A machine learning model on Real World Data for predicting progression to Acute Respiratory Distress Syndrome (ARDS) among COVID-19 patients.

INTRODUCTION: Identifying COVID-19 patients that are most likely to progress to a severe infection is crucial for optimizing care management and increasing the likelihood of survival. This study presents a machine learning model that predicts severe cases of COVID-19, defined as the presence of Acute Respiratory Distress Syndrome (ARDS) and highlights the different risk factors that play a significant role in disease progression. METHODS: A cohort composed of 289,351 patients diagnosed with COVID-19 in April 2020 was created using US administrative claims data from Oct 2015 to Jul 2020. For each patient, information about 817 diagnoses, were collected from the medical history ahead of COVID-19 infection. The primary outcome of the study was the presence of ARDS in the 4 months following COVID-19 infection. The study cohort was randomly split into training set used for model development, test set for model evaluation and validation set for real-world performance estimation. RESULTS: We analyzed three machine learning classifiers to predict the presence of ARDS. Among the algorithms considered, a Gradient Boosting Decision Tree had the highest performance with an AUC of 0.695 (95% CI, 0.679-0.709) and an AUPRC of 0.0730 (95% CI, 0.0676 - 0.0823), showing a 40% performance increase in performance against a baseline classifier. A panel of five clinicians was also used to compare the predictive ability of the model to that of clinical experts. The comparison indicated that our model is on par or outperforms predictions made by the clinicians, both in terms of precision and recall. CONCLUSION: This study presents a machine learning model that uses patient claims history to predict ARDS. The risk factors used by the model to perform its predictions have been extensively linked to the severity of the COVID-19 in the specialized literature. The most contributing diagnosis can be easily retrieved in the patient clinical history and can be used for an early screening of infected patients. Overall, the proposed model could be a promising tool to deploy in a healthcare setting to facilitate and optimize the care of COVID-19 patients.

Identification of CNGB1 as a Predictor of Response to Neoadjuvant Chemotherapy in Muscle-Invasive Bladder Cancer.

Cisplatin-based neoadjuvant chemotherapy (NAC) is recommended prior to radical cystectomy for muscle-invasive bladder cancer (MIBC) patients. Despite a 5-10% survival benefit, some patients do not respond and experience substantial toxicity and delay in surgery. To date, there are no clinically approved biomarkers predictive of response to NAC and their identification is urgently required for more precise delivery of care. To address this issue, a multi-methods analysis approach of machine learning and differential gene expression analysis was undertaken on a cohort of 30 MIBC cases highly selected for an exquisitely strong response to NAC or marked resistance and/or progression (discovery cohort). RGIFE (ranked guided iterative feature elimination) machine learning algorithm, previously demonstrated to have the ability to select biomarkers with high predictive power, identified a 9-gene signature (CNGB1, GGH, HIST1H4F, IDO1, KIF5A, MRPL4, NCDN, PRRT3, SLC35B3) able to select responders from non-responders with 100% predictive accuracy. This novel signature correlated with overall survival in meta-analysis performed using published NAC treated-MIBC microarray data (validation cohort 1, n = 26, Log rank test, p = 0.02). Corroboration with differential gene expression analysis revealed cyclic nucleotide-gated channel, CNGB1, as the top ranked upregulated gene in non-responders to NAC. A higher CNGB1 immunostaining score was seen in non-responders in tissue microarray analysis of the discovery cohort (n = 30, p = 0.02). Kaplan-Meier analysis of a further cohort of MIBC patients (validation cohort 2, n = 99) demonstrated that a high level of CNGB1 expression associated with shorter cancer specific survival (p < 0.001). Finally, in vitro studies showed siRNA-mediated CNGB1 knockdown enhanced cisplatin sensitivity of MIBC cell lines, J82 and 253JB-V. Overall, these data reveal a novel signature gene set and CNGB1 as a simpler proxy as a promising biomarker to predict chemoresponsiveness of MIBC patients.

RGIFE: a ranked guided iterative feature elimination heuristic for the identification of biomarkers.

BACKGROUND: Current -omics technologies are able to sense the state of a biological sample in a very wide variety of ways. Given the high dimensionality that typically characterises these data, relevant knowledge is often hidden and hard to identify. Machine learning methods, and particularly feature selection algorithms, have proven very effective over the years at identifying small but relevant subsets of variables from a variety of application domains, including -omics data. Many methods exist with varying trade-off between the size of the identified variable subsets and the predictive power of such subsets. In this paper we focus on an heuristic for the identification of biomarkers called RGIFE: Rank Guided Iterative Feature Elimination. RGIFE is guided in its biomarker identification process by the information extracted from machine learning models and incorporates several mechanisms to ensure that it creates minimal and highly predictive features sets. RESULTS: We compare RGIFE against five well-known feature selection algorithms using both synthetic and real (cancer-related transcriptomics) datasets. First, we assess the ability of the methods to identify relevant and highly predictive features. Then, using a prostate cancer dataset as a case study, we look at the biological relevance of the identified biomarkers. CONCLUSIONS: We propose RGIFE, a heuristic for the inference of reduced panels of biomarkers that obtains similar predictive performance to widely adopted feature selection methods while selecting significantly fewer feature. Furthermore, focusing on the case study, we show the higher biological relevance of the biomarkers selected by our approach. The RGIFE source code is available at: http://ico2s.org/software/rgife.html .

Functional networks inference from rule-based machine learning models.

BACKGROUND: Functional networks play an important role in the analysis of biological processes and systems. The inference of these networks from high-throughput (-omics) data is an area of intense research. So far, the similarity-based inference paradigm (e.g. gene co-expression) has been the most popular approach. It assumes a functional relationship between genes which are expressed at similar levels across different samples. An alternative to this paradigm is the inference of relationships from the structure of machine learning models. These models are able to capture complex relationships between variables, that often are different/complementary to the similarity-based methods. RESULTS: We propose a protocol to infer functional networks from machine learning models, called FuNeL. It assumes, that genes used together within a rule-based machine learning model to classify the samples, might also be functionally related at a biological level. The protocol is first tested on synthetic datasets and then evaluated on a test suite of 8 real-world datasets related to human cancer. The networks inferred from the real-world data are compared against gene co-expression networks of equal size, generated with 3 different methods. The comparison is performed from two different points of view. We analyse the enriched biological terms in the set of network nodes and the relationships between known disease-associated genes in a context of the network topology. The comparison confirms both the biological relevance and the complementary character of the knowledge captured by the FuNeL networks in relation to similarity-based methods and demonstrates its potential to identify known disease associations as core elements of the network. Finally, using a prostate cancer dataset as a case study, we confirm that the biological knowledge captured by our method is relevant to the disease and consistent with the specialised literature and with an independent dataset not used in the inference process. AVAILABILITY: The implementation of our network inference protocol is available at: http://ico2s.org/software/funel.html.

Hard Data Analytics Problems Make for Better Data Analysis Algorithms: Bioinformatics as an Example.

Data mining and knowledge discovery techniques have greatly progressed in the last decade. They are now able to handle larger and larger datasets, process heterogeneous information, integrate complex metadata, and extract and visualize new knowledge. Often these advances were driven by new challenges arising from real-world domains, with biology and biotechnology a prime source of diverse and hard (e.g., high volume, high throughput, high variety, and high noise) data analytics problems. The aim of this article is to show the broad spectrum of data mining tasks and challenges present in biological data, and how these challenges have driven us over the years to design new data mining and knowledge discovery procedures for biodata. This is illustrated with the help of two kinds of case studies. The first kind is focused on the field of protein structure prediction, where we have contributed in several areas: by designing, through regression, functions that can distinguish between good and bad models of a protein's predicted structure; by creating new measures to characterize aspects of a protein's structure associated with individual positions in a protein's sequence, measures containing information that might be useful for protein structure prediction; and by creating accurate estimators of these structural aspects. The second kind of case study is focused on omics data analytics, a class of biological data characterized for having extremely high dimensionalities. Our methods were able not only to generate very accurate classification models, but also to discover new biological knowledge that was later ratified by experimentalists. Finally, we describe several strategies to tightly integrate knowledge extraction and data mining in order to create a new class of biodata mining algorithms that can natively embrace the complexity of biological data, efficiently generate accurate information in the form of classification/regression models, and extract valuable new knowledge. Thus, a complete data-to-information-to-knowledge pipeline is presented.

Nicotine dependence and psychological distress: outcomes and clinical implications in smoking cessation.

Nicotine dependence is characteristically a chronic and relapsing disease. Although 75%-85% of smokers would like to quit, and one-third make at least three serious lifetime attempts, less than 50% of smokers succeed in stopping before the age of 60. Relevant and complex factors contributing to sustained cigarette consumption, and strongly implicated in the clinical management of smokers, are the level of nicotine dependence and psychological distress. In this review of the literature, these two factors will be examined in detail to show how they may affect smoking cessation outcome and to encourage clinicians to assess patients so they can offer tailored support in quitting smoking.