User-centred design for machine learning in health care: a case study from care management.

OBJECTIVES: Few machine learning (ML) models are successfully deployed in clinical practice. One of the common pitfalls across the field is inappropriate problem formulation: designing ML to fit the data rather than to address a real-world clinical pain point. METHODS: We introduce a practical toolkit for user-centred design consisting of four questions covering: (1) solvable pain points, (2) the unique value of ML (eg, automation and augmentation), (3) the actionability pathway and (4) the model's reward function. This toolkit was implemented in a series of six participatory design workshops with care managers in an academic medical centre. RESULTS: Pain points amenable to ML solutions included outpatient risk stratification and risk factor identification. The endpoint definitions, triggering frequency and evaluation metrics of the proposed risk scoring model were directly influenced by care manager workflows and real-world constraints. CONCLUSIONS: Integrating user-centred design early in the ML life cycle is key for configuring models in a clinically actionable way. This toolkit can guide problem selection and influence choices about the technical setup of the ML problem.

Finding the neural correlates of collaboration using a three-person fMRI hyperscanning paradigm.

Humans have an extraordinary ability to interact and cooperate with others. Despite the social and evolutionary significance of collaboration, research on finding its neural correlates has been limited partly due to restrictions on the simultaneous neuroimaging of more than one participant (also known as hyperscanning). Several studies have used dyadic fMRI hyperscanning to examine the interaction between two participants. However, to our knowledge, no study to date has aimed at revealing the neural correlates of social interactions using a three-person (or triadic) fMRI hyperscanning paradigm. Here, we simultaneously measured the blood-oxygenation level-dependent signal from 12 triads (n = 36 participants), while they engaged in a collaborative drawing task based on the social game of Pictionary General linear model analysis revealed increased activation in the brain regions previously linked with the theory of mind during the collaborative phase compared to the independent phase of the task. Furthermore, using intersubject correlation analysis, we revealed increased synchronization of the right temporo-parietal junction (R TPJ) during the collaborative phase. The increased synchrony in the R TPJ was observed to be positively associated with the overall team performance on the task. In sum, our paradigm revealed a vital role of the R TPJ among other theory-of-mind regions during a triadic collaborative drawing task.

Promoting Smoke-Free Homes Through Biomarker Feedback Documenting Child Exposure to Tobacco Toxins: Protocol for a Randomized Clinical Trial.

BACKGROUND: Exposure to secondhand smoke (SHS) early in life increases the risk of sudden infant death syndrome (SIDS), asthma, and respiratory illnesses. Since children's primary exposure to SHS occurs in the home, these most vulnerable members of our society are not fully protected by recent increases in the adoption of smoking bans in public spaces. Although exposure to SHS is a quickly reversible cause of excess morbidity, few low-income homes strictly enforce smoking restrictions. OBJECTIVE: This study aims to test a novel approach to motivate the adoption of home smoking restrictions and to eliminate child SHS exposure by providing parents with objective data documenting home SHS exposure and "biomarker feedback" of child ingestion of tobacco toxins, that is, objective, laboratory-based results of assays performed on child urine, documenting levels of nicotine; cotinine; and NNAL (4-[methylnitrosamino]-1-[3-pyridyl]-1-butanol), which is a metabolite of the known tobacco carcinogen NNK (4-[methylnitro-samino]-1-[3-pyridyl]-1-butanone). METHODS: From 2011 to 2013, 195 low-income, female smokers with children aged ≤10 years residing in their homes were recruited into a two-arm randomized clinical trial. Participants were assigned to one of two groups: biomarker feedback (n=98) and health education (n=97). In-home assessments were administered at baseline, week 16, and week 26. Children's home SHS exposure and nicotine, cotinine, and NNAL levels from urine samples, measured through a passive nicotine dosimeter and a surface sample of residual tobacco smoke (ie, thirdhand smoke), were collected at all three time points. Primary outcome was dosimeter-verified, self-reported complete home smoking restrictions at 6 months after randomization. Secondary outcomes included parental self-report of smoking behavior change and child urine tobacco toxin (biomarker) change. RESULTS: Data collection and analyses are complete, and the results are being interpreted. CONCLUSIONS: The study protocol describes the development of a novel community-based controlled trial designed to examine the efficacy of biomarker feedback documenting home and child exposure to SHS on parental smoking behavior change. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): RR1-10.2196/12654.

Creativity slumps and bumps: Examining the neurobehavioral basis of creativity development during middle childhood.

Developmental research has found that children's creative thinking ability tends to decline during middle childhood. However, this decline has not been consistently demonstrated, and the underlying neural and behavioral factors that affect fluctuations in children's creative thinking ability remain uncharacterized. Using a longitudinal cohort-sequential experimental design, we investigated the neurobehavioral basis of creative thinking ability during middle childhood in a sample of 48 children (n = 21 starting 3rd grade, n = 27 starting 4th grade) assessed longitudinally at three time-points across one year. For the first time, we used data-driven methods to reveal distinct trajectories in creative thinking ability during middle childhood. We found that although some children show a classic decline in creative ability, others exhibit a significant increase in creativity over time. These trajectories were not associated with differences in intelligence, age, or sex, but rather other developmentally-relevant constructs, including heightened externalizing behavior (i.e., rule-breaking and aggression). Using functional near-infrared spectroscopy (fNIRS) in a smaller cohort (n = 26), we examined longitudinal changes in bilateral frontal neural connectivity and found that increased right lateral frontal segregation or functional specialization tracked developmental improvements in creative thinking ability. Taken together, the findings reveal distinct profiles of change in creative thinking ability during middle childhood and identify behavioral and neural mechanisms potentially underlying changes in children's ability to think creatively.

Social contingencies and college quit and win contest: a qualitative inquiry.

OBJECTIVES: To investigate the social contingencies associated with participation in a college Quit and Win contest to promote smoking cessation. METHODS: Six focus groups (N = 27) were conducted with college students who participated in a Quit and Win research trial. RESULTS: Themes included: (1) participants reluctant to disclose quit decision; (2) perception of little support in their quit attempt, and (3) the social environment as a trigger for relapse. CONCLUSIONS: Although Quit and Win contests appear to motivate an initial quit attempt, the reluctance of smokers to disclose their quit attempt limits the potential positive impact of social support when utilizing this public service campaign.