpretability. In this work, we introduce an augmented reality-based system for collaborative immersive analytics that is designed to support ML modeling in interdisciplinary teams. We conduct a user study to examine how collaboration unfolds when users with different professional backgrounds and levels of ML knowledge interact in solving different ML tasks. Specifically, we use the pair analytics methodology and performance assessments to assess collaboration and explore their interactions with each other and the system. Based on this, we provide qualitative and quantitative results on both teamwork and taskwork during collaboration. Our results show how our system elicits sustained collaboration as measured along six distinct dimensions. We finally make recommendations how immersive systems should be designed to elicit sustained collaboration in ML modeling., Comment: To appear at the 25th ACM Conference On Computer-Supported Cooperative Work And Social Computing (CSCW '22)

We analyse periodic solutions in a system of four delayed differential equations forced by periodic inputs representing two competing neural populations connected with fast mutual excitation and slow delayed inhibition. The combination of mechanisms generates a rich dynamical structure that we are able to characterize using slow-fast dissection and a binary classification of states. We previously proved the existence conditions of all possible states 1:1 locked to the inputs and applied this analysis to the tracking of the rhythms perceived when listening to alternating sequences of low and high tones. Here we extend this analysis using analytical and computational tools by proving the existence a set of n:1 periodically locked states and their location in parameter space. Firstly we examine cycle skipping states and find that they accumulate in an infinite cascade of period-incrementing bifurcations with increasing periods for decreasing values of the local input strength. Secondly we analyse periodic solutions that alternate between 1:1 locked states that repeat after an integer multiple of the input period (swapping states). We show that such states accumulate in similar bifurcation cascades with decreasing values of the lateral input strength. We report a parameter-dependent scaling constant for the ratio of widths of successive regions in the cascades, which generalises across cycle skipping and swapping states. The periodic states reported here - emergent behaviours in the model - can be linked to known phenomena in auditory perception that are beyond the original scope of the model’s design.

Relying on shared tasks and stimuli to conduct research can enhance the replicability of findings and allow a community of researchers to collect large data sets across multiple experiments. This approach is particularly relevant for experiments in spatial navigation, which often require the development of unfamiliar large-scale virtual environments to test participants. One challenge with shared platforms is that undetected technical errors, rather than being restricted to individual studies, become pervasive across many studies. Here, we discuss the discovery of a software bug in a virtual environment platform used to investigate individual differences in spatial navigation: Virtual Silcton. The bug, which was difficult to detect for several reasons, resulted in storing the absolute value of a direction in a pointing task rather than the signed direction and rendered the original sign of the direction unrecoverable. To assess the impact of the bug on published findings, we collected a new data set for comparison. Results revealed that although the bug caused suppression in pointing errors and had different effects across people (less accurate navigators had more suppression), the effect of the bug on published data is small, partially explaining the difficulty in detecting the bug. We also used the new data set to develop a tool that allows researchers who have previously used Virtual Silcton to evaluate the impact of the bug on their findings. We summarize the ways that shared open materials, shared data, and collaboration can pave the way for better science to prevent errors in the future. (PsycInfo Database Record (c) 2022 APA, all rights reserved).

This paper addresses the achievements of the QU4LITY project, funded by the Swiss Innovation Agency. Within this research project, the automation back-bone developed for the SUPSI MiniFactory [1], coupled with adaptive Machine Learning (ML) algorithms, is exploited to test numerous families of bearings. The MiniFactory is associated with an evolving digital profile, a digital twin, based on constant synchronization through IoT devices, that encompasses a massive, real-time, real-world data, gathered from the different sensors interfaced via OPC-UA protocol. This representation feeds a ML algorithm capable of 1) detecting defective bearings and 2) continually tuning the quality testing process parameters based on the analysis performed on the gathered data. Specifically, the identification of defective bearings is performed by a voting classifier fed by statistical metrics measured from the collected experiments. Our approach also aims at continually learning from the tests performed with the cell: the ML algorithm is tuned and adjusted every time a new set of tests is executed. Tests show that the proposed ML classifier accurately distinguishes damaged and uncorrupted bearings (accuracy ∼ 100%, precision ∼100%, recall ∼100%, TNR ∼100%). The digitalization of the quality control process is furtherly enriched by the development of a data aggregator platform. The platform fetches, cleans and aggregates data from every different machine belonging to the quality cell, enabling, also remotely, the pattern-tracking, the significant KPIs displaying and the comprehensive system behavior monitoring. The platform features also as HMI for the operator, who can monitor parameters and schedule new test campaigns.

SUMMARYAnimal behaviour is based on interaction between nervous, musculoskeletal and environmental systems. How does an animal process sensory stimuli, use it to decide whether and how to respond, and initiate the locomotor behaviour? We build the whole body computer models of a simple vertebrate with a complete chain of neural circuits and body units for sensory information processing, decision-making, generation of spiking activities, muscle innervation, body flexion, body-water interaction, and movement. Our Central Nervous System (CNS) model generates biologically-realistic spiking and reveals that sensory memory populations on two hindbrain sides compete for swimming initiation and first body flexion. Biomechanical 3-dimensional “Virtual Tadpole” (VT) model is constructed to evaluate if motor outputs of CNS model can produce swimming-like movements in a volume of “water”. We find that whole animal modelling generates reliable and realistic swimming. The combination of CNS and VT models opens a new perspective for experiments with immobilised tadpoles.

Real engines of the artificial intelligence (AI) revolution, machine learning (ML) models, and algorithms are embedded nowadays in many services and products around us. As a society, we argue it is now necessary to transition into a phronetic paradigm focused on the ethical dilemmas stemming from the conception and application of AIs to define actionable recommendations as well as normative solutions. However, both academic research and society-driven initiatives are still quite far from clearly defining a solid program of study and intervention. In this contribution, we will focus on selected ethical investigations around AI by proposing an incremental model of trust that can be applied to both human-human and human-AI interactions. Starting with a quick overview of the existing accounts of trust, with special attention to Taddeo’s concept of “e-trust,” we will discuss all the components of the proposed model and the reasons to trust in human-AI interactions in an example of relevance for business organizations. We end this contribution with an analysis of the epistemic and pragmatic reasons of trust in human-AI interactions and with a discussion of kinds of normativity in trustworthiness of AIs., Philosophy & Technology, 33 (3), ISSN:2210-5433, ISSN:2210-5441

Previous studies showed that cobalt silicide can form ohmic contacts to p-type 6H-SiC by directly reacting cobalt with 6H-SiC. Similar results can be achieved on 4H-SiC, given the similarities between the different silicon carbide polytypes. However, previous studies using multilayer deposition of silicon/cobalt on 4H-SiC gave ohmic contacts to n-type. In this study, we investigated the cobalt silicide/4H-SiC system to answer two research questions. Can cobalt contacts be self-aligned to contact holes to 4H-SiC? Are the self-aligned contacts ohmic to n-type, p-type, both or neither? Using x-ray diffraction, it was found that a mixture of silicides ( $$\hbox {Co}_2\hbox {Si}$$ and CoSi) was reliably formed at 800 $$^\circ $$ C using rapid thermal processing. The cobalt silicide mixture becomes ohmic to epitaxially grown n-type ( $$1\times 10^{19} \hbox {cm}^{-3}$$ ) if annealed at 1000 $$^\circ $$ C, while it shows rectifying properties to epitaxially grown p-type ( $$1\times 10^{19} \hbox {cm}^{-3}$$ ) for all tested anneal temperatures in the range 800–1000 $$^\circ $$ C. The specific contact resistivity ( $$\rho _\mathrm{C}$$ ) to n-type was $$4.3 \times 10^{-4}$$ $$\mathrm {\Omega }$$ $$\,\hbox {cm}^{2}$$ . This work opens the possibility to investigate other self-aligned contacts to silicon carbide.

As manufacturing industry is moving its steps towards a more digital, smart and flexible scenario, the changes required to achieve the expectations of the Industry 4.0 (I4.0) framework are numerous and extensive. Though, a general lack of understanding of how new technologies could be integrated and shall be implemented is present, limiting the rate of adoption of such changes and the related beneficial impacts. This paper describes the implementation of a smart-factory at the University of Applied Sciences and Arts of Southern Switzerland (SUPSI) aiming at filling the gap in I4.0 related skills development thorough a learning by doing approach, and providing a research platform that could foster collaboration of practitioners and academia on the development and testing of new technologies. The developed factory integrates different production technologies such as additive manufacturing, laser processing and milling, in order to produce a highly customizable item consisting in a TANGRAM game-set, packaged into personalized boxes. The entire factory is coupled with its digital twin, which is fed by an exhaustive monitoring infrastructure composed by vision systems and high precision measurement instruments, allowing to track in real time plant processes. The design has been carried out in order to make the smart factory serving as a mean to face both educational and research challenges at many different levels. As an educational mean, students and professionals have the chance to dive into manufacturing history experiencing both classical automation topics (PLC, MES and SCADA programming, precision axes control and pneumatics), as well as more advanced technologies, typical of the most advanced smart-factories (IoT, vision systems, simulation and digital twin, advanced measuring methods and smart production management systems). From a research point of view, the factory functions as a pilot plant for internal research and applied industrial projects, on the top of which applications, manufacturing methods and technologies are developed, tested and integrated.

In the auditory streaming paradigm alternating sequences of pure tones can be perceived as a single galloping rhythm (integration) or as two sequences with separated low and high tones (segregation). Although studied for decades, the neural mechanisms underlining this perceptual grouping of sound remains a mystery. With the aim of identifying a plausible minimal neural circuit that captures this phenomenon, we propose a firing rate model with two periodically forced neural populations coupled by fast direct excitation and slow delayed inhibition. By analyzing the model in a non-smooth, slow-fast regime we analytically prove the existence of a rich repertoire of dynamical states and of their parameter dependent transitions. We impose plausible parameter restrictions and link all states with perceptual interpretations. Regions of stimulus parameters occupied by states linked with each percept matches those found in behavioral experiments. Our model suggests that slow inhibition masks the perception of subsequent tones during segregation (forward masking), while fast excitation enables integration for large pitch differences between the two tones., Comment: Supplementary Material is at the end of the file

In their article 'Who is afraid of black box algorithms? On the epistemological and ethical basis of trust in medical AI', Duran and Jongsma discuss the epistemic and ethical challenges raised by black box algorithms in medical practice. The opacity of black box algorithms is an obstacle to the trustworthiness of their outcomes. Moreover, the use of opaque algorithms is not normatively justified in medical practice. The authors introduce a formalism, called computational reliabilism, which allows generating justified beliefs on the algorithm reliability and trustworthy outcomes of artificial intelligence (AI) systems by means of epistemic warrants, called reliability indicators. However, they remark the need for reliability indicators specific to black box algorithms and that justified knowledge is not sufficient to justify normatively the actions of the physicians using medical AI systems. Therefore, Duran and Jongsma advocate for a more transparent design and implementation of black box algorithms, providing a series of recommendations to mitigate the epistemic and ethical challenges behind their use in medical practice. In this response, I argue that a peculiar form of black box algorithm transparency, called design publicity, may efficiently implement these recommendations. Design publicity encodes epistemic, that is, reliability indicators, and ethical recommendations for black box algorithms by means of four subtypes of transparency. These target the values and goals, their translation into design requirements, the performance and consistency of the algorithm altogether. I discuss design publicity applying it to a use case focused on the automated classification of skin lesions from medical images., Journal of Medical Ethics, 48 (7), ISSN:0306-6800

BACKGROUND Language use and social interactions have demonstrated a close relationship with cognitive measures. It is important to improve the understanding of language use and behavioral indicators from social context to study the early prediction of cognitive decline among healthy populations of older adults. OBJECTIVE This study aimed at predicting an important cognitive ability, working memory, of 98 healthy older adults participating in a 4-day-long naturalistic observation study. We used linguistic measures, part-of-speech (POS) tags, and social context information extracted from 7450 real-life audio recordings of their everyday conversations. METHODS The methods in this study comprise (1) the generation of linguistic measures, representing idea density, vocabulary richness, and grammatical complexity, as well as POS tags with natural language processing (NLP) from the transcripts of real-life conversations and (2) the training of machine learning models to predict working memory using linguistic measures, POS tags, and social context information. We measured working memory using (1) the Keep Track test, (2) the Consonant Updating test, and (3) a composite score based on the Keep Track and Consonant Updating tests. We trained machine learning models using random forest, extreme gradient boosting, and light gradient boosting machine algorithms, implementing repeated cross-validation with different numbers of folds and repeats and recursive feature elimination to avoid overfitting. RESULTS For all three prediction routines, models comprising linguistic measures, POS tags, and social context information improved the baseline performance on the validation folds. The best model for the Keep Track prediction routine comprised linguistic measures, POS tags, and social context variables. The best models for prediction of the Consonant Updating score and the composite working memory score comprised POS tags only. CONCLUSIONS The results suggest that machine learning and NLP may support the prediction of working memory using, in particular, linguistic measures and social context information extracted from the everyday conversations of healthy older adults. Our findings may support the design of an early warning system to be used in longitudinal studies that collects cognitive ability scores and records real-life conversations unobtrusively. This system may support the timely detection of early cognitive decline. In particular, the use of a privacy-sensitive passive monitoring technology would allow for the design of a program of interventions to enable strategies and treatments to decrease or avoid early cognitive decline.