Predicting one-year outcome in first episode psychosis using machine learning.

BACKGROUND: Early illness course correlates with long-term outcome in psychosis. Accurate prediction could allow more focused intervention. Earlier intervention corresponds to significantly better symptomatic and functional outcomes. Our study objective is to use routinely collected baseline demographic and clinical characteristics to predict employment, education or training (EET) status, and symptom remission in patients with first episode psychosis (FEP) at one-year. METHODS AND FINDINGS: 83 FEP patients were recruited from National Health Service (NHS) Glasgow between 2011 and 2014 to a 24-month prospective cohort study with regular assessment of demographic and psychometric measures. An external independent cohort of 79 FEP patients were recruited from NHS Glasgow and Edinburgh during a 12-month study between 2006 and 2009. Elastic net regularised logistic regression models were built to predict binary EET status, period and point remission outcomes at one-year on 83 Glasgow patients (training dataset). Models were externally validated on an independent dataset of 79 patients from Glasgow and Edinburgh (validation dataset). Only baseline predictors shared across both cohorts were made available for model training and validation. After excluding participants with missing outcomes, models were built on the training dataset for EET status, period and point remission outcomes and externally validated on the validation dataset. Models predicted EET status, period and point remission with receiver operating curve (ROC) area under the curve (AUC) performances of 0.876 (95%CI: 0.864, 0.887), 0.630 (95%CI: 0.612, 0.647) and 0.652 (95%CI: 0.635, 0.670) respectively. Positive predictors of EET included baseline EET and living with spouse/children. Negative predictors included higher PANSS suspiciousness, hostility and delusions scores. Positive predictors for symptom remission included living with spouse/children, and affective symptoms on the Positive and Negative Syndrome Scale (PANSS). Negative predictors of remission included passive social withdrawal symptoms on PANSS. A key limitation of this study is the small sample size (n) relative to the number of predictors (p), whereby p approaches n. The use of elastic net regularised regression rather than ordinary least squares regression helped circumvent this difficulty. Further, we did not have information for biological and additional social variables, such as nicotine dependence, which observational studies have linked to outcomes in psychosis. CONCLUSIONS AND RELEVANCE: Using advanced statistical machine learning techniques, we provide the first externally validated evidence, in a temporally and geographically independent cohort, for the ability to predict one-year EET status and symptom remission in individual FEP patients.

Development and preclinical characterization of a humanized antibody targeting CXCL12.

PURPOSE: Our goal was to develop a potent humanized antibody against mouse/human CXCL12. This report summarized its in vitro and in vivo activities. EXPERIMENTAL DESIGN: Cell surface binding and cell migration assays were used to select neutralizing hamster antibodies, followed by testing in several animal models. Monoclonal antibody (mAb) 30D8 was selected for humanization based on its in vitro and in vivo activities. RESULTS: 30D8, a hamster antibody against mouse and human CXCL12α, CXCL12ß, and CXCL12γ, was shown to dose-dependently block CXCL12α binding to CXCR4 and CXCR7, and CXCL12α-induced Jurkat cell migration in vitro. Inhibition of primary tumor growth and/or metastasis was observed in several models. 30D8 alone significantly ameliorated arthritis in a mouse collagen-induced arthritis model (CIA). Combination with a TNF-α antagonist was additive. In addition, 30D8 inhibited 50% of laser-induced choroidal neovascularization (CNV) in mice. Humanized 30D8 (hu30D8) showed similar in vitro and in vivo activities as the parental hamster antibody. A crystal structure of the hu30D8 Fab/CXCL12α complex in combination with mutational analysis revealed a "hot spot" around residues Asn(44)/Asn(45) of CXCL12α and part of the RFFESH region required for CXCL12α binding to CXCR4 and CXCR7. Finally, hu30D8 exhibited fast clearance in cynomolgus monkeys but not in rats. CONCLUSION: CXCL12 is an attractive target for treatment of cancer and inflammation-related diseases; hu30D8 is suitable for testing this hypothesis in humans.