Volodya Vovk’s research while affiliated with Royal Holloway, University of London and other places

This paper describes the methodology of providing multiprobability predictions for proteomic mass spectrometry data. The methodology is based on a newly developed machine learning framework called Venn machines. Is allows to output a valid probability interval. The methodology is designed for mass spectrometry data. For demonstrative purposes, we applied this methodology to MALDI-TOF data sets in order to predict the diagnosis of heart disease and early diagnoses of ovarian cancer and breast cancer. The experiments showed that probability intervals are narrow, that is, the output of the multiprobability predictor is similar to a single probability distribution. In addition, probability intervals produced for heart disease and ovarian cancer data were more accurate than the output of corresponding probability predictor. When Venn machines were forced to make point predictions, the accuracy of such predictions is for the most data better than the accuracy of the underlying algorithm that outputs single probability distribution of a label. Application of this methodology to MALDI-TOF data sets empirically demonstrates the validity. The accuracy of the proposed method on ovarian cancer data rises from 66.7 % 11 months in advance of the moment of diagnosis to up to 90.2 % at the moment of diagnosis. The same approach has been applied to heart disease data without time dependency, although the achieved accuracy was not as high (up to 69.9 %). The methodology allowed us to confirm mass spectrometry peaks previously identified as carrying statistically significant information for discrimination between controls and cases.

We describe a method for predicting a classification of an object given classifications of the objects in the training set, assuming that the pairs object/classification are generated by an i.i.d. process from a continuous probability distribution. Our method is a modification of Vapnik's support-vector machine; its main novelty is that it gives not only the prediction itself but also a practicable measure of the evidence found in support of that prediction. We also describe a procedure for assigning degrees of confidence to predictions made by the support vector machine. Some experimental results are presented, and possible extensions of the algorithms are discussed.

This paper describes the methodology of providing multiprobability predictions for proteomic mass spectrometry data. The methodology is based on a newly developed machine learning framework called Venn machines. They allow us to output a valid probability interval. We apply this methodology to mass spectrometry data sets in order to predict the diagnosis of heart disease and early diagnoses of ovarian cancer. The experiments show that probability intervals are valid and narrow. In addition, probability intervals were compared with the output of a corresponding probability predictor. © 2012 IFIP International Federation for Information Processing.

The work describes an application of a recently developed machine-learning technique called Mondrian predictors to risk assessment of ovarian and breast cancers. The analysis is based on mass spectrometry profiling of human serum samples that were collected in the United Kingdom Collaborative Trial of Ovarian Cancer Screening. The work describes the technique and presents the results of classification (diagnosis) and the corresponding measures of confidence of the diagnostics. The main advantage of this approach is a proven validity of prediction. The work also describes an approach to improve early diagnosis of ovarian and breast cancers since the data in the United Kingdom Collaborative Trial of Ovarian Cancer Screening were collected over a period of 7 years and do allow to make observations of changes in human serum over that period of time. Significance of improvement is confirmed statistically (for up to 11 months for ovarian cancer and 9 months for breast cancer). In addition, the methodology allowed us to pinpoint the same mass spectrometry peaks as previously detected as carrying statistically significant information for discrimination between healthy and diseased patients. The results are discussed.

A nested case-control discovery study was undertaken to test whether information within the serum peptidome can improve on the utility of CA125 for early ovarian cancer detection. High-throughput matrix-assisted laser desorption ionisation mass spectrometry (MALDI-MS) was used to profile 295 serum samples from women pre-dating their ovarian cancer diagnosis and from 585 matched control samples. Classification rules incorporating CA125 and MS peak intensities were tested for discriminating ability. Two peaks were found which in combination with CA125 discriminated cases from controls up to 15 and 11 months before diagnosis, respectively, and earlier than using CA125 alone. One peak was identified as connective tissue-activating peptide III (CTAPIII), whilst the other was putatively identified as platelet factor 4 (PF4). ELISA data supported the down-regulation of PF4 in early cancer cases. Serum peptide information with CA125 improves lead time for early detection of ovarian cancer. The candidate markers are platelet-derived chemokines, suggesting a link between platelet function and tumour development.

We construct prediction intervals for the linear regression model with IID errors with a known distribution, not necessarily Gaussian. The coverage probability of our prediction intervals is equal to the nominal confidence level not only unconditionally but also conditionally given a natural sigma-algebra of invariant events. This implies, in particular, the perfect calibration of our prediction intervals in the on-line mode of prediction.

Most current machine learning systems for medical decision support do not produce any indication of how reliable each of their predictions is. However, an indication of this kind is highly desirable especially in the medical field. This paper deals with this problem by applying a recently developed technique for assigning confidence measures to predictions, called conformal prediction, to the problem of acute abdominal pain diagnosis. The data used consist of a large number of hospital records of patients who suffered acute abdominal pain. Each record is described by 33 symptoms and is assigned to one of nine diagnostic groups. The proposed method is based on Neural Networks and for each patient it can produce either the most likely diagnosis together with an associated confidence measure, or the set of all possible diagnoses needed to satisfy a given level of confidence.

Medical decision support is an area in which a lot of machine learning research has been conducted and several diagnostic and prognostic systems have been developed. The majority of these systems only produce bare predictions, without any indication of how reliable each of these predictions is. An indication of this kind however, is highly desirable especially in the medical field. In this paper we address this problem with the use of a recently developed technique, called conformal prediction, for accompanying the predictions of traditional machine learning algorithms with measures of their accuracy and reliability. We apply conformal prediction based on a Neural Network classifier to the problem of acute abdominal pain diagnosis and obtain predictions which have a high level of accuracy and are complemented with well-calibrated and practically useful confidence measures.

Ovarian cancer is characterized by vague, non-specific symptoms, advanced stage at diagnosis and poor overall survival. A nested case control study was undertaken on stored serial serum samples from women who developed ovarian cancer and healthy controls (matched for serum processing and storage conditions as well as attributes such as age) in a pilot randomized controlled trial of ovarian cancer screening. The unique feature of this study is that the women were screened for up to 7 years. The serum samples underwent prefractionation using a reversed-phase batch extraction protocol prior to MALDI-TOF MS data acquisition. Our exploratory analysis shows that combining a single MS peak with CA125 allows statistically significant discrimination at the 5% level between cases and controls up to 12 months in advance of the original diagnosis of ovarian cancer. Such combinations work much better than a single peak or CA125 alone. This paper demonstrates that mass spectra from the low molecular weight serum proteome carry information useful for early detection of ovarian cancer. The next step is to identify the specific biomarkers that make early detection possible.