Search

Speech-based automatic depression detection systems have been extensively explored over the past few years. Typically, each speaker is assigned a single label (Depressive or Non-depressive), and most approaches formulate depression detection as a speech classification task without explicitly considering the non-uniformly distributed depression pattern within segments, leading to low generalizability and robustness across different scenarios. However, depression corpora do not provide fine-grained labels (at the phoneme or word level) which makes the dynamic depression pattern in speech segments harder to track using conventional frameworks. To address this, we propose a novel framework, Speechformer-CTC, to model non-uniformly distributed depression characteristics within segments using a Connectionist Temporal Classification (CTC) objective function without the necessity of input-output alignment. Two novel CTC-label generation policies, namely the Expectation-One-Hot and the HuBERT policies, are proposed and incorporated in objectives on various granularities. Additionally, experiments using Automatic Speech Recognition (ASR) features are conducted to demonstrate the compatibility of the proposed method with content-based features. Our results show that the performance of depression detection, in terms of Macro F1-score, is improved on both DAIC-WOZ (English) and CONVERGE (Mandarin) datasets. On the DAIC-WOZ dataset, the system with HuBERT ASR features and a CTC objective optimized using HuBERT policy for label generation achieves 83.15% F1-score, which is close to state-of-the-art without the need for phoneme-level transcription or data augmentation. On the CONVERGE dataset, using Whisper features with the HuBERT policy improves the F1-score by 9.82% on CONVERGE1 (in-domain test set) and 18.47% on CONVERGE2 (out-of-domain test set). These findings show that depression detection can benefit from modeling non-uniformly distributed depression patterns and the proposed framework can be potentially used to determine significant depressive regions in speech utterances.

In order to create and foster learning spaces that build upon children's knowledge and experiences, we must respect and value their ways of knowing and being, including their play. Accordingly, this study highlights the ways that young children (re)imagined spaces, materials, and identities through their digital play in an analog (containing no physical, digital-based toys/materials) preschool classroom. This qualitative study utilized a framework of children's play as murmuration (a transmodal assemblage), to analyze and discuss the children's various digital play engagements. Three main themes were identified within/across these engagements, including the ways the children: (re)imagined the digital, drew from popular digital culture and media to make connections and construct meaning, and composed digital identities. Insights highlight the ways the children set aside perceived rules for materials, objects, spaces, and identities and created space for critically (re)envisioned ideas, concepts, realities, and futures to emerge. We encourage educators to continue to create and foster classroom spaces that value and build upon children's playful ways of knowing, being, and becoming in the digital world.

Teachers hold many beliefs, shaped by their educational knowledge, experiences, and cultural, social, historical, and political environments. These teacher beliefs, together with teacher characteristics and school context factors can influence cognitive processes, expectations, instructional decisions, and practices which could affect learning experiences, student engagement, and achievement. Numerous studies have explored these factors, however, often separately or with only one or two others. This paper explores primary school teachers' self-reported perceptions on the relationships between teacher beliefs (including teacher class level expectations, self-efficacy, motivation, goal orientation, work engagement, passion for teaching, relatedness to students), teacher characteristics (including gender, ethnicity, teacher experience), and school context factors (including decile and year level taught), and the impact of these on student achievement and teachers' instructional practices. Associations were found between teaching self-efficacy and all the other factors explored; work engagement and teachers' years of teaching experience, gender, and school decile; and years of teaching experience and student achievement. Further, relatedness to students, passion for teaching, and teaching self-efficacy was found to be associated with teachers' instructional practices.

Speech signals are valuable biomarkers for assessing an individuals mental health, including identifying Major Depressive Disorder (MDD) automatically. A frequently used approach in this regard is to employ features related to speaker identity, such as speaker-embeddings. However, over-reliance on speaker identity features in mental health screening systems can compromise patient privacy. Moreover, some aspects of speaker identity may not be relevant for depression detection and could serve as a bias factor that hampers system performance. To overcome these limitations, we propose disentangling speaker-identity information from depression-related information. Specifically, we present four distinct disentanglement methods to achieve this - adversarial speaker identification (SID)-loss maximization (ADV), SID-loss equalization with variance (LEV), SID-loss equalization using Cross-Entropy (LECE) and SID-loss equalization using KL divergence (LEKLD). Our experiments, which incorporated diverse input features and model architectures, have yielded improved F1 scores for MDD detection and voice-privacy attributes, as quantified by Gain in Voice Distinctiveness GV D and De-Identification Scores (DeID). On the DAIC-WOZ dataset (English), LECE using ComparE16 features results in the best F1-Scores of 80% which represents the audio-only SOTA depression detection F1-Score along with a GV D of -1.1 dB and a DeID of 85%. On the EATD dataset (Mandarin), ADV using raw-audio signal achieves an F1-Score of 72.38% surpassing multi-modal SOTA along with a GV D of -0.89 dB dB and a DeID of 51.21%. By reducing the dependence on speaker-identity-related features, our method offers a promising direction for speech-based depression detection that preserves patient privacy.

Knowing the genes involved in quantitative traits provides an entry point to understanding the biological bases of behavior, but there are very few examples where the pathway from genetic locus to behavioral change is known. To explore the role of specific genes in fear behavior, we mapped three fear-related traits, tested fourteen genes at six quantitative trait loci (QTLs) by quantitative complementation, and identified six genes. Four genes, Lamp, Ptprd, Nptx2, and Sh3gl, have known roles in synapse function; the fifth, Psip1, was not previously implicated in behavior; and the sixth is a long non-coding RNA, 4933413L06Rik, of unknown function. Variation in transcriptome and epigenetic modalities occurred preferentially in excitatory neurons, suggesting that genetic variation is more permissible in excitatory than inhibitory neuronal circuits. Our results relieve a bottleneck in using genetic mapping of QTLs to uncover biology underlying behavior and prompt a reconsideration of expected relationships between genetic and functional variation.

The genetic influence on human vocal pitch in tonal and non-tonal languages remains largely unknown. In tonal languages, such as Mandarin Chinese, pitch changes differentiate word meanings, whereas in non-tonal languages, such as Icelandic, pitch is used to convey intonation. We addressed this question by searching for genetic associations with interindividual variation in median pitch in a Chinese major depression case-control cohort and compared our results with a genome-wide association study from Iceland. The same genetic variant, rs11046212-T in an intron of the ABCC9 gene, was one of the most strongly associated loci with median pitch in both samples. Our meta-analysis revealed four genome-wide significant hits, including two novel associations. The discovery of genetic variants influencing vocal pitch across both tonal and non-tonal languages suggests the possibility of a common genetic contribution to the human vocal system shared in two distinct populations with languages that differ in tonality (Icelandic and Mandarin).

The COVID-19 pandemic and efforts to manage it have affected mental health around the world. Although early research on the COVID-19 pandemic showed a general decline in mental health after the pandemic began, mental health in later stages of the pandemic might be improving alongside other changes (e.g., availability of vaccines, return to in-person activities). The present study utilized data from a mental health service intervention for individuals at a southeastern university who were exposed to COVID-19 following the university's return to in-person operations. This study tested whether time period (August-September 2021 vs. January-February 2022) predicted individuals' likelihood of being mild or above in depression and anxiety ratings. Results showed that individuals were more likely to be mild or above in both depression and anxiety ratings during August-September of 2021 than January-February of 2022. Suggestions for future research and implications for professional counselors are discussed.

The proposed method focuses on speaker disentanglement in the context of depression detection from speech signals. Previous approaches require patient/speaker labels, encounter instability due to loss maximization, and introduce unnecessary parameters for adversarial domain prediction. In contrast, the proposed unsupervised approach reduces cosine similarity between latent spaces of depression and pre-trained speaker classification models. This method outperforms baseline models, matches or exceeds adversarial methods in performance, and does so without relying on speaker labels or introducing additional model parameters, leading to a reduction in model complexity. The higher the speaker de-identification score (DeID), the better the depression detection system is in masking a patients identity thereby enhancing the privacy attributes of depression detection systems. On the DAIC-WOZ dataset with ComparE16 features and an LSTM-only model, our method achieves an F1-Score of 0.776 and a DeID score of 92.87%, outperforming its adversarial counterpart which has an F1Score of 0.762 and 68.37% DeID, respectively. Furthermore, we demonstrate that speaker-disentanglement methods are complementary to text-based approaches, and a score-level fusion with a Word2vec-based depression detection model further enhances the overall performance to an F1-Score of 0.830.

One well-known prediction of linguistic relativity theories is the effect of a noun's grammatical gender on its semantics; for instance, ”key” is feminine in Spanish but masculine in German and thus might be associated with feminine traits for Spanish speakers but with masculine traits for German speakers. Experimental and corpus evidence for these effects has been mixed. In this work, we considered a distributional semantics account of putative grammatical gender effects on semantics and tested its predictions in Spanish, German, and English (control). In Part 1, we hypothesized that grammatical gender of concrete nouns affects the similarity of noun embeddings to embeddings of adjectives semantically associated with men or with women. We found support for this hypothesis in fastText embeddings, showing that nouns with the same meaning but with opposite genders in Spanish and German show opposite attraction effects both for words “man” and “woman” and for adjectives associated with men and women, although the effect size was weaker for German than for Spanish. BERT embeddings also showed consistent effects for Spanish but mixed results for German, suggesting possible variation across languages. In Part 2, we asked whether people systematically choose adjectives associated with women/men for grammatically feminine/masculine nouns, respectively. In a noun-adjective matching experiment (432 participants total), we found predicted grammatical gender effects for Spanish but not for German. Cosine similarity between the noun and the adjectives in fastText embeddings significantly predicted trial-level responses in all 3 languages; however, Spanish showed an additional effect of grammatical gender, indicating that participant noun-adjective associations are not fully explained by distributional semantics.

Over the last ten years, there has been considerable progress in using digital behavioral phenotypes, captured passively and continuously from smartphones and wearable devices, to infer depressive mood. However, most digital phenotype studies suffer from poor replicability, often fail to detect clinically relevant events, and use measures of depression that are not validated or suitable for collecting large and longitudinal data. Here, we report high-quality longitudinal validated assessments of depressive mood from computerized adaptive testing paired with continuous digital assessments of behavior from smartphone sensors for up to 40 weeks on 183 individuals experiencing mild to severe symptoms of depression. We apply a combination of cubic spline interpolation and idiographic models to generate individualized predictions of future mood from the digital behavioral phenotypes, achieving high prediction accuracy of depression severity up to three weeks in advance (R2 ≥ 80%) and a 65.7% reduction in the prediction error over a baseline model which predicts future mood based on past depression severity alone. Finally, our study verified the feasibility of obtaining high-quality longitudinal assessments of mood from a clinical population and predicting symptom severity weeks in advance using passively collected digital behavioral data. Our results indicate the possibility of expanding the repertoire of patient-specific behavioral measures to enable future psychiatric research.

Relating genetic variants to behavior remains a fundamental challenge. To assess the utility of DNA methylation marks in discovering causative variants, we examined their relationship to genetic variation by generating single-nucleus methylomes from the hippocampus of eight inbred mouse strains. At CpG sequence densities under 40 CpG/Kb, cells compensate for loss of methylated sites by methylating additional sites to maintain methylation levels. At higher CpG sequence densities, the exact location of a methylated site becomes more important, suggesting that variants affecting methylation will have a greater effect when occurring in higher CpG densities than in lower. We found this to be true for a variant's effect on transcript abundance, indicating that candidate variants can be prioritized based on CpG sequence density. Our findings imply that DNA methylation influences the likelihood that mutations occur at specific sites in the genome, supporting the view that the distribution of mutations is not random.

Biobanks that collect deep phenotypic and genomic data across many individuals have emerged as a key resource in human genetics. However, phenotypes in biobanks are often missing across many individuals, limiting their utility. We propose AutoComplete, a deep learning-based imputation method to impute or fill-in missing phenotypes in population-scale biobank datasets. When applied to collections of phenotypes measured across ~300,000 individuals from the UK Biobank, AutoComplete substantially improved imputation accuracy over existing methods. On three traits with notable amounts of missingness, we show that AutoComplete yields imputed phenotypes that are genetically similar to the originally observed phenotypes while increasing the effective sample size by about twofold on average. Further, genome-wide association analyses on the resulting imputed phenotypes led to a substantial increase in the number of associated loci. Our results demonstrate the utility of deep learning-based phenotype imputation to increase power for genetic discoveries in existing biobank datasets.

Biobanks often contain several phenotypes relevant to diseases such as major depressive disorder (MDD), with partly distinct genetic architectures. Researchers face complex tradeoffs between shallow (large sample size, low specificity/sensitivity) and deep (small sample size, high specificity/sensitivity) phenotypes, and the optimal choices are often unclear. Here we propose to integrate these phenotypes to combine the benefits of each. We use phenotype imputation to integrate information across hundreds of MDD-relevant phenotypes, which significantly increases genome-wide association study (GWAS) power and polygenic risk score (PRS) prediction accuracy of the deepest available MDD phenotype in UK Biobank, LifetimeMDD. We demonstrate that imputation preserves specificity in its genetic architecture using a novel PRS-based pleiotropy metric. We further find that integration via summary statistics also enhances GWAS power and PRS predictions, but can introduce nonspecific genetic effects depending on input. Our work provides a simple and scalable approach to improve genetic studies in large biobanks by integrating shallow and deep phenotypes.

Abstract Mild cognitive impairment (MCI) is a prodromal stage in aging to possible progression to Alzheimer’s disease and related dementia (ADRD), where co-occurrence of major depressive disorder (MDD) accelerates the progression. Metabolic and mitochondrial abnormalities in ADRD and other neurodegenerative disorders have been widely suggested, while possible mitochondrial dysfunction has been associated with etiopathology of both MCI and MDD. Hence, investigation of mitochondrial markers in MCI, MDD, and presence of both conditions is warranted. In total, 332 older adult participants were included: 168 with MCI, 108 with MCI plus remitted MDD (rMDD), and 56 with rMDD but without MCI. We measured plasma circulating mitochondrial DNA (ccf-mtDNA), lactate, and extracted nuclear mitochondrial encoded (NMt) single-nucleotide variants (SNVs) (n = 312). Non-parametric statistical tests on ccf-mtDNA and lactate levels were performed on the diagnosis, clinical and cardiometabolic variables. Binary sequence kernel association test (SKAT-O) and burden test were performed on NMt-SNV, adjusted for age, race, gender, type II diabetes, and APOE genotype. Lower level of lactate was observed in MCI (KW χ 2 = 14.8, P = 0.0024), more specifically, significant differences of lower plasma lactate between MCI only and rMDD, but not between MCI+rMDD and MCI were found, suggesting potential roles in MCI driving lactate lower levels. While higher levels of ccf-mtDNA were observed in APOE-ε4 carrier (χ 2 = 5.04, P = 0.05). This relationship was present only in MCI (P = 0.043) and MCI+rMDD groups (P = 0.023). No significant nuclear-encoded mitochondrial gene associations were observed with MCI or MDD. The results suggest decreased level of plasma lactate in individuals with MCI and MCI+rMDD, with inverse correlation with ccf-mtDNA, in addition to effect of APOE-ε4 in further increasing ccf-mtDNA specifically in participants with cognitive impairment. These findings contribute to a deeper understanding of the mitochondrial markers in MCI and MDD, warranting further research to explore the precise roles of mitochondrial abnormalities in the development and progression of MCI.

Abstract Historically, eloquent functions have been viewed as localized to focal areas of human cerebral cortex, while more recent studies suggest they are encoded by distributed networks. We examined the network properties of cortical sites defined by stimulation to be critical for speech and language, using electrocorticography from sixteen participants during word-reading. We discovered distinct network signatures for sites where stimulation caused speech arrest and language errors. Both demonstrated lower local and global connectivity, whereas sites causing language errors exhibited higher inter-community connectivity, identifying them as connectors between modules in the language network. We used machine learning to classify these site types with reasonably high accuracy, even across participants, suggesting that a site’s pattern of connections within the task-activated language network helps determine its importance to function. These findings help to bridge the gap in our understanding of how focal cortical stimulation interacts with complex brain networks to elicit language deficits.

Unearthing the effects of surface water and groundwater interactions on subsurface biogeochemical reactions is crucial for developing a more mechanistic understanding of carbon and energy flow in aquifer ecosystems. To examine physiological characteristics across groundwater microbial communities that experience varying degrees of interaction with surface waters, we investigated 10 springs and a river sink and rise system in north central Florida that discharge from and/or mix with the karstic upper Floridan aquifer (UFA). Groundwater with longer residence times in the aquifer had lower concentrations of dissolved oxygen, dissolved and particulate organic carbon, and microbial biomass, as well as the lowest rates of respiration (0.102 to 0.189 mgO2L-1d-1) and heterotrophic production (198 to 576 µgCL-1d-1). Despite these features, oligotrophic UFA groundwater (< 0.5 mg C L−1) contained bioavailable organic matter that supported doubling times (14 to 62 h) and cell-specific production rates (0.0485 to 0.261 pmol C per cell per hour) comparable to those observed for surface waters (17 to 20 h; 0.105 to 0.124 pmol C per cell per hour). The relatively high specific rates of dissimilatory and assimilatory metabolism indicate a subsurface source of labile carbon to the groundwater (e.g., secondary production and/or chemoautotrophy). Our results link variations in UFA hydrobiogeochemistry to the physiology of its groundwater communities, providing a basis to develop new hypotheses related to microbial carbon cycling, trophic hierarchy, and processes generating bioavailable organic matter in karstic aquifer ecosystems.

In this "Perspective on Practice," we describe an application of recommendations made in "Formative Assessment in Secondary ­Mathematics: Moving Theory to Recommendations for Evidence-Based Practice" (Kenney et al., 2022), which was recently published in this journal. The authors made recommendations for mathematics teacher educators about conducting professional development sessions related to formative assessment. After conducting our own workshop for K-5 teachers and considering the recommendations of Kenney and her colleagues, we share our observations about the benefits of a good opening task for jumpstarting a productive session on formative assessment.

This qualitative study foregrounded four teacher educators' perceptions of teaching collaboratively at shared school sites over the span of two years. As we reconvened to reflect on our experiences both individually and collectively, we retrospectively examined the affordances and challenges from this shared experience. Our data collection was guided by Pinar's method of "currere" which involves four "steps or moments that are temporal and reflective." These moments are "the regressive'' as past experiences are revisited; "the progressive" as the future was anticipated; "the analytic" to seek understanding of the past and future together; and finally, "the synthetical" to mobilize for action based upon these understandings. In considering the demands of university/school partnership work, methodologies such as currere, an autobiographical curriculum theory and method to support a context for reflection, is one that is rarely afforded due to the demands of higher education in general, and in field-based teacher education in particular. In analyzing these reflective interviews, we began to make sense of how these relationships shaped our perspectives of the past and led us to understand our present. Findings suggest that collaborative teaching created a third space that transformed our relationships with our teaching partners, enhanced our relationships with our students, and informed curricular revisions.

BACKGROUND: Dominance and other non-additive genetic effects arise from the interaction between alleles, and historically these phenomena play a major role in quantitative genetics. However, most genome-wide association studies (GWAS) assume alleles act additively. RESULTS: We systematically investigate both dominance-here representing any non-additive within-locus interaction-and additivity across 574 physiological and gene expression traits in three mammalian stocks: F2 intercross pigs, rat heterogeneous stock, and mice heterogeneous stock. Dominance accounts for about one quarter of heritable variance across all physiological traits in all species. Hematological and immunological traits exhibit the highest dominance variance, possibly reflecting balancing selection in response to pathogens. Although most quantitative trait loci (QTLs) are detectable as additive QTLs, we identify 154, 64, and 62 novel dominance QTLs in pigs, rats, and mice respectively that are undetectable as additive QTLs. Similarly, even though most cis-acting expression QTLs are additive, gene expression exhibits a large fraction of dominance variance, and trans-acting eQTLs are enriched for dominance. Genes causal for dominance physiological QTLs are less likely to be physically linked to their QTLs but instead act via trans-acting dominance eQTLs. In addition, thousands of eQTLs are associated with alternatively spliced isoforms with complex additive and dominant architectures in heterogeneous stock rats, suggesting a possible mechanism for dominance. CONCLUSIONS: Although heritability is predominantly additive, many mammalian genetic effects are dominant and likely arise through distinct mechanisms. It is therefore advantageous to consider both additive and dominance effects in GWAS to improve power and uncover causality.