Machine learning in critical care: state-of-the-art and a sepsis case study

BACKGROUND

Like other scientific fields, such as cosmology, high-energy physics, or even the life sciences, medicine and healthcare face the challenge of an extremely quick transformation into data-driven sciences. This challenge entails the daunting task of extracting usable knowledge from these data using algorithmic methods. In the medical context this may for instance realized through the design of medical decision support systems for diagnosis, prognosis and patient management. The intensive care unit (ICU), and by extension the whole area of critical care, is becoming one of the most data-driven clinical environments.

RESULTS

The increasing availability of complex and heterogeneous data at the point of patient attention in critical care environments makes the development of fresh approaches to data analysis almost compulsory. Computational Intelligence (CI) and Machine Learning (ML) methods can provide such approaches and have already shown their usefulness in addressing problems in this context. The current study has a dual goal: it is first a review of the state-of-the-art on the use and application of such methods in the field of critical care. Such review is presented from the viewpoint of the different subfields of critical care, but also from the viewpoint of the different available ML and CI techniques. The second goal is presenting a collection of results that illustrate the breath of possibilities opened by ML and CI methods using a single problem, the investigation of septic shock at the ICU.

CONCLUSION

We have presented a structured state-of-the-art that illustrates the broad-ranging ways in which ML and CI methods can make a difference in problems affecting the manifold areas of critical care. The potential of ML and CI has been illustrated in detail through an example concerning the sepsis pathology. The new definitions of sepsis and the relevance of using the systemic inflammatory response syndrome (SIRS) in its diagnosis have been considered. Conditional independence models have been used to address this problem, showing that SIRS depends on both organ dysfunction measured through the Sequential Organ Failure (SOFA) score and the ICU outcome, thus concluding that SIRS should still be considered in the study of the pathophysiology of Sepsis. Current assessment of the risk of dead at the ICU lacks specificity. ML and CI techniques are shown to improve the assessment using both indicators already in place and other clinical variables that are routinely measured. Kernel methods in particular are shown to provide the best performance balance while being amenable to representation through graphical models, which increases their interpretability and, with it, their likelihood to be accepted in medical practice.

Prediction of Survival in Thyroid Cancer Using Data Mining Technique

Cancer is the second leading cause of death after cardiovascular diseases in the world. Health professionals are seeking ways for suitable treatment and quality of care in these groups of patients. Survival prediction is important for both physicians and patients in order to choose the best way of management. Artificial Neural Network (ANN) is one of the most efficient data mining methods. This technique is able to evaluate the relationship between different variables spontaneously without any prevalent data. In our study ANN and Logistic Regression were used to predict survival in thyroid cancer and compare these results. SEER (Surveillance, Epidemiology and End Result) data were got from SEER site1. Effective features in thyroid cancer have been selected based on supervision by radiation oncologists and evidence. After data pruning 7706 samples were studied with 16 attributes. Multi Layer Prediction (MLP) was used as the chosen neural network and survival was predicted for 1-, 3- and 5-years. Accuracy, sensitivity and specificity were parameters to evaluate the model. The results of MLP and Logistic Regression models for one year are defined as for 1-year (92.9%, 92.8, 93%), (81.2%, 88.9%, 72.5%), for 3-year as (85.1%, 87.8%, 82.8%), (88.6%, 90.2%, 87.2%) and for 5-year as (86.8%, 96%, 74.3%), (90.7%, 95.9%, 83.7) respectively. According to our results ANN could efficiently represent a suitable method of survival prediction in thyroid cancer patients and the results were comparable with statistical models.

Bioinformatics and Nanotechnologies: Nanomedicine

In this chapter we focus on the bioinformatics strategies for translating genome-wide expression analyses into clinically useful cancer markers with a specific focus on breast cancer with a perspective on new diagnostic device tools coming from the field of nanobiotechnology and the challenges related to high-throughput data integration, analysis, and assessment from multiple sources.

Great progress in the development of molecular biology techniques has been seen since the discovery of the structure of deoxyribonucleic acid (DNA) and the implementation of a polymerase chain reaction (PCR) method. This started a new era of research on the structure of nucleic acids molecules, the development of new analytical tools, and DNA-based analyses that allowed the sequencing of the human genome, the completion of which has led to intensified efforts toward comprehensive analysis of mammalian cell struc ture and metabolism in order to better understand the mechanisms that regulate normal cell behavior and identify the gene alterations responsible for a broad spectrum of human diseases, such as cancer, diabetes, cardiovascular diseases, neurodegenerative disorders, and others.

A novel semi-supervised methodology for extracting tumor type-specific MRS sources in human brain data

Background

The clinical investigation of human brain tumors often starts with a non-invasive imaging study, providing information about the tumor extent and location, but little insight into the biochemistry of the analyzed tissue. Magnetic Resonance Spectroscopy can complement imaging by supplying a metabolic fingerprint of the tissue. This study analyzes single-voxel magnetic resonance spectra, which represent signal information in the frequency domain. Given that a single voxel may contain a heterogeneous mix of tissues, signal source identification is a relevant challenge for the problem of tumor type classification from the spectroscopic signal.

Methodology/Principal Findings

Non-negative matrix factorization techniques have recently shown their potential for the identification of meaningful sources from brain tissue spectroscopy data. In this study, we use a convex variant of these methods that is capable of handling negatively-valued data and generating sources that can be interpreted as tumor class prototypes. A novel approach to convex non-negative matrix factorization is proposed, in which prior knowledge about class information is utilized in model optimization. Class-specific information is integrated into this semi-supervised process by setting the metric of a latent variable space where the matrix factorization is carried out. The reported experimental study comprises 196 cases from different tumor types drawn from two international, multi-center databases. The results indicate that the proposed approach outperforms a purely unsupervised process by achieving near perfect correlation of the extracted sources with the mean spectra of the tumor types. It also improves tissue type classification.

Conclusions/Significance

We show that source extraction by unsupervised matrix factorization benefits from the integration of the available class information, so operating in a semi-supervised learning manner, for discriminative source identification and brain tumor labeling from single-voxel spectroscopy data. We are confident that the proposed methodology has wider applicability for biomedical signal processing.

Kernel Generative Topographic Mapping of Protein Sequences

The world of pharmacology is becoming increasingly dependent on the advances in the fields of genomics and proteomics. The –omics sciences bring about the challenge of how to deal with the large amounts of complex data they generate from an intelligent data analysis perspective. In this chapter, the authors focus on the analysis of a specific type of proteins, the G protein-coupled receptors, which are the target for over 15% of current drugs. They describe a kernel method of the manifold learning family for the analysis of protein amino acid symbolic sequences. This method sheds light on the structure of protein subfamilies, while providing an intuitive visualization of such structure.

Robust discrimination of glioblastomas from metastatic brain tumors on the basis of single-voxel (1)H MRS

This article investigates methods for the accurate and robust differentiation of metastases from glioblastomas on the basis of single-voxel (1)H MRS information. Single-voxel (1)H MR spectra from a total of 109 patients (78 glioblastomas and 31 metastases) from the multicenter, international INTERPRET database, plus a test set of 40 patients (30 glioblastomas and 10 metastases) from three different centers in the Barcelona (Spain) metropolitan area, were analyzed using a robust method for feature (spectral frequency) selection coupled with a linear-in-the-parameters single-layer perceptron classifier. For the test set, a parsimonious selection of five frequencies yielded an area under the receiver operating characteristic curve of 0.86, and an area under the convex hull of the receiver operating characteristic curve of 0.91. Moreover, these accurate results for the discrimination between glioblastomas and metastases were obtained using a small number of frequencies that are amenable to metabolic interpretation, which should ease their use as diagnostic markers. Importantly, the prediction can be expressed as a simple formula based on a linear combination of these frequencies. As a result, new cases could be straightforwardly predicted by integrating this formula into a computer-based medical decision support system. This work also shows that the combination of spectra acquired at different TEs (short TE, 20-32 ms; long TE, 135-144 ms) is key to the successful discrimination between glioblastomas and metastases from single-voxel (1)H MRS.

Non-negative matrix factorisation methods for the spectral decomposition of MRS data from human brain tumours

BACKGROUND

In-vivo single voxel proton magnetic resonance spectroscopy (SV 1H-MRS), coupled with supervised pattern recognition (PR) methods, has been widely used in clinical studies of discrimination of brain tumour types and follow-up of patients bearing abnormal brain masses. SV 1H-MRS provides useful biochemical information about the metabolic state of tumours and can be performed at short (< 45 ms) or long (> 45 ms) echo time (TE), each with particular advantages. Short-TE spectra are more adequate for detecting lipids, while the long-TE provides a much flatter signal baseline in between peaks but also negative signals for metabolites such as lactate. Both, lipids and lactate, are respectively indicative of specific metabolic processes taking place. Ideally, the information provided by both TE should be of use for clinical purposes. In this study, we characterise the performance of a range of Non-negative Matrix Factorisation (NMF) methods in two respects: first, to derive sources correlated with the mean spectra of known tissue types (tumours and normal tissue); second, taking the best performing NMF method for source separation, we compare its accuracy for class assignment when using the mixing matrix directly as a basis for classification, as against using the method for dimensionality reduction (DR). For this, we used SV 1H-MRS data with positive and negative peaks, from a widely tested SV 1H-MRS human brain tumour database.

RESULTS

The results reported in this paper reveal the advantage of using a recently described variant of NMF, namely Convex-NMF, as an unsupervised method of source extraction from SV1H-MRS. Most of the sources extracted in our experiments closely correspond to the mean spectra of some of the analysed tumour types. This similarity allows accurate diagnostic predictions to be made both in fully unsupervised mode and using Convex-NMF as a DR step previous to standard supervised classification. The obtained results are comparable to, or more accurate than those obtained with supervised techniques.

CONCLUSIONS

The unsupervised properties of Convex-NMF place this approach one step ahead of classical label-requiring supervised methods for the discrimination of brain tumour types, as it accounts for their increasingly recognised molecular subtype heterogeneity. The application of Convex-NMF in computer assisted decision support systems is expected to facilitate further improvements in the uptake of MRS-derived information by clinicians.