Predicting first time depression onset in pregnancy: applying machine learning methods to patient-reported data.

PURPOSE: To develop a machine learning algorithm, using patient-reported data from early pregnancy, to predict later onset of first time moderate-to-severe depression. METHODS: A sample of 944 U.S. patient participants from a larger longitudinal observational cohortused a prenatal support mobile app from September 2019 to April 2022. Participants self-reported clinical and social risk factors during first trimester initiation of app use and completed voluntary depression screenings in each trimester. Several machine learning algorithms were applied to self-reported data, including a novel algorithm for causal discovery. Training and test datasets were built from a randomized 80/20 data split. Models were evaluated on their predictive accuracy and their simplicity (i.e., fewest variables required for prediction). RESULTS: Among participants, 78% identified as white with an average age of 30 [IQR 26-34]; 61% had income ≥ $50,000; 70% had a college degree or higher; and 49% were nulliparous. All models accurately predicted first time moderate-severe depression using first trimester baseline data (AUC 0.74-0.89, sensitivity 0.35-0.81, specificity 0.78-0.95). Several predictors were common across models, including anxiety history, partnered status, psychosocial factors, and pregnancy-specific stressors. The optimal model used only 14 (26%) of the possible variables and had excellent accuracy (AUC = 0.89, sensitivity = 0.81, specificity = 0.83). When food insecurity reports were included among a subset of participants, demographics, including race and income, dropped out and the model became more accurate (AUC = 0.93) and simpler (9 variables). CONCLUSION: A relatively small amount of self-report data produced a highly predictive model of first time depression among pregnant individuals.

Automated patterns of head dynamics are associated with psychopathic traits in incarcerated women.

Men with elevated psychopathic traits have been characterized by unique patterns of nonverbal communication, including more fixed and focused head positions during clinical interviews, compared to men scoring low on measures of psychopathy. However, it is unclear whether similar patterns of head dynamics help characterize women scoring high on psychopathic traits. Here, we utilized an automated detection algorithm to assess head position and dynamics during a videotaped clinical interview (i.e., the Psychopathy Checklist - Revised [PCL-R]) in a sample of n = 213 incarcerated women. PCL-R Total, Factor 1 (i.e., interpersonal and affective psychopathic traits), and Factor 2 (i.e., lifestyle/behavioral and antisocial/developmental psychopathic traits) scores were associated with a pattern of head dynamics indicative of a rigid head position. The current study extends analyses of nonverbal behavior studies in men to women and highlights how individuals with elevated psychopathic traits demonstrate unique nonverbal behaviors relative to individuals who score low on psychopathic traits. The implications and clinical value of these findings are discussed.

Digital phenotyping of depression during pregnancy using self-report data.

BACKGROUND: Depression is a common pregnancy complication yet is often under-detected and, subsequently, undertreated. Data collected through mobile health tools may be used to support the identification of depression symptoms in pregnancy. METHODS: An observational cohort study of 2062 pregnancies collected self-reports of patient history, mood, pregnancy-specific symptoms, and written language using a prenatal support app. These app inputs were used to model depression risk in subsequent 30- and 60-day periods throughout pregnancy. A selective inference lasso modeling approach examined the individual and additive value of each type of patient-reported app input. RESULTS: Depression models ranged in predictive power (AUC value of 0.64-0.83), depending on the type of inputs. The most predictive model included personal history, daily mood, and acute pregnancy-related symptoms (e.g., severe vomiting, cramping). Across models, daily mood was the strongest indicator of depression symptoms in the following month. Models that retained natural language inputs typically improved predictive accuracy and offered insight into the lived context associated with experiencing depression. LIMITATIONS: Our findings are not generalizable beyond a digitally literate patient population that is self-motivated to report data during pregnancy. CONCLUSIONS: Simple patient reported data, including sparse language, shared directly via digital tools may support earlier depression symptom identification and a more nuanced understanding of depression context.

Adolescents with Elevated Psychopathic Traits are Associated with an Increased Risk for Premature Mortality.

The mortality rate among adolescents has been steadily increasing in recent years. Researchers have previously identified forms of externalizing psychopathology measured during adolescence associated with an increased risk for premature mortality, including attention-deficit/hyperactivity disorder (ADHD), substance use disorders (SUDs), oppositional defiant disorder (ODD), and conduct disorder (CD). The current study investigated whether additional personality traits (i.e., adolescent psychopathic traits, assessed via the Hare Psychopathy Checklist: Youth Version [PCL:YV]) were also associated with premature mortality risk among maximum-security incarcerated adolescents (N = 332). During a follow-up period ranging from 10 to 14 years, premature mortality was observed in n = 33 participants (9.94%), a mortality rate nearly ten times higher than population norms. We observed that adolescents scoring the highest on PCL:YV total scores exhibited significantly higher rates of premature mortality compared to adolescents scoring lower on PCL:YV total scores via Fisher's exact tests. Additionally, through univariate Cox proportional hazard regression analyses, PCL:YV total, Factor 2 (measuring lifestyle/behavioral and antisocial/developmental psychopathic traits), Facet 1 (measuring interpersonal psychopathic traits), and Facet 3 (measuring lifestyle/behavioral psychopathic traits) scores were associated with faster time to premature mortality. In supplemental analyses performed, we observed that adolescents meeting criteria for externalizing psychopathology (i.e., ADHD, SUDs, ODD, and CD) did not exhibit higher rates of premature mortality compared to control participants. The current study therefore identifies additional maladaptive personality traits to consider in relation to premature mortality risk (i.e., psychopathic traits) among a high-risk sample of incarcerated adolescents.

Psychopathy Scores Predict Recidivism in High-risk Youth: A Five-year Follow-up Study.

Psychopathic traits have been associated with rearrest in adolescents involved in the criminal legal system. Much of the prior work has focused on White samples, short follow-up windows, and relatively low-risk youth. The current study aimed to evaluate the utility of the Hare Psychopathy Checklist: Youth Version (PCL:YV) for predicting general and violent felony recidivism in a large sample of high-risk, predominantly Hispanic/Latino, male adolescents (n = 254) with a five-year follow-up period. Results indicated higher PCL:YV scores and lower full-scale estimated IQ scores were significantly associated with a shorter time to felony and violent felony rearrest. These effects generalized to Hispanic/Latino adolescents (n = 193)-a group that faces disproportionate risk of being detained or committed to juvenile correctional facilities in the U.S. These results suggest that expert-rated measures of psychopathic traits and IQ are reliable predictors of subsequent felony and violent felony rearrest among high-risk male adolescents.

Using natural language from a smartphone pregnancy app to identify maternal depression.

Depression is highly prevalent in pregnancy, yet it often goes undiagnosed and untreated. Language can be an indicator of psychological well-being. This longitudinal, observational cohort study of 1,274 pregnancies examined written language shared in a prenatal smartphone app. Natural language feature of text entered in the app (e.g. in a journaling feature) throughout the course of participants' pregnancies were used to model subsequent depression symptoms. Language features were predictive of incident depression symptoms in a 30-day window (AUROC = 0.72) and offer insights into topics most salient in the writing of individuals experiencing those symptoms. When natural language inputs were combined with self-reported current mood, a stronger predictive model was produced (AUROC = 0.84). Pregnancy apps are a promising way to illuminate experiences contributing to depression symptoms. Even sparse language and simple patient-reports collected directly from these tools may support earlier, more nuanced depression symptom identification.

A multidimensional examination of psychopathy traits and gray matter volume in adults.

Uncovering the neurobiological abnormalities that may contribute to the manifestation of psychopathic traits is an important step toward understanding the etiology of this disorder. Although many studies have examined gray matter volume (GMV) in relation to psychopathy, few have examined how dimensions of psychopathic traits interactively relate to GMV, an approach that holds promise for parsing heterogeneity in neurobiological risk factors for this disorder. The aim of this study was to investigate the affective-interpersonal (Factor 1) and impulsive-antisocial (Factor 2) dimensions of psychopathy in relation to cortical surface and subcortical GMV in a mixed-gender, high-risk community sample with significant justice-system involvement (N = 156, 50.0% men). Cortex-wide analysis indicated that (i) the Factor 1 traits correlated negatively with GMV in two cortical clusters, one in the right rostral middle frontal region and one in the occipital lobe, and (ii) the interaction of the affective-interpersonal and impulsive-antisocial traits was negatively associated with GMV bilaterally in the parietal lobe, such that individuals high on both trait dimensions evidenced reduced GMV relative to individuals high on only one psychopathy factor. An interactive effect also emerged for bilateral amygdalar and hippocampal GMV, such that Factor 1 psychopathic traits were significantly negatively associated with GMV only at high (but not low) levels of Factor 2 traits. Results extend prior research by demonstrating the neurobiological correlates of psychopathy differ based on the presentation of Factor 1 and 2 traits.

Identification of maternal depression risk from natural language collected in a mobile health app.

Depression is one of the most common pregnancy complications, affecting approximately 15% of pregnant people. While valid psychometric measures of depression risk exist, they are not consistently administered at routine prenatal care, exacerbating the problem of adequate detection. The language we use in daily life offers a window into our psychological wellbeing. In this longitudinal observational cohort study of prenatal patients using a prenatal care mobile health app, we examine how features of app-entered natural language and other app-entered patient-reported data may be used as indicators for validated depression risk measures. Patient participants (n=1091) were prescribed a prenatal care app as part of a quality improvement initiative in the UPMC healthcare system from September 2019 - May 2022. Natural language from open-ended writing prompts in the app and self-reported daily mood, were entered by patients using the tool. Participants also completed a validated measure of depression risk - the Edinburgh Postnatal Depression Scale (EPDS) - at least once in their pregnancy. A variety of natural language processing tools were used to score sentiment, categorize topics, and capture other semantic and syntactic information from text entries. LASSO was used to model the relationship between the natural language features and depression risk. Open-ended text within a 30-day and 60-day timeframe of completing an EPDS was found to be moderately predictive of moderate to severe depression risk (AUROC=0.66 and 0.67, for each respective timeframe). When combined with average daily reported mood, open-ended text showed good predictive power (AUROC=0.87). Consistently predictive language features across all models included themes of "money" and "sadness." The combination of natural language and other user-reported data collected through a mobile health app offers an opportunity for identifying depression risk among a pregnant population.

Longitudinal relationships between COVID-19 preventative behaviors and perceived vulnerability to disease.

Engagement in infection-preventing behaviors (e.g., mask wearing) has become crucial in the context of the COVID-19 pandemic, and health-related anxiety may be an important determinant of individual compliance with recommended guidelines. However, little is known about transactional associations between health anxiety and preventative behaviors, particularly with respect to COVID-19. The present study aimed to longitudinally examine the links between preventative behaviors and both emotion-driven (Germ Aversion) and belief-based (Perceived Infectability) aspects of health anxiety during the COVID-19 pandemic. We hypothesized that greater health anxiety at Time 1 (early in the pandemic) would predict future compliance with preventative behaviors six months later. Two hundred and ninety-six adults (M/SDage= 30.9/10.9 years, 42.2% female) completed two online assessments during the COVID-19 pandemic (Time 1 =June 2020; Time 2 =December 2020). Longitudinal cross-lagged analyses revealed that initial Germ Aversion predicted greater engagement in preventative behaviors at follow-up (ß = 0.16; p = <.001), over and above initial engagement in such behaviors. Similarly, initial engagement in preventative behaviors predicted increases in Germ Aversion at follow-up (ß = .23; p = <.001), over and above initial Germ Aversion. The present findings indicate that affect-driven aspects of health anxiety have a complex transactional relationship with engagement in behaviors aimed at curbing the spread of the COVID-19 pandemic. Clinical and public health implications are discussed.

Quantitative Head Dynamics Associated with Interpersonal (Grandiose-Manipulative) Psychopathic Traits in Incarcerated Youth.

Clinicians have long noted that individuals with elevated psychopathic traits can be characterized by unique interpersonal styles, including prolonged eye contact, invasion of interpersonal space, and frequent use of hand gestures. Such forms of nonverbal communication can be measured via hand, body, and head position and dynamics. Previous studies have developed an automated algorithm designed to capture head position and dynamics from digital recordings of clinical interviews in a sample of incarcerated adult men. We observed that higher psychopathy scores were associated with stationary head dwell time. Here, we applied a similar automated algorithm to assess head position and dynamics on videotaped clinical interviews assessing psychopathic traits from n = 242 youth housed at a maximum-security juvenile correctional facility. We observed that higher psychopathy scores (assessed via the Hare Psychopathy Checklist: Youth Version [PCL:YV]) were associated with unique patterns of head dynamics. Specifically, PCL:YV Total, Factor 1 (measuring grandiose-manipulative and callous-unemotional traits), and Facet 1 (measuring grandiose-manipulative traits) scores were associated with a higher proportion of time spent in a head dynamics pattern consisting of moderate movement away from the average head position. This study lays the groundwork for future investigations to apply quantitative methods to better understand patterns of nonverbal communication styles in clinical populations characterized by severe antisocial behavior.

Creating a Collaborative Trauma-Informed Interdisciplinary Citywide Victim Services Model Focused on Health Care for Survivors of Human Trafficking.

Although human trafficking is recognized as a public health issue, research on the health effects of human trafficking and best intervention practices is limited. We describe 2 citywide collaborative victim services models, the THRIVE (Trafficking, Healthcare, Resources, and Interdisciplinary Victim Services and Education) Clinic at the University of Miami and Jackson Health System in Miami, Florida, and the Greater Houston Area Pathways for Advocacy-based, Trauma-Informed Healthcare (PATH) Collaborative at Baylor College of Medicine, CommonSpirit Health, and San Jose Clinic in Houston, Texas, funded in part by the Office for Victims of Crime, which focus on trauma-informed health care delivery for victims of human trafficking. From June 2015 through September 2021, the THRIVE Clinic served 214 patients with an average age of 28.7 years at the time of their first visit. From October 2017 through September 2021, the PATH Collaborative received 560 suspected trafficking referrals, 400 of which screened positive for labor or sex trafficking. These models serve as a framework for replication of interdisciplinary practices to provide health care for this unique population and preliminary information about the strategies put in place to assist victims during their recovery. Key lessons include the importance of a citywide needs assessment, patient navigators, interdisciplinary care, and building community partnerships to ensure safe housing, transportation, identification, health insurance, vocation services, input from survivors, peer-to-peer mentorship, and medical-legal services. Further research is needed to understand the detrimental health effects of trafficking and the health care needs of victims. In addition, a need exists to develop optimal models of care for recovery and reintegration for this patient population and to address public health, legal, and medical policies to ensure access to and sustainability of comprehensive, trauma-informed, interdisciplinary victim services.

Use of a Smartphone App to Explore Potential Underuse of Prophylactic Aspirin for Preeclampsia.

Importance: Preeclampsia is a leading preventable cause of maternal morbidity and mortality. Initiation of low-dose aspirin (LDASA) treatment at or before 16 weeks' gestation may prevent preeclampsia onset for patients with specific risk factors. Objective: To assess potential underuse of LDASA and reasons for underuse using data from a prenatal care smartphone app. Design, Setting, and Participants: In this prospective cohort study, English-speaking pregnant patients aged 18 years or older from the UPMC health care system received an invitation to use the MyHealthyPregnancy app at their first prenatal appointment. Use of the app was voluntary. The study took place between September 23, 2019, and August 31, 2020, as part of a quality-improvement initiative. Exposures: The app offered educational information, monitoring tools, and routine screenings tailored to patient-entered gestational age and demographic and clinical characteristics. App-based questions included LDASA eligibility based on US Preventive Services Task Force criteria for preeclampsia risk and a monthly prompt about LDASA recommendations from the patient's health care practitioner. Main Outcomes and Measures: The primary outcomes were the receipt of LDASA recommendations from a practitioner and adherence to any such recommendation, as self-reported on the app. Patients' medical records were examined to cross-reference their self-reports of an LDASA recommendation. Multivariable logistic regression was used to model patient-perceived recommendation as a function of factors associated with preeclampsia. Results: The patient cohort consisted of 2563 patient participants (2036 [79%] White; mean [SD] age, 30 [5.2] years) with 2567 pregnancies; 1882 pregnancies (73.3%) were among women with private or employer-based insurance, and 1246 (48.5%) were among nulliparous patients. At least 1 factor associated with high risk for preeclampsia was reported in 316 pregnancies (12.3%), and 2 or more factors associated with moderate risk were reported in 1051 (40.9%). Of the 1015 pregnancies for which patients answered voluntary questions about aspirin use, 124 (12.2%) met at least 1 criterion for highest risk of preeclampsia. In 57 (46.0%) of these pregnancies, the patient indicated that their practitioner recommended LDASA; after examination of the medical records, 90 pregnancies (72.6%) had evidence of an LDASA recommendation and 34 (27.4%) did not. Of the 90 pregnancies with a documented LDASA recommendation, 33 patients (36.7%) were unaware of it. Prior preeclampsia (28 weeks' gestation: odds ratio, 20.1; 95% CI, 11.0-36.9) and chronic hypertension (28 weeks' gestation: odds ratio, 17.4; 95% CI, 6.3-48.2) were the primary high-risk factors associated with recommendation of LDASA. Conclusions and Relevance: In this cohort study, only 46.0% of prenatal care app users who met the criteria for highest preeclampsia risk reported receiving an LDASA recommendation from their practitioner, and medical records suggested that there may have been frequent miscommunication between patients and practitioners about LDASA use. Digital tools such as the MyHealthyPregnancy app might offer an opportunity to improve identification of patients at risk for preeclampsia and communication with these patients about aspirin use.

Dimensions of impulsivity related to psychopathic traits and homicidal behavior among incarcerated male youth offenders.

Despite impulsivity being included as scoring criteria within several measures of youth psychopathic traits, the relationship between psychopathic traits and dimensions of impulsivity among high-risk youth is not well-understood. Here we assessed psychopathic traits via total, factor, and facet scores from the Psychopathy Checklist: Youth Version (PCL:YV) and impulsivity through total, three-factor, and six-factor model scores from the Barratt Impulsiveness Scale (BIS-11) in incarcerated male youth offenders. Correlational analyses indicated PCL:YV total, Factor 2, Facet 3, and Facet 4 scores were significantly positively correlated with BIS-11 total scores. Additionally, psychopathy scores were significantly positively correlated with specific scores from the three-factor model of the BIS-11 (e.g. Motor and Non-Planning Impulsivity scores) and the six-factor model of the BIS-11 (e.g., Attention, Self-Control, and Cognitive Complexity Impulsivity scores). Secondary analyses suggest that participants who had previously committed homicide scored higher on lifestyle/antisocial psychopathic traits and specific dimensions of impulsivity (e.g., BIS-11 Non-Planning and Self-Control Impulsivity factor scores) compared to youth who had not previously committed homicide. Our results improve our understanding of the specific forms of impulsivity significantly correlated with youth psychopathic traits and how specific factors underlying both constructs potentially characterize youth associated with severe forms of antisocial behavior.

Maize E2F transcription factors. Expression, association to promoters of S-phase genes and interaction with the RBR1 protein in chromatin during seed germination.

For seed germination, it is necessary to restart the cell cycle, a process regulated at multiple levels including transcriptional control, that is executed by the E2F family of transcription factors. We identified 12 genes of the E2F family in maize that are expressed differentially during the first 28 h post imbibition (HAI). E2Fa/b1;1 and E2Fc proteins were characterized as an activator and a putative repressor respectively, both forming heterodimers with DPb2 that bind differentially to consensus E2F response elements in promoters of E2F target genes. Transcripts of target genes for these transcription factors accumulate during germination; in dry seeds E2Fc protein is enriched in the target promoters and is replaced by E2Fa/b1;1 as germination advances. RBR1 is found in the same promoters in non-imbibed and 28 HAI seeds, when DNA replication has concluded, and transcription of the E2F targets should stop. During germination promoters of these target genes seem to be decorated with histone marks related to relaxed chromatin structure. Therefore, E2Fs appear to occupy their target genes in a context of open chromatin, with RBR1 fine tuning the progression between the phases.

C-reactive protein expression is up-regulated in apical lesions of endodontic origin in association with interleukin-6.

INTRODUCTION: C-reactive protein (CRP) is the prototype component of acute-phase proteins induced ultimately by interleukin (IL)-6 in the liver, but it is unknown whether periradicular tissues locally express CRP. The present study aimed to identify whether CRP messenger RNA synthesis occurs in situ within apical lesions of endodontic origin (ALEOs) and healthy periodontal ligament and its association with IL-6 and to determine their protein levels and tissue localization. METHODS: Patients with asymptomatic apical periodontitis and healthy volunteers presenting at the School of Dentistry, University of Chile, Santiago, Chile, were enrolled. ALEOs and healthy teeth were obtained and processed for either immunohistochemistry and double immunofluorescence to assess IL-6 and CRP tissue localization, whereas healthy periodontal ligaments were processed as controls for real-time reverse-transcription polymerase chain reaction for their RNA expression levels and multiplex assay to determine their protein levels. Statistic analysis was performed using the unpaired t test or Mann-Whitney test according to data distribution and Pearson correlation. RESULTS: IL-6 and CRP were synthesized in ALEOs, whereas their RNA expression and protein levels were significantly higher when compared with healthy periodontal ligament. IL-6 and CRP immunolocalized to the inflammatory cells, vascular endothelial cells, and mesenchymal cells. Both, IL-6 and CRP colocalized in ALEOs, and a positive correlation was found between their expression levels (P < .05). CONCLUSIONS: IL-6 and CRP messenger RNA are constitutively expressed in periodontal ligament and up-regulated in ALEOs along with higher protein levels. Given their pleiotropic effects, IL-6 and CRP protein levels in apical tissues might partially explain the development and progression of ALEOs as well as potentially asymptomatic apical periodontitis-associated systemic low-grade inflammation.

Comparison of different probe-level analysis techniques for oligonucleotide microarrays.

Three different software packages for the probe-level analysis of high-density oligonucleotide microarray data were compared using an experiment-derived data set that was validated using real-time PCR. The efficiency with which these three programs could identify true positives in this data set was assessed. In addition, estimates of false-positive and false-negative rates were determined. The performance of the programs using very small data sets was also compared, and recommendations for use are suggested.

Concordant expression of KChIP2 mRNA, protein and transient outward current throughout the canine ventricle.

Expression of the transient outward K+ current (Ito) was analysed in nine different regions of the canine ventricle. In addition to the previously described transmural gradients in the right and left ventricular free walls, an inverted U-shaped pattern of Ito expression was observed in the interventricular septum. The mRNA and protein expression for the K+ channel beta subunit KChIP2 were examined in the same tissues. The KChIP2 protein levels closely matched mRNA expression in all regions of the ventricle and paralleled the density of Ito. The global pattern of gene expression in human epicardial and endocardial tissue was examined using microarrays. Only 0.1 % of the genes expressed in the human ventricle displayed the same expression pattern as the KChIP2 gene in left ventricle. It is unlikely, therefore, that the reported distribution of KChIP2 protein within the ventricle can be explained by a cross-reaction of the anti-KChIP2 antibody with a different protein. It is concluded that transcriptional regulation of the KChIP2 gene is a primary determinant of Ito expression in heart.