The publication data currently available has been vetted by Vanderbilt faculty, staff, administrators and trainees. The data itself is retrieved directly from NCBI's PubMed and is automatically updated on a weekly basis to ensure accuracy and completeness.
If you have any questions or comments, please contact us.
BACKGROUND - Late-life depression (LLD) is associated with a fragile antidepressant response and high recurrence risk. This study examined what measures predict recurrence in remitted LLD.
METHODS - Individuals of age 60 years or older with a Diagnostic and Statistical Manual - IV (DSM-IV) diagnosis of major depressive disorder were enrolled in the neurocognitive outcomes of depression in the elderly study. Participants received manualized antidepressant treatment and were followed longitudinally for an average of 5 years. Study analyses included participants who remitted. Measures included demographic and clinical measures, medical comorbidity, disability, life stress, social support, and neuropsychological testing. A subset underwent structural magnetic resonance imaging (MRI).
RESULTS - Of 241 remitted elders, approximately over 4 years, 137 (56.8%) experienced recurrence and 104 (43.2%) maintained remission. In the final model, greater recurrence risk was associated with female sex (hazard ratio [HR] = 1.536; confidence interval [CI] = 1.027-2.297), younger age of onset (HR = 0.990; CI = 0.981-0.999), higher perceived stress (HR = 1.121; CI = 1.022-1.229), disability (HR = 1.060; CI = 1.005-1.119), and less support with activities (HR = 0.885; CI = 0.812-0.963). Recurrence risk was also associated with higher Montgomery-Asberg Depression Rating Scale (MADRS) scores prior to censoring (HR = 1.081; CI = 1.033-1.131) and baseline symptoms of suicidal thoughts by MADRS (HR = 1.175; CI = 1.002-1.377) and sadness by Center for Epidemiologic Studies-Depression (HR = 1.302; CI, 1.080-1.569). Sex, age of onset, and suicidal thoughts were no longer associated with recurrence in a model incorporating report of multiple prior episodes (HR = 2.107; CI = 1.252-3.548). Neither neuropsychological test performance nor MRI measures of aging pathology were associated with recurrence.
CONCLUSIONS - Over half of the depressed elders who remitted experienced recurrence, mostly within 2 years. Multiple clinical and environmental measures predict recurrence risk. Work is needed to develop instruments that stratify risk.
© 2018 Wiley Periodicals, Inc.
OBJECTIVE - Hepatorenal Syndrome (HRS) is a devastating form of acute kidney injury (AKI) in advanced liver disease patients with high morbidity and mortality, but phenotyping algorithms have not yet been developed using large electronic health record (EHR) databases. We evaluated and compared multiple phenotyping methods to achieve an accurate algorithm for HRS identification.
MATERIALS AND METHODS - A national retrospective cohort of patients with cirrhosis and AKI admitted to 124 Veterans Affairs hospitals was assembled from electronic health record data collected from 2005 to 2013. AKI was defined by the Kidney Disease: Improving Global Outcomes criteria. Five hundred and four hospitalizations were selected for manual chart review and served as the gold standard. Electronic Health Record based predictors were identified using structured and free text clinical data, subjected through NLP from the clinical Text Analysis Knowledge Extraction System. We explored several dimension reduction techniques for the NLP data, including newer high-throughput phenotyping and word embedding methods, and ascertained their effectiveness in identifying the phenotype without structured predictor variables. With the combined structured and NLP variables, we analyzed five phenotyping algorithms: penalized logistic regression, naïve Bayes, support vector machines, random forest, and gradient boosting. Calibration and discrimination metrics were calculated using 100 bootstrap iterations. In the final model, we report odds ratios and 95% confidence intervals.
RESULTS - The area under the receiver operating characteristic curve (AUC) for the different models ranged from 0.73 to 0.93; with penalized logistic regression having the best discriminatory performance. Calibration for logistic regression was modest, but gradient boosting and support vector machines were superior. NLP identified 6985 variables; a priori variable selection performed similarly to dimensionality reduction using high-throughput phenotyping and semantic similarity informed clustering (AUC of 0.81 - 0.82).
CONCLUSION - This study demonstrated improved phenotyping of a challenging AKI etiology, HRS, over ICD-9 coding. We also compared performance among multiple approaches to EHR-derived phenotyping, and found similar results between methods. Lastly, we showed that automated NLP dimension reduction is viable for acute illness.
Copyright © 2018 Elsevier Inc. All rights reserved.
Computational protein design has been successful in modeling fixed backbone proteins in a single conformation. However, when modeling large ensembles of flexible proteins, current methods in protein design have been insufficient. Large barriers in the energy landscape are difficult to traverse while redesigning a protein sequence, and as a result current design methods only sample a fraction of available sequence space. We propose a new computational approach that combines traditional structure-based modeling using the Rosetta software suite with machine learning and integer linear programming to overcome limitations in the Rosetta sampling methods. We demonstrate the effectiveness of this method, which we call BROAD, by benchmarking the performance on increasing predicted breadth of anti-HIV antibodies. We use this novel method to increase predicted breadth of naturally-occurring antibody VRC23 against a panel of 180 divergent HIV viral strains and achieve 100% predicted binding against the panel. In addition, we compare the performance of this method to state-of-the-art multistate design in Rosetta and show that we can outperform the existing method significantly. We further demonstrate that sequences recovered by this method recover known binding motifs of broadly neutralizing anti-HIV antibodies. Finally, our approach is general and can be extended easily to other protein systems. Although our modeled antibodies were not tested in vitro, we predict that these variants would have greatly increased breadth compared to the wild-type antibody.
Extent of response to neoadjuvant chemotherapy, tumor size, and patient age are important prognostic variables for patients with osteosarcoma, but applying information from these continuous variables in survival models is difficult. Dichotomization is usually inappropriate and alternative statistical techniques should be considered instead. Nonlinear multivariable regression methods (restricted cubic splines and fractional polynomials) were applied to data from the National Cancer Database to model continuous prognostic factors for overall survival from localized, high-grade osteosarcoma of the appendicular and nonspinal skeleton following neoadjuvant chemotherapy and surgical resection (N=2493). The assumption that log hazard ratios were linear in relation to these continuous prognostic factors was tested using likelihood ratio tests of model deviance and Wald tests of spline coefficients. Log hazard ratios for increasing patient age were linear over the range of 4 to 80 years, but showed evidence for variation in the coefficient over elapsed follow-up time. Tumor size also showed a linear relationship with log hazard over the range of 1 to 30 cm. Hazard ratios for chemotherapy effect profoundly deviated from log-linear (P<0.004), with significantly decreased hazard for death from baseline for patients with ≥90% tumor necrosis (hazard ratio, 0.32; 95% confidence interval, 0.20-0.52; P<0.0001). Important implications of these results include: (1) ≥90% tumor necrosis defines good chemotherapy response in a clinically useful manner; (2) staging osteosarcoma by dichotomizing tumor size is inappropriate; and (3) patient age can be modeled as a linear effect on the log hazard ratio in prognostic models with the caveat that risk may change over duration of the analysis.
BACKGROUND - The objective of this study is to evaluate use of the American College of Surgeons (ACS) National Surgical Quality Improvement Program (NSQIP) online risk calculator for estimating common outcomes after operations for gallbladder cancer and extrahepatic cholangiocarcinoma.
METHODS - Subjects from the United States Extrahepatic Biliary Malignancy Consortium (USE-BMC) who underwent operation between January 1, 2000 and December 31, 2014 at 10 academic medical centers were included in this study. Calculator estimates of risk were compared to actual outcomes.
RESULTS - The majority of patients underwent partial or major hepatectomy, Whipple procedures or extrahepatic bile duct resection. For the entire cohort, c-statistics for surgical site infection (0.635), reoperation (0.680) and readmission (0.565) were less than 0.7. The c-statistic for death was 0.740. For all outcomes the actual proportion of patients experiencing an event was much higher than the median predicted risk of that event. Similarly, the group of patients who experienced an outcome did have higher median predicted risk than those who did not.
CONCLUSIONS - The ACS NSQIP risk calculator is easy to use but requires further modifications to more accurately estimate outcomes for some patient populations and operations for which validation studies show suboptimal performance.
Copyright © 2017 International Hepato-Pancreato-Biliary Association Inc. Published by Elsevier Ltd. All rights reserved.
Objective - Predictive analytics create opportunities to incorporate personalized risk estimates into clinical decision support. Models must be well calibrated to support decision-making, yet calibration deteriorates over time. This study explored the influence of modeling methods on performance drift and connected observed drift with data shifts in the patient population.
Materials and Methods - Using 2003 admissions to Department of Veterans Affairs hospitals nationwide, we developed 7 parallel models for hospital-acquired acute kidney injury using common regression and machine learning methods, validating each over 9 subsequent years.
Results - Discrimination was maintained for all models. Calibration declined as all models increasingly overpredicted risk. However, the random forest and neural network models maintained calibration across ranges of probability, capturing more admissions than did the regression models. The magnitude of overprediction increased over time for the regression models while remaining stable and small for the machine learning models. Changes in the rate of acute kidney injury were strongly linked to increasing overprediction, while changes in predictor-outcome associations corresponded with diverging patterns of calibration drift across methods.
Conclusions - Efficient and effective updating protocols will be essential for maintaining accuracy of, user confidence in, and safety of personalized risk predictions to support decision-making. Model updating protocols should be tailored to account for variations in calibration drift across methods and respond to periods of rapid performance drift rather than be limited to regularly scheduled annual or biannual intervals.
© The Author 2017. Published by Oxford University Press on behalf of the American Medical Informatics Association. All rights reserved. For Permissions, please email: firstname.lastname@example.org
OBJECTIVE - To characterize in vivo signatures of pathological diagnosis in a large cohort of patients with primary progressive aphasia (PPA) variants defined by current diagnostic classification.
METHODS - Extensive clinical, cognitive, neuroimaging, and neuropathological data were collected from 69 patients with sporadic PPA, divided into 29 semantic (svPPA), 25 nonfluent (nfvPPA), 11 logopenic (lvPPA), and 4 mixed PPA. Patterns of gray matter (GM) and white matter (WM) atrophy at presentation were assessed and tested as predictors of pathological diagnosis using support vector machine (SVM) algorithms.
RESULTS - A clinical diagnosis of PPA was associated with frontotemporal lobar degeneration (FTLD) with transactive response DNA-binding protein (TDP) inclusions in 40.5%, FTLD-tau in 40.5%, and Alzheimer disease (AD) pathology in 19% of cases. Each variant was associated with 1 typical pathology; 24 of 29 (83%) svPPA showed FTLD-TDP type C, 22 of 25 (88%) nfvPPA showed FTLD-tau, and all 11 lvPPA had AD. Within FTLD-tau, 4R-tau pathology was commonly associated with nfvPPA, whereas Pick disease was observed in a minority of subjects across all variants except for lvPPA. Compared with pathologically typical cases, svPPA-tau showed significant extrapyramidal signs, greater executive impairment, and severe striatal and frontal GM and WM atrophy. nfvPPA-TDP patients lacked general motor symptoms or significant WM atrophy. Combining GM and WM volumes, SVM analysis showed 92.7% accuracy to distinguish FTLD-tau and FTLD-TDP pathologies across variants.
INTERPRETATION - Each PPA clinical variant is associated with a typical and most frequent cognitive, neuroimaging, and neuropathological profile. Specific clinical and early anatomical features may suggest rare and atypical pathological diagnosis in vivo. Ann Neurol 2017;81:430-443.
© 2017 American Neurological Association.