Brain age of rhesus macaques over the lifespan.

Through the application of machine learning algorithms to neuroimaging data the brain age methodology was shown to provide a useful individual-level biological age prediction and identify key brain regions responsible for the prediction. In this study, we present the methodology of constructing a rhesus macaque brain age model using a machine learning algorithm and discuss the key predictive brain regions in comparison to the human brain, to shed light on cross-species primate similarities and differences. Structural information of the brain (e.g., parcellated volumes) from brain magnetic resonance imaging of 43 rhesus macaques were used to develop brain atlas-based features to build a brain age model that predicts biological age. The best-performing model used 22 selected features and achieved an R2 of 0.72. We also identified interpretable predictive brain features including Right Fronto-orbital Cortex, Right Frontal Pole, Right Inferior Lateral Parietal Cortex, and Bilateral Posterior Central Operculum. Our findings provide converging evidence of the parallel and comparable brain regions responsible for both non-human primates and human biological age prediction.

S100 protein family: Emerging role and mechanism in digestive tract cancer (Review).

Digestive tract cancer is one of the most common types of cancers globally, with ~4.8 million new cases and 3.4 million cancer­associated deaths in 2018, accounting for 26% of cancer incidence and 35% of cancer­related deaths worldwide. S100 protein family is involved in regulating cancer cell proliferation, angiogenesis, epithelial­mesenchymal transition (EMT), metastasis, metabolism and immune microenvironment homeostasis. The critical role of S100 protein family in digestive tract cancer involves complicated mechanisms, such as cancer stemness remodeling, anaerobic glycolysis regulation, tumor­associated macrophage differentiation and EMT. The present study systematically reviewed published studies on the compositions, function and the underlying molecular mechanisms of the S100 family, as well as guidance for diagnosis, treatment and prognosis of digestive tract cancer. Systematic review of the roles and underlying molecular mechanisms of S100 protein family may provide new insight into exploring potential cancer biomarkers and the optimized therapeutic strategies for digestive tract cancer.

Evaluating the effectiveness of a school-based mental health literacy intervention from a comprehensive demographic and social-cognitive perspective.

Childhood and adolescence are a critical period for the onset of mental and neurodevelopmental disorders and a time when many can be first identified. Research demonstrates that mental health literacy applied in school settings may be an effective approach to address these challenges. In contrast to many existing studies conducted in multicultural and multilingual settings that treated subjects' language as a demographic feature, the present study recognizes English proficiency as a social-cognitive factor and views the school-based mental health literacy (MHL) intervention as a learning process. The present study aimed to assess the effectiveness of school-based mental health literacy intervention and explore how ethnicity and English proficiency as a social-cognitive factor, as a modified, rather than a fixed variable, impacted the intervention outcomes. Grade 9 students (n = 240) from schools in West Canada with diverse social/cultural background received the intervention in the classroom delivered by trained teachers and completed the pre-test and post-test over a 6-month period. The intervention was effective in improving knowledge and help-seeking attitudes among all students. Non-Chinese and native English-speaking students performed the best on all outcomes. Gender demonstrated an association with changes in stigma, stress and wellbeing. English proficiency was linked to knowledge acquisition, while ethnicity was connected to changes of attitude-related outcomes. These findings deepened our understanding of how demographic and social-cognitive factors underlie changes in mental health literacy outcomes, which will facilitate the development of mental health literacy interventions for diverse student populations.

Effects of simulated microgravity on current generation of electrochemically active bacteria: Insights from case-control study using random positioning machine.

Electrochemically active bacteria (EAB) exhibit promising prospects for space exploration and life support systems. However, the effects of the space environment on EAB are unclear. In this study, the effects of simulated microgravity on the current generation of mixed-culture EAB were illustrated, and the underlying mechanism was elucidated. The results demonstrated that the electrochemical activity of mixed-culture EAB was enhanced, which was mainly due to the enrichment of Geobacter and the increase in EAB biomass. Additionally, the genes and proteins of the biofilm changed obviously under simulated microgravity conditions, including: I) genes related to signal transfer, II) genes related to cell wall synthesis, and III) genes related to riboflavin synthesis. This study first revealed the enrichment in EAB abundance, the increase in EAB biomass, and the promotion of current generation under simulated microgravity.

The altered volume of striatum: A neuroimaging marker of treatment in first-episode and drug-naïve schizophrenia.

Although schizophrenia patients exhibit structural abnormalities in the striatum, it remains largely unknown for the role of the striatum subregions in the treatment response of antipsychotic drugs. The purpose of this study was to investigate the associations between the striatal subregions and improved clinical symptoms in first-episode drug-naïve (FEDN) schizophrenia. Forty-two FEDN schizophrenia patients and 29 healthy controls (HCs) were recruited. At baseline, the Positive and Negative Syndrome Scale (PANSS) was used to assess the clinical symptoms of patients, MRI scanner was used to obtain anatomical images of patients and HCs. After 12-week stable doses of risperidone treatment, clinical symptoms were obtained in 38 patients and anatomical images in 26 patients. After 12 weeks of treatment, the left nucleus accumbens volume decreased, whereas the left pallidum volume increased in schizophrenia patients. The decreased left nucleus accumbens volume was positively correlated with cognitive factor improvement measured by PANSS. Intriguingly, greater left nucleus accumbens volume at baseline predicted greater cognitive improvements. Furthermore, the responders who had >50 % improvement in cognitive symptoms exhibited significantly greater baseline left nucleus accumbens volume compared to non-responders. The left striatum volume at baseline and after treatment predicted the cognitive improvements in FEDN schizophrenia, which could be a potential biomarker for the development of precision medicine approaches targeting cognitive function.

Integrated microcavity electric field sensors using Pound-Drever-Hall detection.

Discerning weak electric fields has important implications for cosmology, quantum technology, and identifying power system failures. Photonic integration of electric field sensors is highly desired for practical considerations and offers opportunities to improve performance by enhancing microwave and lightwave interactions. Here, we demonstrate a high-Q microcavity electric field sensor (MEFS) by leveraging the silicon chip-based thin film lithium niobate photonic integrated circuits. Using the Pound-Drever-Hall detection scheme, our MEFS achieves a detection sensitivity of 5.2 µV/(m[Formula: see text]), which surpasses previous lithium niobate electro-optical electric field sensors by nearly two orders of magnitude, and is comparable to atom-based quantum sensing approaches. Furthermore, our MEFS has a bandwidth that can be up to three orders of magnitude broader than quantum sensing approaches and measures fast electric field amplitude and phase variations in real-time. The ultra-sensitive MEFSs represent a significant step towards building electric field sensing networks and broaden the application spectrum of integrated microcavities.

[Pseudo-targeted metabolomics study of immune stress-mediated idiosyncratic liver injury induced by synergistic effects of bavachin and epimedin B].

Chinese patent medicine preparations containing Epimedii Folium and Psoraleae Fructus have been associated with the occurrence of idiosyncratic drug-induced liver injury(IDILI). However, the specific toxic biomarkers and mechanisms underlying these effects remain unclear. This study aimed to comprehensively assess the impact of bavachin and epimedin B, two principal consti-tuents found in Psoraleae Fructus and Epimedii Folium, on an IDILI model induced by tumor necrosis factor-α(TNF-α) treatment, both in vitro and in vivo. To evaluate the extent of liver injury, various parameters were assessed. Lactate dehydrogenase(LDH) release in the cell culture supernatant, as well as the levels of alanine aminotransferase(ALT) and aspartate transaminase(AST) in mouse plasma were measured. Additionally, histological analysis employing hematoxylin-eosin staining was performed to observe liver tissue changes indicative of the severity of liver injury. Furthermore, a pseudo-targeted metabolomics approach was employed, followed by multivariate analysis, to identify differential metabolites. These identified metabolites were subsequently subjected to Kyoto Encyclopedia of Genes and Genomes(KEGG) pathway enrichment analysis. The results showed that at the cellular level, after 2 hours of TNF-α stimulation, bavachin significantly increased the release of LDH in HepG2 cells compared to the normal group and the group treated alone; after the combination of bavachin and epimedin B, the release of LDH further significantly increased on the original basis. Similarly, although the individual or combination treatments of bavachin and epimedin B did not induce liver injury in normal mice, the combination of both drugs induced marked liver injury in TNF-α treated mice, leading to a significant elevation in plasma AST and ALT levels and substantial infiltration of inflammatory immune cells in the liver tissue. Pseudo-targeted metabolomics analysis identified seven common differential metabolites. Among these, D-glucosamine-6-phosphate, N1-methyl-2-pyridone-5-carboxamide, 17beta-nitro-5a-androstane, irisolidone-7-O-glucuronide, and N-(1-deoxy-1-fructosyl) valine emerged as potential biomarkers, with an area under the curve(AUC) exceeding 0.9. Furthermore, our results suggest that the metabolism of nicotinic acid and nicotinamide, as well as the linoleic acid metabolic pathway, may play pivotal roles in bavachin and epimedin B-induced IDILI. In conclusion, within an immune-stressed environment mediated by TNF-α, bavachin and epimedin B appear to induce IDILI through disruptions in metabolic processes.

Mid-long term boundary dynamic optimization of open-pit coal mine considering coal price fluctuation.

The delineation of the open-pit mining boundary, particularly in the context of medium to long-term planning, forms the foundation of mining design. However, due to the non-linear and dynamic nature of the economic and technical parameters influencing boundary delineation, determining the optimal mining boundary can be exceedingly challenging. Currently, most boundary optimization methods assume that block parameters remain fixed, which results in enterprises assuming a certain level of risk when facing changes in internal and external conditions. In this regard, this paper introduces the concept of "achievement degree" to reflect the risk associated with the results of boundary design. Using coal prices as an example, this article applies the predicted coal price curve to boundary optimization adjustments by specifying the "achievement degree" requirements for various time periods, thereby facilitating risk-controlled and economically optimal boundary decisions. Taking the illustrative case of an idealized small-scale inclined coal seam open-pit mine, adjustments to the boundary closely track variations in coal prices, further enhancing returns. The results demonstrate that the method proposed in this paper can increase overall revenue by approximately 51.15% within the forecast period, while effectively managing risks.

Identifying misdiagnosed bipolar disorder using support vector machine: feature selection based on fMRI of follow-up confirmed affective disorders.

Nearly a quarter of bipolar disorder (BD) patients were misdiagnosed as major depressive disorder (MDD) patients, which cannot be corrected until mania/hypomania develops. It is important to recognize these obstacles so that the appropriate treatment can be initiated. Thus, we sought to distinguish patients with BD from MDD, especially to identify misdiagnosed BD before mania/hypomania, and further explore potential trait features that allow accurate differential diagnosis independent of state matters. Functional magnetic resonance imaging scans were performed at baseline on 92 MDD patients and 48 BD patients. The MDD patients were then followed up for more than two years. After follow-up, 23 patients transformed into BD (tBD), and 69 patients whose diagnoses remained unchanged were eligible for unipolar depression (UD). A support vector machine classifier was trained on the amygdala-based functional connectivity (FC) of 48 BD and 50 UD patients using a novel region-based feature selection. Then, the classifier was tested on the dataset, encompassing tBD and the remaining UD. It performed well for known BD and UD and can also distinguish tBD from UD with an accuracy of 81%, sensitivity of 82.6%, specificity of 79%, and AUC of 74.6%, respectively. Feature selection results revealed that ten regions within the cortico-limbic neural circuit contributed most to classification. Furthermore, in the FC comparisons among diseases, BD and tBD shared almost overlapped FC patterns in the cortico-limbic neural circuit, and both of them presented pronounced differences in most regions within the circuit compared with UD. The FC values of the most discriminating brain regions had no prominent correlations with the severity of depression, anxiety, and mania/hypomania (FDR correction). It suggests that BD possesses some trait features in the cortico-limbic neural circuit, rendering it dichotomized by the classifier based on known-diagnosis data.

Protective role of pyrroloquinoline quinone against gentamicin induced cochlear hair cell ototoxicity.

Gentamicin (GM) is one of the commonly used antibiotics in the aminoglycoside class but is ototoxic, which constantly impacts the quality of human life. Pyrroloquinoline quinone (PQQ) as a redox cofactor produced by bacteria was found in soil and foods that exert an antioxidant and redox modulator. It is well documented that the PQQ can alleviate inflammatory responses and cytotoxicity. However, our understanding of PQQ in ototoxicity remains unclear. We reported that PQQ could protect against GM-induced ototoxicity in House Ear Institute-Organ of Corti 1 (HEI-OC1) cells in vitro. To evaluate reactive oxygen species (ROS) production and mitochondrial function, ROS and JC-1 staining, oxygen consumption rate (OCR), and extracellular acidification rate (ECAR) measurements in living cells, mitochondrial dynamics analysis was performed. GM-mediated damage was performed by reducing the production of ROS and inhibiting mitochondria biogenesis and dynamics. PQQ ameliorated the cellular oxidative stress and recovered mitochondrial membrane potential, facilitating the recovery of mitochondrial biogenesis and dynamics. Our in vitro findings improve our understanding of the GM-induced ototoxicity with therapeutic implications for PQQ.

Mechanisms and efficacy of traditional Chinese herb monomers in diabetic kidney disease.

Diabetic kidney disease (DKD) is a serious complication of diabetes and is the primary cause of end-stage renal disease. Current treatment strategies primarily focus on the inhibition of the renin-angiotensin-aldosterone system and the attainment of blood glucose control. Although current medical therapies for DKD have been shown to delay disease progression and improve long-term outcomes, their efficacy is limited and they may be restricted in certain cases, particularly when hyperkalemia is present. Traditional Chinese medicine (TCM) treatment has emerged as a significant complementary approach for DKD. TCM monomers, derived from various Chinese herbs, have been found to modulate multiple therapeutic targets and exhibit a broad range of therapeutic effects in patients with DKD. This review aims to summarize the mechanisms of action of TCM monomers in the treatment of DKD, based on findings from clinical trials, as well as cell and animal studies. The results of these investigations demonstrate the potential effective use of TCM monomers in treating or preventing DKD, offering a promising new direction for future research in the field. By providing a comprehensive overview of the mechanisms and efficacy of TCM monomers in DKD, this review highlights the potential of these natural compounds as alternative therapeutic options for improving outcomes in patients with DKD.

Total versus proximal gastrectomy for proximal gastric cancer after neoadjuvant chemotherapy: a multicenter retrospective propensity score-matched cohort study.

BACKGROUND: This study aimed to analyze and compare the short-term and long-term outcomes of proximal gastrectomy (PG) and total gastrectomy (TG) in patients with locally advanced proximal gastric cancer (GC) following neoadjuvant chemotherapy (NACT). METHOD: A multicenter retrospective cohort study and propensity score matching (PSM) were employed. The authors examined 367 patients with proximal GC who received NACT followed by PG ( n =164) or TG ( n =203) at two Chinese medical institutions between December 2009 and December 2022. Clinical and pathological parameters, postoperative complications, and 5-year overall survival (OS) and recurrence-free survival (RFS) were compared between the two groups. The dissection status and metastasis rate of each lymph node station were assessed. RESULTS: After PSM, 80 patients were enrolled in both TG and PG group, and baseline characteristics were comparable between the groups (all P >0.05). The TG group had a higher total number of lymph nodes retrieved ( P <0.001) and longer operative time ( P =0.007) compared to the PG group. The incidence of Clavien-Dindo grade II or higher postoperative complications was similar between the TG group (21.3%, 17/80) and the PG group (17.5%, 14/80) ( P =0.689). The 5-year OS rates were 68.4 for the PG group and 66.0% for the TG group ( P =0.881), while the 5-year RFS rates were 64.8 and 61.9%, respectively ( P =0.571), with no statistically significant differences. Metastasis rates at lymph node stations #4d, #5, #6, and #12a were notably low in the TG group, with values of 2.74, 0.67, 1.33, and 1.74%, respectively. CONCLUSION: For proximal GC patients following NACT, PG maintains comparable curative potential and oncological efficacy to TG, making it a safe option.

Collectin 11 has a pivotal role in host defense against kidney and bladder infection in mice.

The urinary tract is constantly exposed to microorganisms. Host defense mechanisms in protection from microbial colonization and development of urinary tract infections require better understanding to control kidney infection. Here we report that the lectin collectin 11 (CL-11), particularly kidney produced, has a pivotal role in host defense against uropathogen infection. CL-11 was found in mouse urine under normal and pathological conditions. Mice with global gene ablation of Colec11 had increased susceptibility to and severity of kidney and to an extent, bladder infection. Mice with kidney-specific Colec11 ablation exhibited a similar disease phenotype to that observed in global Colec11 deficient mice, indicating the importance of kidney produced CL-11 for protection against kidney and bladder infection. Conversely, intravesical or systemic administration of recombinant CL-11 reduced susceptibility to and severity of kidney and bladder infection. Mechanism analysis revealed that CL-11 can mediate several key innate defense mechanisms (agglutination, anti- adhesion, opsonophagocytosis), and limit local inflammatory responses to pathogens. Furthermore, CL-11-mediated innate defense mechanisms can act on clinically relevant microorganisms including multiple antibiotic resistant strains. CL-11 was detectable in eight of 24 urine samples from patients with urinary tract infections but not detectable in urine samples from ten healthy individuals. Thus, our findings demonstrate that CL-11 is a key factor of host defense mechanisms in kidney and bladder infection with therapeutic potential for human application.

A statistical method for image-mediated association studies discovers genes and pathways associated with four brain disorders.

Brain imaging and genomics are critical tools enabling characterization of the genetic basis of brain disorders. However, imaging large cohorts is expensive and may be unavailable for legacy datasets used for genome-wide association studies (GWASs). Using an integrated feature selection/aggregation model, we developed an image-mediated association study (IMAS), which utilizes borrowed imaging/genomics data to conduct association mapping in legacy GWAS cohorts. By leveraging the UK Biobank image-derived phenotypes (IDPs), the IMAS discovered genetic bases underlying four neuropsychiatric disorders and verified them by analyzing annotations, pathways, and expression quantitative trait loci (eQTLs). A cerebellar-mediated mechanism was identified to be common to the four disorders. Simulations show that, if the goal is identifying genetic risk, our IMAS is more powerful than a hypothetical protocol in which the imaging results were available in the GWAS dataset. This implies the feasibility of reanalyzing legacy GWAS datasets without conducting additional imaging, yielding cost savings for integrated analysis of genetics and imaging.

Research on boundary optimization of adjacent mining areas in open pit coal mine based on calculation of sectional stripping ratio.

To address the problem of excessive local secondary stripping between adjacent mining areas in open pit mines caused by internal row raising, a multivariate function was fitted to the model of the main mining seam of Zhundong open pit coal mine in Xinjiang, and the different locations of the end gang of the second mining area were divided into multiple sections at certain step sizes and calculated by integration, resulting in stripping ratios for each section, which were fitted to a stripping ratio curve. The optimal location of the mining area boundary was found to be 55 m westward offset from the mining area boundary in the inner row of the raised section, and numerical simulations based on the strength reduction method were applied to analyse the slope stability of the end gang at this location. The results of the study show that the analysed slope meets the stability requirements and the optimised new boundary avoids the stripping of approximately 65,837,376 m3 of economically unreasonable section.

Downregulating lncRNA MIAT attenuates apoptosis of podocytes exposed to high glucose.

AIMS: Diabetic nephropathy (DN), a destructive complication of diabetes mellitus (DM), is one of the leading causes of end-stage renal disease (ESRD). This study aimed to investigate the role of long non-coding RNA (lncRNA) MIAT in high-glucose (HG)-induced podocyte injury associated with DN. METHODS: Three human kidney podocyte (HKP) cultures were treated with HG to mimic DN. Expression of lncRNA MIAT, podocyte-specific and injury-related proteins, and apoptosis were assessed before and after MIAT knockdown using MIAT shRNAs. RESULTS: MIAT expression was upregulated in HKPs in response to glucose stress. HG treatment resulted in a significant increase in the apoptotic rate, Bax level, and levels of injury-related proteins desmin, fibroblast-specific protein 1 (FSP-1), and smooth muscle α-actin (α-SMA), and a significant reduction in Bcl-2 levels and the levels of podocyte-specific proteins synaptopodin and podocin. Transfection of HKPs with shRNAs significantly reduced MIAT levels (p < 0.05) and attenuated apoptosis in HG-medium. Correspondingly, the levels of synaptopodin and podocin were upregulated, and desmin, FSP-1, and α-SMA were reduced (p < 0.05). Western blot analysis also showed that anti-apoptotic active caspase-3 and Bax and proapoptotic Bcl-2 were elevated and decreased, respectively, after MIAT knockdown, suggesting that apoptosis pathways are deactivated after MIAT downregulation. CONCLUSIONS: High glucose upregulates MIAT level in HKPs and induces cellular injury. Knockdown of MIAT alleviates the injury likely via deactivating apoptosis pathways.

Enhancing surgical precision: unveiling the impact of preoperative colonoscopy in anal fistula patients.

BACKGROUND: Anal fistula is a common benign anorectal disease that often requires surgical intervention for effective treatment. In recent years, preoperative colonoscopy as a diagnostic tool in patients with anal fistula has garnered increasing attention due to its potential clinical application value. By investigating underlying inflammatory bowel disease (IBD), polyps, and other abnormalities, preoperative colonoscopy can offer insights to refine surgical strategies and improve patient outcomes. METHODS: This retrospective study focused on 1796 patients with various benign anorectal diseases who underwent preoperative intestinal endoscopy and met surgical criteria within the preceding three years at the First Affiliated Hospital of Guizhou University of Traditional Chinese Medicine. Among these patients, 949 diagnosed with anal fistula comprised group A, while 847 patients without anal fistula were assigned to group B for comparison. The investigation encompassed an analysis of general patient information, endoscopic findings, polyp histopathology, distribution of bowel inflammation sites, and results of inflammatory bowel disease assessments between the two patient cohorts. A subgroup analysis was also conducted on 2275 anal fistula patients with no surgical contraindications. This subgroup was categorized into Group A (949 patients who underwent preoperative intestinal endoscopy) and Group C (1326 patients who did not undergo preoperative colonoscopy). The study compared the rates of detecting endoscopic lesions and IBD-related findings between the two subgroups. RESULTS: The study initially confirmed the comparability of general patient information between groups A and B. Notably, the abnormal detection rate in group A was significantly higher than in group B (P < 0.01). In terms of endoscopic findings, the anal fistula group (group A) exhibited higher rates of detecting bowel inflammation, inflammatory bowel disease, and polyps compared to the non-anal fistula group (group B) (P < 0.05). The distribution of inflammation locations indicated higher detection rates in the terminal ileum, ileocecal region, and ascending colon for group A compared to group B (P < 0.05). Although the incidence of IBD in group A was higher than in group B, this difference did not reach statistical significance (P > 0.05). Subsequently, the analysis of the subgroup (groups A and C) revealed a significant disparity in intestinal endoscopic detection rates (P < 0.01) and statistically significant differences in detecting IBD (P < 0.05) and Crohn's disease (P < 0.05) between the two anal fistula subgroups. CONCLUSIONS: The findings of this study underscore the substantial clinical value of preoperative colonoscopy in the comprehensive evaluation of patients with anal fistula. Preoperative colonoscopy aids in ruling out localized perianal lesions caused by underlying inflammatory bowel disease, thereby mitigating the likelihood of missed diagnoses and enhancing treatment outcomes. This research highlights the importance of incorporating preoperative colonoscopy as a valuable diagnostic tool in managing anal fistula patients.

Risk factors for developmental vulnerability: Insight from population-level surveillance using the Early Development Instrument.

Objectives: Population-level studies may elucidate the most promising intervention targets to prevent negative outcomes of developmental vulnerability in children. This study aims to bridge the current literature gap on identifying population-level developmental vulnerability risk factors using combined social and biological/health information. Methods: This study assessed developmental vulnerability among kindergarten children using the 2016 Early Development Instrument (EDI) and identified risk factors of developmental vulnerability using EDI data cross-linked to a population-wide administrative health dataset. A total number of 23,494 children aged 5-6 were included (48% female). Prenatal, neonatal, and early childhood risk factors for developmental vulnerability were investigated, highlighting the most important ones contributing to early development. Results: The main risk factors for developmental vulnerability were children with a history of mental health diagnosis (risk ratio = 1.46), biological sex-male (risk ratio = 1.51), and poor socioeconomic status (risk ratio = 1.58). Conclusion: Our study encompasses both social and health information in a populational-level representative sample of Alberta, Canada. The results confirm evidence established in other geographic regions and jurisdictions and demonstrate the association between perinatal risk factors and developmental vulnerability. Based on these results, we argue that the health system should adopt a multilevel prevention and intervention strategy, targeting individual, family, and community together.

Using Wearable Devices and Speech Data for Personalized Machine Learning in Early Detection of Mental Disorders: Protocol for a Participatory Research Study.

BACKGROUND: Early identification of mental disorder symptoms is crucial for timely treatment and reduction of recurring symptoms and disabilities. A tool to help individuals recognize warning signs is important. We posit that such a tool would have to rely on longitudinal analysis of patterns and trends in the individual's daily activities and mood, which can now be captured through data from wearable activity trackers, speech recordings from mobile devices, and the individual's own description of their mental state. In this paper, we describe such a tool developed by our team to detect early signs of depression, anxiety, and stress. OBJECTIVE: This study aims to examine three questions about the effectiveness of machine learning models constructed based on multimodal data from wearables, speech, and self-reports: (1) How does speech about issues of personal context differ from speech while reading a neutral text, what type of speech data are more helpful in detecting mental health indicators, and how is the quality of the machine learning models influenced by multilanguage data? (2) Does accuracy improve with longitudinal data collection and how, and what are the most important features? and (3) How do personalized machine learning models compare against population-level models? METHODS: We collect longitudinal data to aid machine learning in accurately identifying patterns of mental disorder symptoms. We developed an app that collects voice, physiological, and activity data. Physiological and activity data are provided by a variety of off-the-shelf fitness trackers, that record steps, active minutes, duration of sleeping stages (rapid eye movement, deep, and light sleep), calories consumed, distance walked, heart rate, and speed. We also collect voice recordings of users reading specific texts and answering open-ended questions chosen randomly from a set of questions without repetition. Finally, the app collects users' answers to the Depression, Anxiety, and Stress Scale. The collected data from wearable devices and voice recordings will be used to train machine learning models to predict the levels of anxiety, stress, and depression in participants. RESULTS: The study is ongoing, and data collection will be completed by November 2023. We expect to recruit at least 50 participants attending 2 major universities (in Canada and Mexico) fluent in English or Spanish. The study will include participants aged between 18 and 35 years, with no communication disorders, acute neurological diseases, or history of brain damage. Data collection complied with ethical and privacy requirements. CONCLUSIONS: The study aims to advance personalized machine learning for mental health; generate a data set to predict Depression, Anxiety, and Stress Scale results; and deploy a framework for early detection of depression, anxiety, and stress. Our long-term goal is to develop a noninvasive and objective method for collecting mental health data and promptly detecting mental disorder symptoms. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/48210.