Search for: All records

AI tools intend to transform mental healthcare by providing remote estimates of depression risk using behavioral data collected by sensors embedded in smartphones. While these tools accurately predict elevated depression symptoms in small, homogenous populations, recent studies show that these tools are less accurate in larger, more diverse populations. In this work, we show that accuracy is reduced because sensed-behaviors are unreliable predictors of depression across individuals: sensed-behaviors that predict depression risk are inconsistent across demographic and socioeconomic subgroups. We first identified subgroups where a developed AI tool underperformed by measuring algorithmic bias, where subgroups with depression were incorrectly predicted to be at lower risk than healthier subgroups. We then found inconsistencies between sensed-behaviors predictive of depression across these subgroups. Our findings suggest that researchers developing AI tools predicting mental health from sensed-behaviors should think critically about the generalizability of these tools, and consider tailored solutions for targeted populations.

 

Abstract Overly restrictive eligibility criteria for clinical trials may limit the generalizability of the trial results to their target real-world patient populations. We developed a novel machine learning approach using large collections of real-world data (RWD) to better inform clinical trial eligibility criteria design. We extracted patients’ clinical events from electronic health records (EHRs), which include demographics, diagnoses, and drugs, and assumed certain compositions of these clinical events within an individual’s EHRs can determine the subphenotypes—homogeneous clusters of patients, where patients within each subgroup share similar clinical characteristics. We introduced an outcome-guided probabilistic model to identify those subphenotypes, such that the patients within the same subgroup not only share similar clinical characteristics but also at similar risk levels of encountering severe adverse events (SAEs). We evaluated our algorithm on two previously conducted clinical trials with EHRs from the OneFlorida+ Clinical Research Consortium. Our model can clearly identify the patient subgroups who are more likely to suffer or not suffer from SAEs as subphenotypes in a transparent and interpretable way. Our approach identified a set of clinical topics and derived novel patient representations based on them. Each clinical topic represents a certain clinical event composition pattern learned from the patient EHRs. Tested on both trials, patient subgroup (#SAE=0) and patient subgroup (#SAE>0) can be well-separated by k-means clustering using the inferred topics. The inferred topics characterized as likely to align with the patient subgroup (#SAE>0) revealed meaningful combinations of clinical features and can provide data-driven recommendations for refining the exclusion criteria of clinical trials. The proposed supervised topic modeling approach can infer the clinical topics from the subphenotypes with or without SAEs. The potential rules for describing the patient subgroups with SAEs can be further derived to inform the design of clinical trial eligibility criteria. 

We synthesized single crystals for Mn2-xZnxSb (0 ≤ x ≤ 1) and studied their magnetic and electronic transport properties. This material system displays rich magnetic phase tunable with temperature and Zn composition. In addition, two groups of distinct magnetic and electronic properties, separated by a critical Zn composition of x = 0.6, are discovered. The Zn-less samples are metallic and characterized by a resistivity jump at the magnetic ordering temperature, while the Zn-rich samples lose metallicity and show a metal-to-insulator transition-like feature tunable by magnetic field. Our findings establish Mn2-xZnxSb as a promising material platform that offers opportunities to study how the coupling of spin, charge, and lattice degrees of freedom governs interesting transport properties in 2D magnets, which is currently a topic of broad interest. 

Abstract Magnetic and electronic properties of quantum materials heavily rely on the crystal structure even in the same chemical compositions. In this study, it is demonstrated that a layered tetragonal EuCd 2 Sb 2 structure can be obtained by treating bulk trigonal EuCd 2 Sb 2 under high pressure (6 GPa) and high temperature (600 °C). Magnetization measurements of the newly formed layered tetragonal EuCd 2 Sb 2 confirm an antiferromagnetic ordering with Neel temperature ( T N ) around 16 K, which is significantly higher than that ( T N ≈ 7 K) of trigonal EuCd 2 Sb 2 , consistent with heat capacity measurements. Moreover, bad metal behavior is observed in the temperature dependence of the electrical resistivity and the resistivity shows a dramatic increase around the Neel temperature. Electronic structure calculations with local density approximation dynamic mean–field theory (LDA+DMFT) show that this material is strongly correlated with well‐formed large magnetic moments, due to Hund's coupling, which is known to dramatically suppress the Kondo scale.