Background

Smartphones offer the hope that depression can be detected using passively collected data from the phone sensors. The aim of this study was to replicate and extend previous work using geographic location (GPS) sensors to identify depressive symptom severity.

Methods

We used a dataset collected from 48 college students over a 10-week period, which included GPS phone sensor data and the Patient Health Questionnaire 9-item (PHQ-9) to evaluate depressive symptom severity at baseline and end-of-study. GPS features were calculated over the entire study, for weekdays and weekends, and in 2-week blocks.

Results

The results of this study replicated our previous findings that a number of GPS features, including location variance, entropy, and circadian movement, were significantly correlated with PHQ-9 scores (r's ranging from -0.43 to -0.46, p-values <  .05). We also found that these relationships were stronger when GPS features were calculated from weekend, compared to weekday, data. Although the correlation between baseline PHQ-9 scores with 2-week GPS features diminished as we moved further from baseline, correlations with the end-of-study scores remained significant regardless of the time point used to calculate the features.

Discussion

Our findings were consistent with past research demonstrating that GPS features may be an important and reliable predictor of depressive symptom severity. The varying strength of these relationships on weekends and weekdays suggests the role of weekend/weekday as a moderating variable. The finding that GPS features predict depressive symptom severity up to 10 weeks prior to assessment suggests that GPS features may have the potential as early warning signals of depression.

Given the extraordinary ability of humans and animals to recognize communication signals over a background of noise, describing noise invariant neural responses is critical not only to pinpoint the brain regions that are mediating our robust perceptions but also to understand the neural computations that are performing these tasks and the underlying circuitry. Although invariant neural responses, such as rotation-invariant face cells, are well described in the visual system, high-level auditory neurons that can represent the same behaviorally relevant signal in a range of listening conditions have yet to be discovered. Here we found neurons in a secondary area of the avian auditory cortex that exhibit noise-invariant responses in the sense that they responded with similar spike patterns to song stimuli presented in silence and over a background of naturalistic noise. By characterizing the neurons' tuning in terms of their responses to modulations in the temporal and spectral envelope of the sound, we then show that noise invariance is partly achieved by selectively responding to long sounds with sharp spectral structure. Finally, to demonstrate that such computations could explain noise invariance, we designed a biologically inspired noise-filtering algorithm that can be used to separate song or speech from noise. This novel noise-filtering method performs as well as other state-of-the-art de-noising algorithms and could be used in clinical or consumer oriented applications. Our biologically inspired model also shows how high-level noise-invariant responses could be created from neural responses typically found in primary auditory cortex.

Perceptual events derive their significance to an animal from their meaning about the world, that is from the information they carry about their causes. The brain should thus be able to efficiently infer the causes underlying our sensory events. Here we use multisensory cue combination to study causal inference in perception. We formulate an ideal-observer model that infers whether two sensory cues originate from the same location and that also estimates their location(s). This model accurately predicts the nonlinear integration of cues by human subjects in two auditory-visual localization tasks. The results show that indeed humans can efficiently infer the causal structure as well as the location of causes. By combining insights from the study of causal inference with the ideal-observer approach to sensory cue combination, we show that the capacity to infer causal structure is not limited to conscious, high-level cognition; it is also performed continually and effortlessly in perception.

Randomized Controlled Trials (RCTs) are considered the gold standard for measuring the efficacy of medical interventions. However, RCTs are expensive, and use a limited population. Techniques to estimate the effects of stroke interventions from observational data that minimize confounding would be useful. We used regression discontinuity design (RDD), a technique well-established in economics, on the Get With The Guidelines-Stroke (GWTG-Stroke) data set. RDD, based on regression, measures the occurrence of a discontinuity in an outcome (e.g., odds of home discharge) as a function of an intervention (e.g., alteplase) that becomes significantly more likely when crossing the threshold of a continuous variable that determines that intervention (e.g., time from symptom onset, since alteplase is only given if symptom onset is less than e.g., 3 h). The technique assumes that patients near either side of a threshold (e.g., 2.99 and 3.01 h from symptom onset) are indistinguishable other than the use of the treatment. We compared outcomes of patients whose estimated onset to treatment time fell on either side of the treatment threshold for three cohorts of patients in the GWTG-Stroke data set. This data set spanned three different treatment thresholds for alteplase (3 h, 2003-2007, N = 1,869; 3 h, 2009-2016, N = 13,086, and 4.5 h, 2009-2016, N = 6,550). Patient demographic characteristics were overall similar across the treatment thresholds. We did not find evidence of a discontinuity in clinical outcome at any treatment threshold attributable to alteplase. Potential reasons for failing to find an effect include violation of some RDD assumptions in clinical care, large sample sizes required, or already-well-chosen treatment threshold.

Climate change is one of the greatest challenges facing humanity, and we, as machine learning (ML) experts, may wonder how we can help. Here we describe how ML can be a powerful tool in reducing greenhouse gas emissions and helping society adapt to a changing climate. From smart grids to disaster management, we identify high impact problems where existing gaps can be filled by ML, in collaboration with other fields. Our recommendations encompass exciting research questions as well as promising business opportunities. We call on the ML community to join the global effort against climate change.