Feature selection with the R package MXM

Physical performance strongly predicts all-cause mortality risk in a real-world population of older diabetic patients: machine learning approach for mortality risk stratification

Background

Prognostic risk stratification in older adults with type 2 diabetes (T2D) is important for guiding decisions concerning advance care planning.

Materials and methods

A retrospective longitudinal study was conducted in a real-world sample of older diabetic patients afferent to the outpatient facilities of the Diabetology Unit of the IRCCS INRCA Hospital of Ancona (Italy). A total of 1,001 T2D patients aged more than 70 years were consecutively evaluated by a multidimensional geriatric assessment, including physical performance evaluated using the Short Physical Performance Battery (SPPB). The mortality was assessed during a 5-year follow-up. We used the automatic machine-learning (AutoML) JADBio platform to identify parsimonious mathematical models for risk stratification.

Results

Of 977 subjects included in the T2D cohort, the mean age was 76.5 (SD: 4.5) years and 454 (46.5%) were men. The mean follow-up time was 53.3 (SD:15.8) months, and 209 (21.4%) patients died by the end of the follow-up. The JADBio AutoML final model included age, sex, SPPB, chronic kidney disease, myocardial ischemia, peripheral artery disease, neuropathy, and myocardial infarction. The bootstrap-corrected concordance index (c-index) for the final model was 0.726 (95% CI: 0.687-0.763) with SPPB ranked as the most important predictor. Based on the penalized Cox regression model, the risk of death per unit of time for a subject with an SPPB score lower than five points was 3.35 times that for a subject with a score higher than eight points (P-value <0.001).

Conclusion

Assessment of physical performance needs to be implemented in clinical practice for risk stratification of T2D older patients.

Integration of Computational Pipeline to Streamline Efficacious Drug Nomination and Biomarker Discovery in Glioblastoma

Glioblastoma multiforme (GBM) is the deadliest, most heterogeneous, and most common brain cancer in adults. Not only is there an urgent need to identify efficacious therapeutics, but there is also a great need to pair these therapeutics with biomarkers that can help tailor treatment to the right patient populations. We built patient drug response models by integrating patient tumor transcriptome data with high-throughput cell line drug screening data as well as Bayesian networks to infer relationships between patient gene expression and drug response. Through these discovery pipelines, we identified agents of interest for GBM to be effective across five independent patient cohorts and in a mouse avatar model: among them are a number of MEK inhibitors (MEKis). We also predicted phosphoglycerate dehydrogenase enzyme (PHGDH) gene expression levels to be causally associated with MEKi efficacy, where knockdown of this gene increased tumor sensitivity to MEKi and overexpression led to MEKi resistance. Overall, our work demonstrated the power of integrating computational approaches. In doing so, we quickly nominated several drugs with varying known mechanisms of action that can efficaciously target GBM. By simultaneously identifying biomarkers with these drugs, we also provide tools to select the right patient populations for subsequent evaluation.

The FEDHC Bayesian Network Learning Algorithm

The paper proposes a new hybrid Bayesian network learning algorithm, termed Forward Early Dropping Hill Climbing (FEDHC), devised to work with either continuous or categorical variables. Further, the paper manifests that the only implementation of MMHC in the statistical software R is prohibitively expensive, and a new implementation is offered. Further, specifically for the case of continuous data, a robust to outliers version of FEDHC, which can be adopted by other BN learning algorithms, is proposed. The FEDHC is tested via Monte Carlo simulations that distinctly show that it is computationally efficient, and that it produces Bayesian networks of similar to, or of higher accuracy than MMHC and PCHC. Finally, an application of FEDHC, PCHC and MMHC algorithms to real data, from the field of economics, is demonstrated using the statistical software R.

The γ-OMP Algorithm for Feature Selection With Application to Gene Expression Data

Feature selection for predictive analytics is the problem of identifying a minimal-size subset of features that is maximally predictive of an outcome of interest. To apply to molecular data, feature selection algorithms need to be scalable to tens of thousands of features. In this paper, we propose γ-OMP, a generalisation of the highly-scalable Orthogonal Matching Pursuit feature selection algorithm. γ-OMP can handle (a)various types of outcomes, such as continuous, binary, nominal, time-to-event, (b)discrete (categorical)features, (c)different statistical-based stopping criteria, (d)several predictive models (e.g., linear or logistic regression), (e)various types of residuals, and (f)different types of association. We compare γ-OMP against LASSO, a prototypical, widely used algorithm for high-dimensional data. On both simulated data and several real gene expression datasets, γ-OMP is on par, or outperforms LASSO in binary classification (case-control data), regression (quantified outcomes), and time-to-event data (censored survival times). γ-OMP is based on simple statistical ideas, it is easy to implement and to extend, and our extensive evaluation shows that it is also effective in bioinformatics analysis settings.

Forecasting military mental health in a complete sample of Danish military personnel deployed between 1992-2013

OBJECTIVE

Mental health problems (MHP) are a relatively common consequence of deployment to war zones. Early identification of those at risk of post-deployment MHP would improve prevention efforts. However, screening instruments based on linear models have not been successful. Machine learning (ML) has shown promise for providing the methodological frame for better prognostic models.

METHODS

The study population was all Danish military personnel deployed for the first time between January 1, 1992 and December 31, 2013. From extensive registry data, 21 pre- or at-deployment predictors comprising early adversity, social, clinical and demographic variables were used to predict psychiatric contacts (psychiatric diagnosis and/or use of psychotropic medicine) occurring within 6.5 years after homecoming. Four supervised ML methods (penalized logistic regression, random forests, support vector machines and gradient boosting machines) were compared in ability to classify those with high risk of post-deployment MHP and those without.

RESULTS

Of 27594 subjects, 2175 (8%) had a psychiatric contact. All four ML methods applied had performances well above chance (Area under the Receiver-operating Curve 0.62-0.68). Positive predictive value for the best model was 0.16. A range of pre-deployment factors were found to be predictive of post-deployment psychiatric contacts.

CONCLUSIONS

ML methods can be useful in early identification of soldiers with high risk of MPH in the years following their first deployment. However, performances were modest and positive predictive values were low, limiting the applicability of the models for pre-deployment screening. Future studies should include neurobiological data and deployment experiences to increase accuracy of the models.

Current Achievements and Applications of Transcriptomics in Personalized Cancer Medicine

Over the last decades, transcriptome profiling emerged as one of the most powerful approaches in oncology, providing prognostic and predictive utility for cancer management. The development of novel technologies, such as revolutionary next-generation sequencing, enables the identification of cancer biomarkers, gene signatures, and their aberrant expression affecting oncogenesis, as well as the discovery of molecular targets for anticancer therapies. Transcriptomics contribute to a change in the holistic understanding of cancer, from histopathological and organic to molecular classifications, opening a more personalized perspective for tumor diagnostics and therapy. The further advancement on transcriptome profiling may allow standardization and cost reduction of its analysis, which will be the next step for transcriptomics to become a canon of contemporary cancer medicine.

Applicability of an Automated Model and Parameter Selection in the Prediction of Screening-Level PTSD in Danish Soldiers Following Deployment: Development Study of Transferable Predictive Models Using Automated Machine Learning

BACKGROUND

Posttraumatic stress disorder (PTSD) is a relatively common consequence of deployment to war zones. Early postdeployment screening with the aim of identifying those at risk for PTSD in the years following deployment will help deliver interventions to those in need but have so far proved unsuccessful.

OBJECTIVE

This study aimed to test the applicability of automated model selection and the ability of automated machine learning prediction models to transfer across cohorts and predict screening-level PTSD 2.5 years and 6.5 years after deployment.

METHODS

Automated machine learning was applied to data routinely collected 6-8 months after return from deployment from 3 different cohorts of Danish soldiers deployed to Afghanistan in 2009 (cohort 1, N=287 or N=261 depending on the timing of the outcome assessment), 2010 (cohort 2, N=352), and 2013 (cohort 3, N=232).

RESULTS

Models transferred well between cohorts. For screening-level PTSD 2.5 and 6.5 years after deployment, random forest models provided the highest accuracy as measured by area under the receiver operating characteristic curve (AUC): 2.5 years, AUC=0.77, 95% CI 0.71-0.83; 6.5 years, AUC=0.78, 95% CI 0.73-0.83. Linear models performed equally well. Military rank, hyperarousal symptoms, and total level of PTSD symptoms were highly predictive.

CONCLUSIONS

Automated machine learning provided validated models that can be readily implemented in future deployment cohorts in the Danish Defense with the aim of targeting postdeployment support interventions to those at highest risk for developing PTSD, provided the cohorts are deployed on similar missions.

Identification of the Prognosis-Related lncRNAs and Genes in Gastric Cancer

Gastric cancer is a common malignant tumor with high occurrence and recurrence and is the leading cause of death worldwide. However, the prognostic value of protein-coding and non-coding RNAs in stage III gastric cancer has not been systematically analyzed. In this study, using TCGA data, we identified 585 long noncoding RNAs (lncRNAs) and 927 protein-coding genes (PCGs) correlated with the overall survival rate of gastric cancer. Functional enrichment analysis revealed that the prognostic genes positively correlated with death rates were enriched in pathways, including gap junction, focal adhesion, cell adhesion molecules (CAMs), and neuroactive ligand-receptor interaction, that are involved in the tumor microenvironment and cell-cell communications, suggesting that their dysregulation may promote the tumor progression. To evaluate the performance of the prognostic genes in risk prediction, we built three multivariable Cox models based on prognostic genes selected from the prognostic PCGs and lncRNAs. The performance of the three models based on features from only PCGs or lncRNAs or from all prognostic genes were systematically compared, which revealed that the features selected from all the prognostic genes showed higher performance than the features selected only from lncRNAs or PCGs. Furthermore, the multivariable Cox regression analysis revealed that the stratification with the highest performance was an independent prognostic factor in stage III gastric cancer. In addition, we explored the underlying mechanism of the prognostic lncRNAs in the Cox model by predicting the lncRNA and protein interaction. Specifically, CTD-2218G20.2 was predicted to interact with PSG4, PSG5, and PSG7, which could also interact with cancer-related proteins, including KISS1, TIMP2, MMP11, IGFBP1, EGFR, and CDKN1C, suggesting that CTD-2218G20.2 might participate in the cancer progression via these cancer-related proteins. In summary, the systematic analysis of the prognostic lncRNAs and PCGs was of great importance to the understanding of the progression of stage III gastric cancer.