Tyler M Moore1,2, Monica E Calkins1,2, Adon F G Rosen1, Ellyn R Butler1, Kosha Ruparel1,2, Paolo Fusar-Poli3,4,5, Nikolaos Koutsouleris6, Philip McGuire3, Tyrone D Cannon7, Ruben C Gur1,2, Raquel E Gur1,2. 1. Department of Psychiatry, Brain Behavior Laboratory, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA19104, USA. 2. Lifespan Brain Institute, Penn Medicine and Children's Hospital of Philadelphia, Philadelphia, PA19104, USA. 3. Department of Psychosis Studies, Institute of Psychiatry, Psychology & Neuroscience, King's College London, London, UK. 4. OASIS service, South London and Maudsley NHS Foundation Trust, London, UK. 5. Department of Brain and Behavioral Sciences, University of Pavia, Pavia, Italy. 6. Department of Psychiatry and Psychotherapy, Ludwig-Maximilian-University Munich, Germany. 7. Departments of Psychology and Psychiatry, Yale University, New Haven, CT06520, USA.
Abstract
BACKGROUND: Assessment of risks of illnesses has been an important part of medicine for decades. We now have hundreds of 'risk calculators' for illnesses, including brain disorders, and these calculators are continually improving as more diverse measures are collected on larger samples. METHODS: We first replicated an existing psychosis risk calculator and then used our own sample to develop a similar calculator for use in recruiting 'psychosis risk' enriched community samples. We assessed 632 participants age 8-21 (52% female; 48% Black) from a community sample with longitudinal data on neurocognitive, clinical, medical, and environmental variables. We used this information to predict psychosis spectrum (PS) status in the future. We selected variables based on lasso, random forest, and statistical inference relief; and predicted future PS using ridge regression, random forest, and support vector machines. RESULTS: Cross-validated prediction diagnostics were obtained by building and testing models in randomly selected sub-samples of the data, resulting in a distribution of the diagnostics; we report the mean. The strongest predictors of later PS status were the Children's Global Assessment Scale; delusions of predicting the future or having one's thoughts/actions controlled; and the percent married in one's neighborhood. Random forest followed by ridge regression was most accurate, with a cross-validated area under the curve (AUC) of 0.67. Adjustment of the model including only six variables reached an AUC of 0.70. CONCLUSIONS: Results support the potential application of risk calculators for screening and identification of at-risk community youth in prospective investigations of developmental trajectories of the PS.
BACKGROUND: Assessment of risks of illnesses has been an important part of medicine for decades. We now have hundreds of 'risk calculators' for illnesses, including brain disorders, and these calculators are continually improving as more diverse measures are collected on larger samples. METHODS: We first replicated an existing psychosis risk calculator and then used our own sample to develop a similar calculator for use in recruiting 'psychosis risk' enriched community samples. We assessed 632 participants age 8-21 (52% female; 48% Black) from a community sample with longitudinal data on neurocognitive, clinical, medical, and environmental variables. We used this information to predict psychosis spectrum (PS) status in the future. We selected variables based on lasso, random forest, and statistical inference relief; and predicted future PS using ridge regression, random forest, and support vector machines. RESULTS: Cross-validated prediction diagnostics were obtained by building and testing models in randomly selected sub-samples of the data, resulting in a distribution of the diagnostics; we report the mean. The strongest predictors of later PS status were the Children's Global Assessment Scale; delusions of predicting the future or having one's thoughts/actions controlled; and the percent married in one's neighborhood. Random forest followed by ridge regression was most accurate, with a cross-validated area under the curve (AUC) of 0.67. Adjustment of the model including only six variables reached an AUC of 0.70. CONCLUSIONS: Results support the potential application of risk calculators for screening and identification of at-risk community youth in prospective investigations of developmental trajectories of the PS.
Authors: Barbara A Cornblatt; Ricardo E Carrión; Jean Addington; Larry Seidman; Elaine F Walker; Tyronne D Cannon; Kristin S Cadenhead; Thomas H McGlashan; Diana O Perkins; Ming T Tsuang; Scott W Woods; Robert Heinssen; Todd Lencz Journal: Schizophr Bull Date: 2011-11-10 Impact factor: 9.306
Authors: J Kaufman; B Birmaher; D Brent; U Rao; C Flynn; P Moreci; D Williamson; N Ryan Journal: J Am Acad Child Adolesc Psychiatry Date: 1997-07 Impact factor: 8.829
Authors: TianHong Zhang; HuiJun Li; YingYing Tang; Margaret A Niznikiewicz; Martha E Shenton; Matcheri S Keshavan; William S Stone; Robert W McCarley; Larry J Seidman; JiJun Wang Journal: Am J Psychiatry Date: 2018-09-01 Impact factor: 18.112
Authors: R C Gur; J D Ragland; P J Moberg; T H Turner; W B Bilker; C Kohler; S J Siegel; R E Gur Journal: Neuropsychopharmacology Date: 2001-11 Impact factor: 7.853
Authors: Karl Y Bilimoria; Yaoming Liu; Jennifer L Paruch; Lynn Zhou; Thomas E Kmiecik; Clifford Y Ko; Mark E Cohen Journal: J Am Coll Surg Date: 2013-09-18 Impact factor: 6.113
Authors: Joaquim Radua; Valentina Ramella-Cravaro; John P A Ioannidis; Abraham Reichenberg; Nacharin Phiphopthatsanee; Taha Amir; Hyi Yenn Thoo; Dominic Oliver; Cathy Davies; Craig Morgan; Philip McGuire; Robin M Murray; Paolo Fusar-Poli Journal: World Psychiatry Date: 2018-02 Impact factor: 49.548
Authors: Ruben C Gur; Jan Richard; Paul Hughett; Monica E Calkins; Larry Macy; Warren B Bilker; Colleen Brensinger; Raquel E Gur Journal: J Neurosci Methods Date: 2009-11-27 Impact factor: 2.390