Learning from medical data streamspprodrigues/lmds11/lemeds... · Learning from Medical Data...

33
Learning from medical data streams an introduction Pedro Pereira Rodrigues, Mykola Pechenizkiy Mohamed Medhat Gaber, João Gama [email protected] [email protected] [email protected] [email protected] 6 th July 2011

Transcript of Learning from medical data streamspprodrigues/lmds11/lemeds... · Learning from Medical Data...

Page 1: Learning from medical data streamspprodrigues/lmds11/lemeds... · Learning from Medical Data Streams Recent trends Carolyn McGregor et al. Event correlation in neonatal ICU using

Learning frommedical data streams

an introduction

Pedro Pereira Rodrigues, Mykola PechenizkiyMohamed Medhat Gaber, João Gama

[email protected] [email protected]@port.ac.uk [email protected]

6th July 2011

Page 2: Learning from medical data streamspprodrigues/lmds11/lemeds... · Learning from Medical Data Streams Recent trends Carolyn McGregor et al. Event correlation in neonatal ICU using

2LEMEDS @ AIME 2011Pedro Pereira Rodrigues

Roadmap

Data stream paradigm

● Medical data streams

Machine learning

● Learning from data streams

Learning from medical data streams

● Recent trends

LEMEDS Workshop

● Objectives

● Program

Page 3: Learning from medical data streamspprodrigues/lmds11/lemeds... · Learning from Medical Data Streams Recent trends Carolyn McGregor et al. Event correlation in neonatal ICU using

3LEMEDS @ AIME 2011Pedro Pereira Rodrigues

Data Stream Paradigm

Many sources produce data continuously:

● web clicks logs

● telephone records

● sensors and RFIDs

● information systems

● …

These continuous flows of data are called data streams1.

After processing, a data point is either discarded or archived2.

1. Muthukrishnan, S. (2005). Data Streams: Algorithms and Applications. […]

2. Gama, J. and Rodrigues, P. P. (2007). “Data stream processing”. [...]

Page 4: Learning from medical data streamspprodrigues/lmds11/lemeds... · Learning from Medical Data Streams Recent trends Carolyn McGregor et al. Event correlation in neonatal ICU using

4LEMEDS @ AIME 2011Pedro Pereira Rodrigues

Data Stream Paradigm

Set Stream

Size finite infinite

Distribution i.i.d. non i.i.d.

Ordering independent dependent

Evolution static non­stationary

Page 5: Learning from medical data streamspprodrigues/lmds11/lemeds... · Learning from Medical Data Streams Recent trends Carolyn McGregor et al. Event correlation in neonatal ICU using

5LEMEDS @ AIME 2011Pedro Pereira Rodrigues

Ubiquitous Data Streams

Multiple sources producing streams of data:

● web sites and users

● smart phones and other mobile devices

● integrated health information systems

● sensor networks

● …

Most devices are now able to sense and process information1.

Distributed sources, each one producing a high-speed data stream2.

1. Rodrigues, P.P, Gama, J., and Lopes, L. (2010). “Knowledge discovery for sensor network comprehension”. [...]

2. Rodrigues, P. P. and Gama, J. (2009). “A system for analysis and prediction of electricity load streams”. [...]

Page 6: Learning from medical data streamspprodrigues/lmds11/lemeds... · Learning from Medical Data Streams Recent trends Carolyn McGregor et al. Event correlation in neonatal ICU using

6LEMEDS @ AIME 2011Pedro Pereira Rodrigues

Medical Data Streams

Anatomical sensors

● movement● position● location

Physiological sensors

● blood pressure● heartbeat rate● ECG● EEG● ...

BiomedicalSignals

(high rate)

Page 7: Learning from medical data streamspprodrigues/lmds11/lemeds... · Learning from Medical Data Streams Recent trends Carolyn McGregor et al. Event correlation in neonatal ICU using

7LEMEDS @ AIME 2011Pedro Pereira Rodrigues

Medical Data Streams

Hospital data

● episode descriptions● consultation records● diagnosis● executed procedures

Incidence records

● personal health records● collaborative disease surveilance● bacterial surveilance● pharmacologic surveilance

HealthRecords

(large size)

Page 8: Learning from medical data streamspprodrigues/lmds11/lemeds... · Learning from Medical Data Streams Recent trends Carolyn McGregor et al. Event correlation in neonatal ICU using

8LEMEDS @ AIME 2011Pedro Pereira Rodrigues

Medical Data Streams

Medical settings are using sensors and networks of health information systems to integrate data from patients from which it is necessary to extract some sort of knowledge.

New services like Google Health appear allowing users to store and track information about their medical history, to connect to and stream data from medical devices.

Medical data streams become widespread and call for development of intelligent tools for making use of these data.

Page 9: Learning from medical data streamspprodrigues/lmds11/lemeds... · Learning from Medical Data Streams Recent trends Carolyn McGregor et al. Event correlation in neonatal ICU using

9LEMEDS @ AIME 2011Pedro Pereira Rodrigues

Medical Data Streams

Possible uses:

● Decision support

● Alerting services

● Ambient intelligence

● Assisted leaving

● Personalization services

All of them are characterized by the huge amounts of data being produced, and often require fast and accurate information retrieval and analysis, that can effectively support clinical decisions.

Page 10: Learning from medical data streamspprodrigues/lmds11/lemeds... · Learning from Medical Data Streams Recent trends Carolyn McGregor et al. Event correlation in neonatal ICU using

10LEMEDS @ AIME 2011Pedro Pereira Rodrigues

Medical Data Streams

Medical domains introduce extra peculiarities to the learning problem:

Structured and uncertain data

Health information systems deal with heterogeneous data sources

Possibly distributed across healthcare institutions

Data integration requirement yields privacy-preserving issues

Integration forces the system to manage:

● time● resources, and● costs.

Page 11: Learning from medical data streamspprodrigues/lmds11/lemeds... · Learning from Medical Data Streams Recent trends Carolyn McGregor et al. Event correlation in neonatal ICU using

11LEMEDS @ AIME 2011Pedro Pereira Rodrigues

Medical Data Streams

Particular issues to address include:

● Summarization of infinite data

● Incremental and decremental learning

● Resource-awareness

● Real-time monitoring of changes

● Novelty detection

This is an incremental task that requires incremental learning algorithms that integrate artificial intelligence in medical domains.

Page 12: Learning from medical data streamspprodrigues/lmds11/lemeds... · Learning from Medical Data Streams Recent trends Carolyn McGregor et al. Event correlation in neonatal ICU using

12LEMEDS @ AIME 2011Pedro Pereira Rodrigues

Learning from Data Streams

Learning in the presence of drift requires monitoring of the learning process1.

1. Gama, J. and Rodrigues, P.P.  (2007). “Data stream processing”. [...]

Page 13: Learning from medical data streamspprodrigues/lmds11/lemeds... · Learning from Medical Data Streams Recent trends Carolyn McGregor et al. Event correlation in neonatal ICU using

13LEMEDS @ AIME 2011Pedro Pereira Rodrigues

Medical Data Streams

● Intelligent analysis and learning from streaming data are widely spread in the machine learning research community.

● In medical domains, technological issues of data collection and storage, access, integration and fusion are also widely studied in the health informatics research community.

● However, adoption and development of tailored techniques for medical stream mining and clinical decision support is still to come.

Page 14: Learning from medical data streamspprodrigues/lmds11/lemeds... · Learning from Medical Data Streams Recent trends Carolyn McGregor et al. Event correlation in neonatal ICU using

14LEMEDS @ AIME 2011Pedro Pereira Rodrigues

Knowledge Discovery

1. Patel, V., Shortliffe, E., Stefanelli, M., Szolovitz, P.,Berthold, M., et al. (2009) “The coming of age of artificial intelligence in medicine”. [...]

Page 15: Learning from medical data streamspprodrigues/lmds11/lemeds... · Learning from Medical Data Streams Recent trends Carolyn McGregor et al. Event correlation in neonatal ICU using

15LEMEDS @ AIME 2011Pedro Pereira Rodrigues

Learning from Medical Data Streams

1. Zhou, X., et al. (2006) “Monitoring Abnormal Patterns with Complex Semantics over ICU Data Streams” [...]

Page 16: Learning from medical data streamspprodrigues/lmds11/lemeds... · Learning from Medical Data Streams Recent trends Carolyn McGregor et al. Event correlation in neonatal ICU using

16LEMEDS @ AIME 2011Pedro Pereira Rodrigues

Learning from Medical Data Streams

Recent trends

● Carolyn McGregor et al.

● Event correlation in neonatal ICU using SOA for integration of clinical and physiological streams

● Daby Sow et al.

● Body sensor stream processing

● Mykola Pechenizkiy et al.

● Concept drift in antibiotic resistace in nosocomial infections

● Raquel Sebastião et al.

● Concept drift detection for CTG and BIS

● Xinbiao Zhou et al.

● Mining abnormal patterns in ICU

Page 17: Learning from medical data streamspprodrigues/lmds11/lemeds... · Learning from Medical Data Streams Recent trends Carolyn McGregor et al. Event correlation in neonatal ICU using

17LEMEDS @ AIME 2011Pedro Pereira Rodrigues

SOA for Integration and Event Correlation

Service-oriented arquitecture (SOA)

● integrates physiological and clinical data

● based on temporal abstractions

● aims to correlatetemporal events

1. Kamaleswaran, R., et al. (2009) “Service oriented architecture for the integration of clinical and physiological data for real­time event stream processing” [...]

Page 18: Learning from medical data streamspprodrigues/lmds11/lemeds... · Learning from Medical Data Streams Recent trends Carolyn McGregor et al. Event correlation in neonatal ICU using

18LEMEDS @ AIME 2011Pedro Pereira Rodrigues

Body Sensor Stream Processing

Language to support processing of body sensor streaming data

● extracts medically significant events

● interacts with external data mining systems

● allows streaming applications to make use of historical data

● improve their detection and prediction performance

1. Sow, D., et al. (2010) “Body Sensor Data Processing using Stream Computing” [...]

Page 19: Learning from medical data streamspprodrigues/lmds11/lemeds... · Learning from Medical Data Streams Recent trends Carolyn McGregor et al. Event correlation in neonatal ICU using

19LEMEDS @ AIME 2011Pedro Pereira Rodrigues

Antibiotic Resistance in Nosocomial Infections

Concept drift detection on laboratory data

● emsemble learning

● multiple learning models● output value is a weighted average of the single predictions

● dynamic integration of classifiers

● weights managing local drift detection

● improves classification results

● captures seasonal trends in infections and resistance effects

1. Tsymbal, A. et al. (2006) “Handling Local Concept Drift with Dynamic Integration of Classifiers: Domain of Antibiotic Resistance in Nosocomial Infections” [...]

Page 20: Learning from medical data streamspprodrigues/lmds11/lemeds... · Learning from Medical Data Streams Recent trends Carolyn McGregor et al. Event correlation in neonatal ICU using

20LEMEDS @ AIME 2011Pedro Pereira Rodrigues

Concept Drift Detection in CTG

Cardiotocography (CTG)

● fetal heart rate (FHR)

● uterine contractions (UC)

SisPorto®

● 'Normal' – green

● 'Suspicious' – yellow/orange

● 'Problematic' – red

1. Sebastião, R.. et al. (2010) “Monitoring Incremental Histogram Distribution for Change Detection in Data Streams” [...]

Page 21: Learning from medical data streamspprodrigues/lmds11/lemeds... · Learning from Medical Data Streams Recent trends Carolyn McGregor et al. Event correlation in neonatal ICU using

21LEMEDS @ AIME 2011Pedro Pereira Rodrigues

Concept Drift Detection in BIS

Bispectral Index (BIS)

● Monitor anesthesia depth

● Detect sudden drift of the BIS signal

1. Sebastião, R.. et al. (2009) “Contributions to an Advisory System to Enhanced TCI in Sedation­Analgesia Procedures” [...]

Page 22: Learning from medical data streamspprodrigues/lmds11/lemeds... · Learning from Medical Data Streams Recent trends Carolyn McGregor et al. Event correlation in neonatal ICU using

22LEMEDS @ AIME 2011Pedro Pereira Rodrigues

Abnormal Patterns in ICU Streams

Monitoring abnormal patterns over ICU data streams

● complex repetitive phenomena

● defines the deviation of the process from true periodicity

● efficiently identifies the anomalies just in a single pass

1. Zhou, X., et al. (2006) “Monitoring Abnormal Patterns with Complex Semantics over ICU Data Streams” [...]

Page 23: Learning from medical data streamspprodrigues/lmds11/lemeds... · Learning from Medical Data Streams Recent trends Carolyn McGregor et al. Event correlation in neonatal ICU using

23LEMEDS @ AIME 2011Pedro Pereira Rodrigues

AIME 2011

This year at AIME 2011 several papers addressed data streams (mainly biomedical signals) and related fields. Two of them were even distinguished as the two best student papers:

● Fernando García-García, Gema García-Sáez, Paloma Chausa, Iñaki Martínez-Sarriegui, Pedro José Benito, Enrique J. Gómez and M. Elena Hernando

Statistical Machine Learning for Automatic Assessment of Physical Activity Intensity Using Multi-axial Accelerometry and Heart Rate

● Catherine G. Enright, Michael G. Madden and Niall Madden

Clinical Time Series Data Analysis Using Mathematical Models and DBNs

Page 24: Learning from medical data streamspprodrigues/lmds11/lemeds... · Learning from Medical Data Streams Recent trends Carolyn McGregor et al. Event correlation in neonatal ICU using

24LEMEDS @ AIME 2011Pedro Pereira Rodrigues

LEMEDS Workshop

Objectives:

● Bring together researchers from the machine learning and the clinical data streams communities

● Promote discussion for requirements and recommendations for learning from medical data streams

Program:

● 1 invited talk

● 5 contributed papers

● 1 expert panel discussion

Page 25: Learning from medical data streamspprodrigues/lmds11/lemeds... · Learning from Medical Data Streams Recent trends Carolyn McGregor et al. Event correlation in neonatal ICU using

25LEMEDS @ AIME 2011Pedro Pereira Rodrigues

LEMEDS Workshop

The fact that more and more medical data is being produced by sensors that measure physiological parameters [6] includes new challenges to artificial intelligence in general, and machine learning in particular.

Peter Lucas talk “Disease Monitoring and Clinical Decision Support” will focus on the properties of biomedical data streams (e.g. from sensors) and the constraints on how collected data can be exploited, and the new opportunities to monitor the progress of diseases in patients.

Page 26: Learning from medical data streamspprodrigues/lmds11/lemeds... · Learning from Medical Data Streams Recent trends Carolyn McGregor et al. Event correlation in neonatal ICU using

26LEMEDS @ AIME 2011Pedro Pereira Rodrigues

LEMEDS Workshop

Biomedical signals have been addressed by most papers.

Jones et al. [3] proposed to interpret biosignals to improve mobile health monitoring for clinical decision support, using body sensor networks.

The paper presents two possible applications and discusses the possibilities of applying machine learning in this ubiquitous streaming scenario.

Page 27: Learning from medical data streamspprodrigues/lmds11/lemeds... · Learning from Medical Data Streams Recent trends Carolyn McGregor et al. Event correlation in neonatal ICU using

27LEMEDS @ AIME 2011Pedro Pereira Rodrigues

LEMEDS Workshop

Rodrigues et al. [10] propose to improve cardiotocography monitoring using streaming statistics of both the fetal heart rate and the uterine contractions signals.

The statistics will then be used to early detect changes in the monitored signals, and help in the prediction of birth outcome.

It is a position paper that has not experimentation yet, but should foster a sound discussion on the subject.

Page 28: Learning from medical data streamspprodrigues/lmds11/lemeds... · Learning from Medical Data Streams Recent trends Carolyn McGregor et al. Event correlation in neonatal ICU using

28LEMEDS @ AIME 2011Pedro Pereira Rodrigues

LEMEDS Workshop

Sebastião et al. [11] developed a learning-based advisory system for detecting changes in depth of anesthesia signals.

The paper addresses an important problem in the operational settings that can help to adapt administered doses for patients.

The problem is formulated and addressed as the problem of handling concept drift in online settings, with the obtained experimental results, based on real data collected at one of the hospitals, being very promising.

Page 29: Learning from medical data streamspprodrigues/lmds11/lemeds... · Learning from Medical Data Streams Recent trends Carolyn McGregor et al. Event correlation in neonatal ICU using

29LEMEDS @ AIME 2011Pedro Pereira Rodrigues

LEMEDS Workshop

McGregor et al. [7] presents a process mining framework to improve clinical guidelines in clinical care.

The paper presents a very interesting approach to knowledge discovery in a challenging scenario where data is produced as several heterogeneous streams.

Intensive care units are, undoubtedly in current healthcare services, the main clinical setting where data streams are being produced.

Page 30: Learning from medical data streamspprodrigues/lmds11/lemeds... · Learning from Medical Data Streams Recent trends Carolyn McGregor et al. Event correlation in neonatal ICU using

30LEMEDS @ AIME 2011Pedro Pereira Rodrigues

LEMEDS Workshop

But other medical streams exist differing from biomedical signals.

In Rodrigues et al. [9], the authors describe a setting of integrated electronic health records, trying to improve the visualization mechanism of the increasing amount of clinical documents available in a central hospital.

As a position paper, this paper clearly presents the problem spaces and the research presents a valid and realistic problem that exists within health-care today.

Page 31: Learning from medical data streamspprodrigues/lmds11/lemeds... · Learning from Medical Data Streams Recent trends Carolyn McGregor et al. Event correlation in neonatal ICU using

31LEMEDS @ AIME 2011Pedro Pereira Rodrigues

LEMEDS Workshop

Three experts will guide us through a discussion on:

main domains where medical data is produced as a stream

applications for LEMEDS

related fields of research

issues that differentiate this research area from other fields;

best forums for researchers to publish and discuss LEMEDS.

Panel:

Carlo Combi

Carolyn McGregor

João Gama

Page 32: Learning from medical data streamspprodrigues/lmds11/lemeds... · Learning from Medical Data Streams Recent trends Carolyn McGregor et al. Event correlation in neonatal ICU using

32LEMEDS @ AIME 2011Pedro Pereira Rodrigues

Acknowledgments

AIME 2011 organization.

The authors of contributed papers.

Invited speaker: Peter Lucas.

Experts panel: Carlo Combi, Carolyn McGregor, João Gama.

PC members:

Miguel Coimbra, Antoine Cornuéjols, Matjaz Kukar, Mark Last, Florent Masseglia, Ernestina Menasalvas, Josep Roure Alcobé, Cristina Santos, Alexey Tsymbal and Indre Zliobaite.

Page 33: Learning from medical data streamspprodrigues/lmds11/lemeds... · Learning from Medical Data Streams Recent trends Carolyn McGregor et al. Event correlation in neonatal ICU using

33LEMEDS @ AIME 2011Pedro Pereira Rodrigues

Learning from Medical Data Streams

Thank you and Welcome!