RESUMEN
Patients with obstructive sleep apnea (OSA) show autonomic, mood, cognitive, and breathing dysfunctions that are linked to increased morbidity and mortality, which can be improved with early screening and intervention. The gold standard and other available methods for OSA diagnosis are complex, require whole-night data, and have significant wait periods that potentially delay intervention. Our aim was to examine whether using faster and less complicated machine learning models, including support vector machine (SVM) and random forest (RF), with brain diffusion tensor imaging (DTI) data can classify OSA from healthy controls. We collected two DTI series from 59 patients with OSA [age: 50.2 ± 9.9 years; body mass index (BMI): 31.5 ± 5.6 kg/m2 ; apnea-hypopnea index (AHI): 34.1 ± 21.2 events/h 23 female] and 96 controls (age: 51.8 ± 9.7 years; BMI: 26.2 ± 4.1 kg/m2 ; 51 female) using a 3.0-T magnetic resonance imaging scanner. Using DTI data, mean diffusivity maps were calculated from each series, realigned and averaged, normalised to a common space, and used to conduct cross-validation for model training and selection and to predict OSA. The RF model showed 0.73 OSA and controls classification accuracy and 0.85 area under the curve (AUC) value on the receiver-operator curve. Cross-validation showed the RF model with comparable fitting over SVM for OSA and control data (SVM; accuracy, 0.77; AUC, 0.84). The RF ML model performs similar to SVM, indicating the comparable statistical fitness to DTI data. The findings indicate that RF model has similar AUC and accuracy over SVM, and either model can be used as a faster OSA screening tool for subjects having brain DTI data.
Asunto(s)
Imagen de Difusión Tensora , Apnea Obstructiva del Sueño , Humanos , Femenino , Adulto , Persona de Mediana Edad , Apnea Obstructiva del Sueño/diagnóstico por imagen , Apnea Obstructiva del Sueño/patología , Encéfalo , Índice de Masa Corporal , Aprendizaje AutomáticoRESUMEN
BACKGROUND: Adversity occurring during development is associated with detrimental health and quality of life outcomes, not just following exposure but throughout the lifespan. Despite increased research, there exists both overlapping and distinct definitions of early life adversity exposure captured by over 30 different empirically validated tools. A data-driven approach to defining and cataloging exposure is needed to better understand associated outcomes and advance the field. METHODS: We utilized baseline data on 11,566 youth enrolled in the ABCD Study to catalog youth and caregiver-reported early life adversity exposure captured across 14 different measures. We employed an exploratory factor analysis to identify the factor domains of early life adversity exposure and conducted a series of regression analyses to examine its association with problematic behavioral outcomes. RESULTS: The exploratory factor analysis yielded a 6-factor solution corresponding to the following distinct domains: 1) physical and sexual violence; 2) parental psychopathology; 3) neighborhood threat; 4) prenatal substance exposure; 5) scarcity; and 6) household dysfunction. The prevalence of exposure among 9-and 10-year-old youth was largely driven by the incidence of parental psychopathology. Sociodemographic characteristics significantly differed between youth with adversity exposure and controls, depicting a higher incidence of exposure among racial and ethnic minoritized youth, and among those identifying with low socioeconomic status. Adversity exposure was significantly associated with greater problematic behaviors and largely driven by the incidence of parental psychopathology, household dysfunction and neighborhood threat. Certain types of early life adversity exposure were more significantly associated with internalizing as opposed to externalizing problematic behaviors. CONCLUSIONS: We recommend a data-driven approach to define and catalog early life adversity exposure and suggest the incorporation of more versus less data to capture the nuances of exposure, e.g., type, age of onset, frequency, duration. The broad categorizations of early life adversity exposure into two domains, such as abuse and neglect, or threat and deprivation, fail to account for the routine co-occurrence of exposures and the duality of some forms of adversity. The development and use of a data-driven definition of early life adversity exposure is a crucial step to lessening barriers to evidence-based treatments and interventions for youth.
Asunto(s)
Experiencias Adversas de la Infancia , Femenino , Adolescente , Embarazo , Humanos , Niño , Calidad de VidaRESUMEN
Background and Purpose- The National Institutes of Health Stroke Scale, designed and validated for use in clinical stroke trials, is now required for all patients with stroke at hospital admission. Recertification is required annually but no data support this frequency; the effect of mandatory training before recertification is unknown. Methods- To clarify optimal recertification frequency and training effect, we assessed users' mastery of the National Institutes of Health Stroke Scale over several years using correct scores (accuracy) on each scale item of the 15-point scale. We also constructed 9 technical errors that could result from misunderstanding the scoring rules. We measured accuracy and the frequency of these technical errors over time. Using multivariable regression, we assessed the effect of time, repeat testing, and profession on user mastery. Results- The final dataset included 1.3×106 examinations. Data were consistent among all 3 online vendors that provide training and certification. Test accuracy showed no significant changes over time. Technical error rates were remarkably low, ranging from 0.48 to 1.36 per 90 test items. Within 2 vendors (that do not require training), the technical error rates increased negligibly over time (P<0.05). In data from a third vendor, mandatory training before recertification improved (reduced) technical errors but not accuracy. Conclusions- The data suggest that mastery of National Institutes of Health Stroke Scale scoring rules is stable over time, and the recertification interval should be lengthened. Mandatory retraining may be needed after unsuccessful recertifications, but not routinely otherwise.
Asunto(s)
Certificación , Índice de Severidad de la Enfermedad , Accidente Cerebrovascular , Ensayos Clínicos como Asunto , Femenino , Humanos , Masculino , National Institutes of Health (U.S.) , Estados UnidosRESUMEN
BACKGROUND: To characterize acoustic features of an infant's cry and use machine learning to provide an objective measurement of behavioral state in a cry-translator. To apply the cry-translation algorithm to colic hypothesizing that these cries sound painful. METHODS: Assessment of 1000 cries in a mobile app (ChatterBabyTM). Training a cry-translation algorithm by evaluating >6000 acoustic features to predict whether infant cry was due to a pain (vaccinations, ear-piercings), fussy, or hunger states. Using the algorithm to predict the behavioral state of infants with reported colic. RESULTS: The cry-translation algorithm was 90.7% accurate for identifying pain cries, and achieved 71.5% accuracy in discriminating cries from fussiness, hunger, or pain. The ChatterBaby cry-translation algorithm overwhelmingly predicted that colic cries were most likely from pain, compared to fussy and hungry states. Colic cries had average pain ratings of 73%, significantly greater than the pain measurements found in fussiness and hunger (p < 0.001, 2-sample t test). Colic cries outranked pain cries by measures of acoustic intensity, including energy, length of voiced periods, and fundamental frequency/pitch, while fussy and hungry cries showed reduced intensity measures compared to pain and colic. CONCLUSIONS: Acoustic features of cries are consistent across a diverse infant population and can be utilized as objective markers of pain, hunger, and fussiness. The ChatterBaby algorithm detected significant acoustic similarities between colic and painful cries, suggesting that they may share a neuronal pathway.
Asunto(s)
Dolor Abdominal/psicología , Acústica , Cólico/psicología , Llanto , Conducta del Lactante , Aprendizaje Automático , Aplicaciones Móviles , Percepción del Dolor , Procesamiento de Señales Asistido por Computador , Dolor Abdominal/diagnóstico , Cólico/diagnóstico , Femenino , Humanos , Lactante , Recién Nacido , Masculino , Reconocimiento de Normas Patrones Automatizadas , Espectrografía del SonidoRESUMEN
22q11.2 Deletion syndrome (22q11DS) is a genetic disorder associated with numerous phenotypic consequences and is one of the greatest known risk factors for psychosis. We investigated intrinsic-connectivity-networks (ICNs) as potential biomarkers for patient and psychosis-risk status in 2 independent cohorts, UCLA (33 22q11DS-participants, 33 demographically matched controls), and Syracuse (28 22q11DS, 28 controls). After assessing group connectivity differences, ICNs from the UCLA cohort were used to train classifiers to distinguish cases from controls, and to predict psychosis risk status within 22q11DS; classifiers were subsequently tested on the Syracuse cohort. In both cohorts we observed significant hypoconnectivity in 22q11DS relative to controls within anterior cingulate (ACC)/precuneus, executive, default mode (DMN), posterior DMN, and salience networks. Of 12 ICN-derived classifiers tested in the Syracuse replication-cohort, the ACC/precuneus, DMN, and posterior DMN classifiers accurately distinguished between 22q11DS and controls. Within 22q11DS subjects, connectivity alterations within 4 networks predicted psychosis risk status for a given individual in both cohorts: the ACC/precuneus, DMN, left executive, and salience networks. Widespread within-network-hypoconnectivity in large-scale networks implicated in higher-order cognition may be a defining characteristic of 22q11DS during adolescence and early adulthood; furthermore, loss of coherence within these networks may be a valuable biomarker for individual prediction of psychosis-risk in 22q11DS.
Asunto(s)
Síndrome de DiGeorge/complicaciones , Giro del Cíngulo/fisiopatología , Red Nerviosa/fisiopatología , Lóbulo Parietal/fisiopatología , Trastornos Psicóticos , Adolescente , Estudios de Casos y Controles , Niño , Estudios de Cohortes , Conectoma , Femenino , Giro del Cíngulo/diagnóstico por imagen , Humanos , Imagen por Resonancia Magnética , Masculino , Movimiento (Física) , Red Nerviosa/diagnóstico por imagen , Pruebas Neuropsicológicas , Oxígeno/sangre , Lóbulo Parietal/diagnóstico por imagen , Escalas de Valoración Psiquiátrica , Trastornos Psicóticos/clasificación , Trastornos Psicóticos/etiología , Trastornos Psicóticos/genética , Trastornos Psicóticos/patología , Adulto JovenRESUMEN
OBJECTIVES: An estimated 25% of type two diabetes mellitus (DM2) patients in the United States are undiagnosed due to inadequate screening, because it is prohibitive to administer laboratory tests to everyone. We assess whether electronic health record (EHR) phenotyping could improve DM2 screening compared to conventional models, even when records are incomplete and not recorded systematically across patients and practice locations, as is typically seen in practice. METHODS: In this cross-sectional, retrospective study, EHR data from 9948 US patients were used to develop a pre-screening tool to predict current DM2, using multivariate logistic regression and a random-forests probabilistic model for out-of-sample validation. We compared (1) a full EHR model containing commonly prescribed medications, diagnoses (as ICD9 categories), and conventional predictors, (2) a restricted EHR DX model which excluded medications, and (3) a conventional model containing basic predictors and their interactions (BMI, age, sex, smoking status, hypertension). RESULTS: Using a patient's full EHR or restricted EHR was superior to using basic covariates alone for detecting individuals with diabetes (hierarchical X(2) test, p<0.001). Migraines, depot medroxyprogesterone acetate, and cardiac dysrhythmias were associated negatively with DM2, while sexual and gender identity disorder diagnosis, viral and chlamydial infections, and herpes zoster were associated positively. Adding EHR phenotypes improved classification; the AUC for the full EHR Model, EHR DX model, and conventional model using logistic regression, were 84.9%, 83.2%, and 75.0% respectively. For random forest machine learning out-of-sample prediction, accuracy also was improved when using EHR phenotypes; the AUC values were 81.3%, 79.6%, and 74.8%, respectively. Improved AUCs reflect better performance for most thresholds that balance sensitivity and specificity. CONCLUSIONS: EHR phenotyping resulted in markedly superior detection of DM2, even in the face of missing and unsystematically recorded data, based on the ROC curves. EHR phenotypes could more efficiently identify which patients do require, and don't require, further laboratory screening. When applied to the current number of undiagnosed individuals in the United States, we predict that incorporating EHR phenotype screening would identify an additional 400,000 patients with active, untreated diabetes compared to the conventional pre-screening models.
Asunto(s)
Diabetes Mellitus Tipo 2/diagnóstico , Registros Electrónicos de Salud , Informática Médica/métodos , Adulto , Anciano , Área Bajo la Curva , Estudios Transversales , Diabetes Mellitus Tipo 2/epidemiología , Femenino , Humanos , Modelos Logísticos , Aprendizaje Automático , Masculino , Persona de Mediana Edad , Modelos Estadísticos , Fenotipo , Curva ROC , Estudios Retrospectivos , Factores de Riesgo , Estados UnidosRESUMEN
The recent Deoni et al. (2013) manuscript proposed that breastfeeding was associated with increased cognitive ability and white-matter in older children (over 26 months), using ms-DESPOT MRI imaging to indirectly measure white matter in children who were either breastfed, formula fed, or combined breast+formula fed. In this response, we identify limitations in drawing causal inference among white matter, cognitive ability, and breastfeeding. We propose that the observed cognitive and neurodevelopmental differences between breastfed and formula-fed infants might actually be caused by the premature introduction of cow's milk in the second year of life, among other contributing factors. The implication of a causal relationship between intelligence and white matter metrics, especially in a developmentally young population, is premature given the recency of this field. The original analyses did not control for important covariates; when comparing both white matter and test scores, mothers were not controlled for age and socio-economic status (SES) and their children were not controlled for gender. Raw test scores, instead of age-adjusted test scores, were used even though the children were of different ages. Mothers were not controlled for reason(s) not to breastfeed, even though many prenatal factors are known to predict this such as stress, parity, obesity, and smoking habits. The observed cognitive ability and white matter benefits identified primarily within the long-term breastfed children are at least partially attributable to other factors such as age, gender, and SES. We suggest methodological approaches to removing such ambiguity, and ways to dissociate cause from effect. The formula and breastfeeding groups didn't show differences until the "formula fed" children likely had been fed cow's milk for longer than they had been fed formula, at 2.2 years. The greatest cognitive differences however were observed within the high SES breastfed infants depending on breastfeeding duration; infants who were breastfed over 15 months showed increased cognitive ability compared to those breastfed less than months. This implicates the source of dairy during the second year of life, and not other SES factors or infant formula, as the most likely nutritional factor responsible for the observed differences within the breastfed children. Given the known nutritional deficiencies of cow's milk, these findings imply infants who received cow's milk during the second year of life were at a disadvantage compared to those who were breastfed, independent of whether they were fed formula or breast milk during the first year of life. This evidence suggests that infants should receive formula in lieu of cow's milk when breast milk is unavailable as a dairy source, until roughly 2 years of age.
Asunto(s)
Encéfalo/crecimiento & desarrollo , Lactancia Materna , Fibras Nerviosas Mielínicas/ultraestructura , Femenino , Humanos , MasculinoRESUMEN
The recent Chu et al. (2012) manuscript discusses two key findings regarding feature selection (FS): (1) data driven FS was no better than using whole brain voxel data and (2) a priori biological knowledge was effective to guide FS. Use of FS is highly relevant in neuroimaging-based machine learning, as the number of attributes can greatly exceed the number of exemplars. We strongly endorse their demonstration of both of these findings, and we provide additional important practical and theoretical arguments as to why, in their case, the data-driven FS methods they implemented did not result in improved accuracy. Further, we emphasize that the data-driven FS methods they tested performed approximately as well as the all-voxel case. We discuss why a sparse model may be favored over a complex one with similar performance. We caution readers that the findings in the Chu et al. report should not be generalized to all data-driven FS methods.
Asunto(s)
Enfermedad de Alzheimer/clasificación , Enfermedad de Alzheimer/patología , Disfunción Cognitiva/clasificación , Disfunción Cognitiva/patología , Imagen por Resonancia Magnética , Neuroimagen , Femenino , Humanos , MasculinoRESUMEN
In the multimodal neuroimaging framework, data on a single subject are collected from inherently different sources such as functional MRI, structural MRI, behavioral and/or phenotypic information. The information each source provides is not independent; a subset of features from each modality maps to one or more common latent dimensions, which can be interpreted using generative models. These latent dimensions, or "topics," provide a sparse summary of the generative process behind the features for each individual. Topic modeling, an unsupervised generative model, has been used to map seemingly disparate features to a common domain. We use Non-Negative Matrix Factorization (NMF) to infer the latent structure of multimodal ADHD data containing fMRI, MRI, phenotypic and behavioral measurements. We compare four different NMF algorithms and find that the sparsest decomposition is also the most differentiating between ADHD and healthy patients. We identify dimensions that map to interpretable, recognizable dimensions such as motion, default mode network activity, and other such features of the input data. For example, structural and functional graph theory features related to default mode subnetworks clustered with the ADHD-Inattentive diagnosis. Structural measurements of the default mode network (DMN) regions such as the posterior cingulate, precuneus, and parahippocampal regions were all related to the ADHD-Inattentive diagnosis. Ventral DMN subnetworks may have more functional connections in ADHD-I, while dorsal DMN may have less. ADHD topics are dependent upon diagnostic site, suggesting diagnostic differences across geographic locations. We assess our findings in light of the ADHD-200 classification competition, and contrast our unsupervised, nominated topics with previously published supervised learning methods. Finally, we demonstrate the validity of these latent variables as biomarkers by using them for classification of ADHD in 730 patients. Cumulatively, this manuscript addresses how multimodal data in ADHD can be interpreted by latent dimensions.
Asunto(s)
Trastorno por Déficit de Atención con Hiperactividad/diagnóstico , Imagen por Resonancia Magnética , Imagen Multimodal , Neuroimagen , Adolescente , Algoritmos , Trastorno por Déficit de Atención con Hiperactividad/genética , Niño , Femenino , Humanos , Masculino , Fenotipo , Adulto JovenRESUMEN
OBJECTIVE: The current study explores relationships between mindfulness, emotional regulation, impulsivity, and stress proneness in a sample of participants recruited in a Diagnostic and Statistical Manual of Mental Disorder Fifth Edition Field Trial for Hypersexual Disorder and healthy controls to assess whether mindfulness attenuates symptoms of hypersexuality. METHOD: Hierarchal regression analysis was used to assess whether significant relationships between mindfulness and hypersexuality exist beyond associations commonly found with emotional dysregulation, impulsivity, and stress proneness in a sample of male hypersexual patients (n = 40) and control subjects (n = 30). RESULTS: Our results show a robust inverse relationship of mindfulness to hypersexuality over and above associations with emotional regulation, impulsivity, and stress proneness. CONCLUSIONS: These results suggest that mindfulness may be a meaningful component of successful therapy among patients seeking help for hypersexual behavior in attenuating hypersexuality, improving affect regulation, stress coping, and increasing tolerance for desires to act on maladaptive sexual urges and impulses.
Asunto(s)
Atención Plena , Disfunciones Sexuales Psicológicas/psicología , Adolescente , Adulto , Anciano , Ansiedad/fisiopatología , Depresión/fisiopatología , Humanos , Conducta Impulsiva , Masculino , Persona de Mediana Edad , Personalidad/fisiología , Disfunciones Sexuales Psicológicas/fisiopatología , Estrés Psicológico/fisiopatología , Adulto JovenRESUMEN
Although the placebo effect is known to have a strong impact on the outcomes of clinical trials, methods for measuring it are limited to physiological observations. We propose a method of localizing, identifying and measuring placebo and treatment-induced networks in the brain using functional neuroimaging. Measuring the relative activation of these "placebo" brain networks serves as a proxy for the placebo effect contained within the variable of interest (depression rating, blood pressure, etc). Analogous to the difference between a paired and unpaired t-test, this allows for a sharp gain in power and reduction in the sample sizes needed in clinical trials, potentially leading to a drastically smaller sample sizes for establishing efficacy, a shorter time-to-market for a drug, and a drastic reduction in the cost of bringing new drugs into the market.
Asunto(s)
Encéfalo/efectos de los fármacos , Ensayos Clínicos como Asunto/economía , Neuroimagen/economía , Neuroimagen/métodos , Evaluación de Resultado en la Atención de Salud/economía , Preparaciones Farmacéuticas/economía , Efecto Placebo , Ensayos Clínicos como Asunto/métodos , Ahorro de Costo/economía , Ahorro de Costo/métodos , Humanos , Interpretación de Imagen Asistida por Computador/métodos , Evaluación de Resultado en la Atención de Salud/métodos , Preparaciones Farmacéuticas/administración & dosificación , Estados UnidosRESUMEN
Sensory features are common and impairing in autism spectrum disorder (ASD), but there are few observational sensory assessments that are valid across ages. We used the Sensory Processing 3-Dimensional (SP3-D) observed Assessment and parent-reported Inventory to examine sensory responsivity in 41 ASD and 33 typically-developing (TD) youth across 7-17 years. ASD youth had higher and more variable observed and reported sensory responsivity symptoms compared to TD, but the two measures were not correlated. Observed sensory over-responsivity (SOR) and sensory craving (SC) decreased with age in ASD, though SOR remained higher in ASD versus TD through adolescence. Results suggest that in ASD, the SP3-D Assessment can identify SOR through adolescence, and that there is value in integrating multiple sensory measures.
Asunto(s)
Trastorno del Espectro Autista , Adolescente , Humanos , Trastorno del Espectro Autista/diagnóstico , Trastorno del Espectro Autista/complicaciones , Trastornos de la Sensación/diagnóstico , Trastornos de la Sensación/complicaciones , SensaciónRESUMEN
BACKGROUND: Mitigating rating inconsistency can improve measurement fidelity and detection of treatment response. METHODS: The International Society for CNS Clinical Trials and Methodology convened an expert Working Group that developed consistency checks for ratings of the Hamilton Anxiety Rating Scale (HAM-A) and Clinical Global Impression of Severity of anxiety (CGIS) that are widely used in studies of mood and anxiety disorders. Flags were applied to 40,349 HAM-A administrations from 15 clinical trials and to Monte Carlo-simulated data as a proxy for applying flags under conditions of inconsistency. RESULTS: Thirty-three flags were derived these included logical consistency checks and statistical outlier-response pattern checks. Twenty-percent of the HAM-A administrations had at least one logical scoring inconsistency flag, 4 % had two or more. Twenty-six percent of the administrations had at least one statistical outlier flag and 11 % had two or more. Overall, 35 % of administrations had at least one flag of any type, 19 % had one and 16 % had 2 or more. Most of administrations in the Monte Carlo- simulated data raised multiple flags. LIMITATIONS: Flagged ratings may represent less-common presentations of administrations done correctly. Conclusions-Application of flags to clinical ratings may aid in detecting imprecise measurement. Flags can be used for monitoring of raters during an ongoing trial and as part of post-trial evaluation. Appling flags may improve reliability and validity of trial data.
Asunto(s)
Trastornos de Ansiedad , Ansiedad , Humanos , Reproducibilidad de los Resultados , Escalas de Valoración Psiquiátrica , Trastornos de Ansiedad/diagnóstico , Trastornos de Ansiedad/tratamiento farmacológico , PsicometríaRESUMEN
Interictal electroencephalography (EEG) has clinically meaningful limitations in its sensitivity and specificity in the diagnosis of epilepsy because of its dependence on the occurrence of epileptiform discharges. We have developed a computer-aided diagnostic (CAD) tool that operates on the absolute spectral energy of the routine EEG and has both substantially higher sensitivity and negative predictive value than the identification of interictal epileptiform discharges. Our approach used a multilayer perceptron to classify 156 patients admitted for video-EEG monitoring. The patient population was diagnostically diverse; 87 were diagnosed with either generalized or focal seizures. The remainder of the patients were diagnosed with nonepileptic seizures. The sensitivity was 92% (95% confidence interval [CI] 85-97%) and the negative predictive value was 82% (95% CI 67-92%). We discuss how these findings suggest that this CAD can be used to supplement event-based analysis by trained epileptologists.
Asunto(s)
Diagnóstico por Computador/métodos , Electroencefalografía/métodos , Epilepsia/diagnóstico , Epilepsia/fisiopatología , HumanosRESUMEN
The placebo response is a highly complex psychosocial-biological phenomenon that has challenged drug development for decades, particularly in neurological and psychiatric disease. While decades of research have aimed to understand clinical trial factors that contribute to the placebo response, a comprehensive solution to manage the placebo response in drug development has yet to emerge. Advanced data analytic techniques, such as artificial intelligence (AI), might be needed to take the next leap forward in mitigating the negative consequences of high placebo-response rates. The objective of this review was to explore the use of techniques such as AI and the sub-discipline of machine learning (ML) to address placebo response in practical ways that can positively impact drug development. This examination focused on the critical factors that should be considered in applying AI and ML to the placebo response issue, examples of how these techniques can be used, and the regulatory considerations for integrating these approaches into clinical trials.
RESUMEN
BACKGROUND: Symptom manifestations in mood disorders can be subtle. Cumulatively, small imprecisions in measurement can limit our ability to measure treatment response accurately. Logical and statistical consistency checks between item responses (i.e., cross-sectionally) and across administrations (i.e., longitudinally) can contribute to improving measurement fidelity. METHODS: The International Society for CNS Clinical Trials and Methodology convened an expert Working Group that assembled flags indicating consistency/inconsistency ratings for the Hamilton Rating Scale for Depression (HAM-D17), a widely-used rating scale in studies of depression. Proposed flags were applied to assessments derived from the NEWMEDS data repository of 95,468 HAM-D administrations from 32 registration trials of antidepressant medications and to Monte Carlo-simulated data as a proxy for applying flags under conditions of known inconsistency. RESULTS: Two types of flags were derived: logical consistency checks and statistical outlier-response pattern checks. Almost thirty percent of the HAMD administrations had at least one logical scoring inconsistency flag. Seven percent had flags judged to suggest that a thorough review of rating is warranted. Almost 22% of the administrations had at least one statistical outlier flag and 7.9% had more than one. Most of the administrations in the Monte Carlo- simulated data raised multiple flags. LIMITATIONS: Flagged ratings may represent less-common presentations of administrations done correctly. CONCLUSIONS: Application of flags to clinical ratings may aid in detecting imprecise measurement. Reviewing and addressing these flags may improve reliability and validity of clinical trial data.
Asunto(s)
Antidepresivos , Depresión , Antidepresivos/uso terapéutico , Depresión/diagnóstico , Humanos , Trastornos del Humor/tratamiento farmacológico , Escalas de Valoración Psiquiátrica , Reproducibilidad de los ResultadosRESUMEN
Machine learning methods have been applied to classifying fMRI scans by studying locations in the brain that exhibit temporal intensity variation between groups, frequently reporting classification accuracy of 90% or better. Although empirical results are quite favorable, one might doubt the ability of classification methods to withstand changes in task ordering and the reproducibility of activation patterns over runs, and question how much of the classification machines' power is due to artifactual noise versus genuine neurological signal. To examine the true strength and power of machine learning classifiers we create and then deconstruct a classifier to examine its sensitivity to physiological noise, task reordering, and across-scan classification ability. The models are trained and tested both within and across runs to assess stability and reproducibility across conditions. We demonstrate the use of independent components analysis for both feature extraction and artifact removal and show that removal of such artifacts can reduce predictive accuracy even when data has been cleaned in the preprocessing stages. We demonstrate how mistakes in the feature selection process can cause the cross-validation error seen in publication to be a biased estimate of the testing error seen in practice and measure this bias by purposefully making flawed models. We discuss other ways to introduce bias and the statistical assumptions lying behind the data and model themselves. Finally we discuss the complications in drawing inference from the smaller sample sizes typically seen in fMRI studies, the effects of small or unbalanced samples on the Type 1 and Type 2 error rates, and how publication bias can give a false confidence of the power of such methods. Collectively this work identifies challenges specific to fMRI classification and methods affecting the stability of models.
Asunto(s)
Inteligencia Artificial , Mapeo Encefálico/métodos , Interpretación de Imagen Asistida por Computador/métodos , Imagen por Resonancia Magnética , Simulación por Computador , Femenino , HumanosRESUMEN
International Society for CNS Clinical Trials and Methodology convened an expert Working Group that assembled consistency/inconsistency flags for the Personal and Social Performance Scale (PSP). One hundred and forty seven flags were identified, 16 flag errors in deriving the PSP decile (i.e., total) score from the four individual domain scores, 74 flag inconsistencies between domain scores relative to Positive and Negative Symptom Scale (PANSS) item ratings and 57 flag inconsistencies between PSP decile score and PANSS items ratings. The flags were applied to assessments from randomized clinical trial data of antipsychotics in schizophrenia from almost 18,000 ratings. Twenty-two flags were raised in at least 5 of 1000 ratings. Nearly 20% of the PSP ratings had at least one inconsistency flag raised. Application of flags to clinical ratings may improve the reliability of ratings and validity of trials.
Asunto(s)
Antipsicóticos , Esquizofrenia , Humanos , Escalas de Valoración Psiquiátrica , Reproducibilidad de los Resultados , Esquizofrenia/diagnóstico , Esquizofrenia/tratamiento farmacológicoRESUMEN
The analysis of fMRI data is challenging because they consist generally of a relatively modest signal contained in a high-dimensional space: a single scan can contain millions of voxel recordings over space and time. We present a method for classification and discrimination among fMRI that is based on modeling the scans as distance matrices, where each matrix measures the divergence of spatial network signals that fluctuate over time. We used single-subject independent components analysis (ICA), decomposing an fMRI scan into a set of statistically independent spatial networks, to extract spatial networks and time courses from each subject that have unique relationship with the other components within that subject. Mathematical properties of these relationships reveal information about the infrastructure of the brain by measuring the interaction between and strength of the components. Our technique is unique, in that it does not require spatial alignment of the scans across subjects. Instead, the classifications are made solely on the temporal activity taken by the subject's unique ICs. Multiple scans are not required and multivariate classification is implementable, and the algorithm is effectively blind to the subject-uniform underlying task paradigm. Classification accuracy of up to 90% was realized on a resting-scanned schizophrenia/normal dataset and a tasked multivariate Alzheimer's/old/young dataset. We propose that the ICs represent a plausible set of imaging basis functions consistent with network-driven theories of neural activity in which the observed signal is an aggregate of independent spatial networks having possibly dependent temporal activity.
Asunto(s)
Enfermedad de Alzheimer/clasificación , Encéfalo/patología , Interpretación de Imagen Asistida por Computador/métodos , Imagen por Resonancia Magnética , Esquizofrenia/clasificación , Adulto , Factores de Edad , Anciano , Algoritmos , Enfermedad de Alzheimer/patología , Humanos , Persona de Mediana Edad , Esquizofrenia/patología , Sensibilidad y EspecificidadRESUMEN
BACKGROUND: 22q11.2 copy number variants are among the most highly penetrant genetic risk variants for developmental neuropsychiatric disorders such as schizophrenia (SCZ) and autism spectrum disorder (ASD). However, the specific mechanisms through which they confer risk remain unclear. METHODS: Using a functional genomics approach, we integrated transcriptomic data from the developing human brain, genome-wide association findings for SCZ and ASD, protein interaction data, and gene expression signatures from SCZ and ASD postmortem cortex to 1) organize genes into the developmental cellular and molecular systems within which they operate, 2) identify neurodevelopmental processes associated with polygenic risk for SCZ and ASD across the allelic frequency spectrum, and 3) elucidate pathways and individual genes through which 22q11.2 copy number variants may confer risk for each disorder. RESULTS: Polygenic risk for SCZ and ASD converged on partially overlapping neurodevelopmental modules involved in synaptic function and transcriptional regulation, with ASD risk variants additionally enriched for modules involved in neuronal differentiation during fetal development. The 22q11.2 locus formed a large protein network during development that disproportionately affected SCZ-associated and ASD-associated neurodevelopmental modules, including loading highly onto synaptic and gene regulatory pathways. SEPT5, PI4KA, and SNAP29 genes are candidate drivers of 22q11.2 synaptic pathology relevant to SCZ and ASD, and DGCR8 and HIRA are candidate drivers of disease-relevant alterations in gene regulation. CONCLUSIONS: This approach offers a powerful framework to identify neurodevelopmental processes affected by diverse risk variants for SCZ and ASD and elucidate mechanisms through which highly penetrant, multigene copy number variants contribute to disease risk.