Psychosocial Variables as Predictors of Psychological Stress–Induced Ischemia in the Laboratory

This study examined ischemic reactivity to a psychological stress protocol and whether psychological variables could reliably classify individuals as ischemic reactors. Participants were 54 male Veterans Administration patients who had or were suspected of having CAD. Psychological inventories were administered prior to a psychological stress protocol consisting of a surgical video, the Stroop Color–Word task, an arithmetic task, and discussion of a stressful event. Cardiac functioning was evaluated using an ECG Holter monitor and 23.53% of participants were classified as reactors. Mean differences between reactors and nonreactors were found for State Anger, Health Locus of Control—Powerful Others (MHLC-PO), and Depression. State Anger and MHLC-PO emerged as significant predictors of reactor status in logistic regression analyses. Models based on individual scale items suggested three items could be used to achieve higher classification rates. Implications for revising screening procedures for determining risk and possible mechanisms underlying psychological stress–induced ischemia are discussed.     

Two-Part Predictors in Regression Models

Researchers often build regression models to relate a response to a set of predictor variables. In some cases, there are predictors that apply to some participants, or to some measurement occasions, but not others. For example, a romantic partner's substance use may be a key predictor of one's own substance use. However, not all participants have a partner, and in a longitudinal study, participants may have a partner during only some occasions. This could be viewed as missing data, but of a very distinctive type: the values are not just unknown but also undefined. In this paper, we present a simple method to accommodate this situation, along with a motivating example, the algebraic justification, a simulation study, and examples on how to carry out the technique.     

Inconsistencies in the Reporting of Perceived Trauma Severity Among Acute Physical Injury Survivors

This study aimed to identify and predict inconsistency in perceived trauma severity reports over time among trauma survivors. Hospitalized adult survivors of a traumatic injury completed trauma exposure assessments within 40 days post-injury and 6 weeks later (n = 77). The following trauma severity characteristics were examined: (1) threat of loss of life, (2) threat of loss of a body part, (3) threat of serious injury, and (4) peritraumatic emotionality. Potential predictors of inconsistency were also examined. About half of the reports regarding perceived trauma severity characteristics were inconsistent between the baseline to 6-week assessment. The inconsistent reports were mostly small and equally likely to be either more or less severe over time. Increases in posttraumatic stress disorder (PTSD; especially avoidance) predicted increases in severity of life threat and threat of loss of a body part. Thus, acute reports of perceived trauma severity vary and are influenced by PTSD symptoms.     

Predictors of PTSD Improvement with Cognitive/Exposure Group Interventions in Operation Enduring Freedom/Operation Iraqi Freedom Female Veterans

Predictors of successful PTSD outcome have been examined through individually delivered treatments. We examined predictors using a group protocol with cognitive, exposure, and skills modules. Assessments included self-report and interview (CAPS, SCID-I/II) measures at baseline, post, and six months; treatment was a 16-week, three-member group for 32 OEF/OIF women Veterans. A regression analysis showed major depressive disorder and no baseline psychiatric medication predicted PTSD improvement. PTSD improvement predicted fewer outpatient medical visits at follow-up. The results supported past research and challenged other findings (e.g., sexual assault predicts less improvement). An additional unique contribution was examining predictors in a group treatment format.     

Infants’ statistical word segmentation in an artificial language is linked to both parental speech input and reported production abilities

Individual variability in infant's language processing is partly explained by environmental factors, like the quantity of parental speech input, as well as by infant‐specific factors, like speech production. Here, we explore how these factors affect infant word segmentation. We used an artificial language to ensure that only statistical regularities (like transitional probabilities between syllables) could cue word boundaries, and then asked how the quantity of parental speech input and infants’ babbling repertoire predict infants’ abilities to use these statistical cues. We replicated prior reports showing that 8‐month‐old infants use statistical cues to segment words, with a preference for part‐words over words (a novelty effect). Crucially, 8‐month‐olds with larger novelty effects had received more speech input at 4 months and had greater production abilities at 8 months. These findings establish for the first time that the ability to extract statistical information from speech correlates with individual factors in infancy, like early speech experience and language production. Implications of these findings for understanding individual variability in early language acquisition are discussed.     

Combining predictors for multi-layer architecture of adaptive fuzzy inference system

To solve problems with a Sugeno adaptive fuzzy neural network using training data, it is necessary to select the appropriate combination of input characteristics of the sub-adaptive neuro-fuzzy inference system (ANFIS) and to determine the appropriate topology. The multi-layer architecture of a sub-ANFIS (MLA-ANFIS) is a good model for prediction problems and solves them modularity. Since, the combination of several predictors is the current focus in the construction of hybrid intelligent systems; we created many solutions to combine machine learning methods, namely ANFIS, support vector machine (SVM), deep neural network (DNN), naive Bayes (NB), linear regression (LR), extreme learning machine (ELM), and decision tree (DT) mixed predictors, and ensemble bootstrap aggregation based on MLA-ANFIS in order to discover the optimal model of combined predictors based on the MLA-ANFIS with a combination of input features entered in the MLA-ANFIS. We implemented our approaches on 365-day concrete compressive strength, thoracic surgery, fertility diagnosis, breast, energy, and glass identification datasets from UCI. The experimental results prove that the combining predictors for the MLA-ANFIS show performance improvements compared to the pure MLA-ANFIS method.     

Predictors of improvement in an open-trial multisite evaluation of emotion regulation group therapy

Emotion regulation group therapy (ERGT) is a novel treatment specifically targeting deliberate non-suicidal self-harm (DSH) in individuals with borderline personality disorder (BPD). Identifying robust predictors of positive response to ERGT could aid clinicians in treatment selection; however, to date, only one such study has been conducted. Thus, we aimed to replicate previously identified predictors of treatment response to ERGT by investigating demographic, clinical, and diagnostic predictors in 95 women with BPD or subclinical BPD who had participated in an open-trial evaluation of ERGT. Outcomes evaluated were frequency of DSH and emotion dysregulation. Assessments were conducted at pretreatment, post-treatment, and 6-month follow-up. Multilevel mixed linear models and multilevel negative binomial generalized estimated equations were used to identify significant interactions between the predictors and outcomes.

We found that greater pretreatment DSH frequency was associated with greater improvements in DSH during treatment (b = 0.998, SE = 0.00, p = 0.03) and follow-up (b = 0.997, SE = 0.00, p < 0.01) and that greater BPD severity was associated with greater improvements in DSH during treatment (b = 0.84, SE = 0.06, p = 0.02) and in emotion dysregulation at follow-up (b = ?3.05, SE = 1.47, p = 0.04). Co-occurring disorders were associated with poorer treatment response during follow-up. Results were generally consistent with a previous study of the predictors of response to ERGT. The findings provide further support for the utility of this treatment across a range of BPD patients, including patients with severe DSH and BPD.     

The role of optimism in the process of schema-focused cognitive therapy of personality problems

The aim of this study was to examine the determinants and effects of optimism in the process of schema-focused cognitive therapy of personality problems. The sample consisted of 35 patients with panic disorder and/or agoraphobia and DSM-IV Cluster C personality traits who participated in an 11-week residential program with one symptom-focused and one personality-focused phase. This study examines the role played by optimism during the individual sessions of the second phase, using a time series approach. Decreased patient's belief in his/her primary Early Maladaptive Schema and increased patient-experienced empathy from the therapist in a session predicted increased patient-rated optimism before the subsequent session. Increased patient-rated optimism in turn predicted decreased schema belief and distress and increased insight, empathy, and therapist-rated optimism. The slope of optimism across sessions was related to change in most of the overall outcome measures. There appears to be a positive feedback in the process of schema-focused cognitive therapy between decreased schema belief and increased optimism. In addition, optimism appears to mediate the effects of schema belief and therapist empathy on overall improvement, and to serve as an antecedent to decreased distress and to increased empathy, insight, and therapist's optimism.     

CBT对社交焦虑障碍有效干预的神经预测因子及机器学习应用

认知行为疗法（CBT）是社交焦虑障碍的标准疗法,对其疗效的神经预测因子研究有利于个性化诊疗方案选择。初步证据表明,干预前高级视皮层、背侧前扣带回、背内/外侧前额叶及眶额皮层的功能激活,杏仁核与情绪调节相关脑区的结构与功能连接,情绪性刺激诱发的晚期正成分与治疗后症状的改善有关,因而是潜在的预测因子。基于机器学习的个体化预测存在样本量小的突出问题。未来研究应考虑跨研究机构合作共享大数据,在多模态、多任务条件下收集数据,并在独立样本中验证预测的有效性。