Clinical Bioinformatics: a research agenda to support health care - - PowerPoint PPT Presentation

▶
clinical bioinformatics a research agenda to support
SMART_READER_LITE
LIVE PREVIEW

Clinical Bioinformatics: a research agenda to support health care - - PowerPoint PPT Presentation

Jan 11, 2023 342 likes •789 views

Clinical Bioinformatics: a research agenda to support health care transformation Riccardo Bellazzi Laboratory for Biomedical Informatics Labs Biomedical Informatics University of Pavia IRCCS Fondazione S. Maugeri Pavia Translational

slide-1
SLIDE 1

Laboratory for Biomedical Informatics

Clinical Bioinformatics: a research agenda to support health care transformation

Riccardo Bellazzi

Biomedical Informatics Labs University of Pavia IRCCS Fondazione S. Maugeri Pavia

slide-2
SLIDE 2

Translational Bioinformatics

"It is the responsibility of those of us involved in today's biomedical research enterprise to translate the remarkable scientific innovations we are witnessing into health gains for the nation... At no other time has the need for a robust, bidirectional information flow between basic and translational scientists been so necessary."

  • -Dr. Elias Zerhouni, Director of the National Institutes of Health, 2005
slide-3
SLIDE 3
slide-4
SLIDE 4

Risk assessment Genetic markers Individual risk Diagnosis and therapy planning Genetic markers Diagnosis Drug selection and therapy planning Patients clinical findings Non- genetic molecular markers Life style

slide-5
SLIDE 5

Bars represent the Request for Applications (RFAs) and Program Announcements (PAs) by NIH containing the term “informatics”. Line represents the fraction of this count over the total count of RFAs and PAs that year.

slide-6
SLIDE 6
slide-7
SLIDE 7

genomic proteomic

clinical

transcriptomic

biological

histology images

patient biomarkers clinical trial HETEROGENOUS DATA

Translational Cancer Research & Clinical Bioinformatics

DATAMINE tissue

data

patient

demographic

Paul Lewis, Cancer Informatics Group

Clinical Bioinformatics

slide-8
SLIDE 8

Informatics for Integrating Biology and the Bedside (i2b2) Isaac Kohane, PI Center for Computational Biology (CCB) Arthur Toga, PI Multiscale Analysis of Genomic and Cellular Networks (MAGNet) Andrea Califano, PI National Alliance for Medical Imaging Computing (NA-MIC) Ron Kikinis, PI The National Center For Biomedical Ontology (NCBO) Mark Musen, PI Physics-Based Simulation of Biological Structures (SIMBIOS) Russ Altman, PI National Center for Integrative Biomedical Informatics (NCIBI) Brian D. Athey, PI

NIH Roadmap National Centers for Biomedical Computing (NCBC)

slide-9
SLIDE 9

Clinical by Informatics &Translational Bioinformatics

http://clinicalinformatics.stanford.edu/ http://ycmi.med.yale.edu/index.html http://www.bioontology.org/ http://portal.ncibi.org/gateway/ https://www.i2b2.org/ http://idash.ucsd.edu/

slide-10
SLIDE 10

Laboratory for Biomedical Informatics

Infrastructures

slide-11
SLIDE 11

Informatics for Integrating Biology and the Bedside (i2b2) Isaac Kohane, PI Center for Computational Biology (CCB) Arthur Toga, PI Multiscale Analysis of Genomic and Cellular Networks (MAGNet) Andrea Califano, PI National Alliance for Medical Imaging Computing (NA-MIC) Ron Kikinis, PI The National Center For Biomedical Ontology (NCBO) Mark Musen, PI Physics-Based Simulation of Biological Structures (SIMBIOS) Russ Altman, PI National Center for Integrative Biomedical Informatics (NCIBI) Brian D. Athey, PI

Informatics for Integrating Biology and the Bedside (i2b2) Isaac Kohane, PI

NIH Roadmap National Centers for Biomedical Computing (NCBC)

slide-12
SLIDE 12
slide-13
SLIDE 13

Clinical Bioinformatics

Knowledge discovery Knowledge to practice Bedside to bench Test new Knowledge

slide-14
SLIDE 14

CLINICAL RESEARCH CHART

slide-15
SLIDE 15

Crimson i2b2

Cohort

IRB#

Crimson

High-throughput sample collection

HIV

Samples: Pathology Depts/Clinical Labs BWH labs discard >5000 Clinical samples/day >2 million/year Partners hospitals: >20,000 samples/day BWH AP >200,000 samples/year

slide-16
SLIDE 16

Clinical Bioinformatics – the i2b2 Pavia project

DW / clinical research chart Intelligent query / data mining Knowledge repositories Reasoning systems EMR Research data-bases Discharge letters HIV Biobanks IRCCS Fondazione

  • C. Mondino

IRCCS Fondazione

  • S. Maugeri
slide-17
SLIDE 17

BIOINFORMATICS METHODOLOGY AND TECHNOLOGY TO INTEGRATE CLINICAL AND BIOLOGICAL KNOWLEDGE SUPPORTING ONCOLOGY TRANSATIONAL RESEARCH (ONCO-I2B2)

slide-18
SLIDE 18

I2b2-Pavia populating the datawarehouse CRC

Research Clinical Data Ontology Mapped Clinical Data Domain Ontology Documents Legacy Databases NLP System ICHD Diagnosis ICHD Code System

slide-19
SLIDE 19

NLP – extracting information from clinical narratives

Section splitter Text tokenizer POS tagger NP chunker Diagnosis extractor Document Data Base

slide-20
SLIDE 20

Section splitter

[…] trattamento raccomandato: sulla base della storia clinica e della

  • biettività neurologica ho concordato con il paziente di tenere un diario

della cefalea (indicando durata, frequenza, intensità delle crisi, uso di analgesici). si consiglia di mantenere un regolare ritmo sonno-veglia, di riprendere un'attività fisica periodica. ritengo che vi sia una tensione a livello dei muscoli epicranici e del collo che potrebbe essere migliorata con della fisioterapia. diagnosi:

  • 1. emicrania senza aura
  • 2. cefalea tensiva episodica sporadica.

terapia consigliata: " almotriptan cpr: una cpr all'inizio della crisi; in alternativa/dopo due

  • re: indometacina supp. 50 mg: una supp.

[…]

TREATMENT DIAGNOSIS THERAPY

Sections

slide-21
SLIDE 21

NP - chunker

[…] Si consiglia di mantenere un regolare ritmo sonno-veglia, di riprendere un'attività fisica periodica. Ritengo che vi sia una tensione a livello dei muscoli epicranici e del collo che potrebbe essere migliorata con della fisioterapia. […]

Noun Phrase

slide-22
SLIDE 22

Concept Finder

[…] Diagnosis:

  • 1. Emicrania senza aura
  • 2. Cefalea tensiva episodica sporadica

[…]

ICHD – 1.1

  • Emicrania senza aura

ICHD – 2 - Cefalea di tipo tensivo

slide-23
SLIDE 23

Towards knowledge-discovery support systems

Intelligent query / data mining Knowledge repositories Reasoning systems The Phenotype Miner1 Genephony3 The ST-Model4

Nuzzo et al, BMC Bioinformatics, 20081 Malovini et al, BMC Bioinformatics, 20082 Nuzzo et al, BMC Bioinformatics, 20093 Riva et al, JBI, 20094

SNP-2-Net3

slide-24
SLIDE 24

The phenotype miner

Dynamic inspection table (provided by Mondrian) Genotypic data retrieving utilities Phenotype Editor

slide-25
SLIDE 25

The phenotype miner

Dynamic inspection table (provided by Mondrian) Genotypic data retrieving utilities Phenotype Editor

slide-26
SLIDE 26

Risk stratification

slide-27
SLIDE 27

Genome-wide association studies

Controls Cases

slide-28
SLIDE 28
slide-29
SLIDE 29

Naive Bayes classifier July 1st

slide-30
SLIDE 30

Diagnosis and therapy planning

slide-31
SLIDE 31

Laboratory for Biomedical Informatics

slide-32
SLIDE 32

Dilated cardiomiopathy

Centre for Inherited Cardiovascular Diseases - IRCCS Policlinico San Matteo - Pavia

slide-33
SLIDE 33

1980 1990 2000 2009

% 100 50

Viral etiology Dilated Cardiomyopathy 30 years of research

Genetic/familial. Data from family screening studies and serial monitoring

  • f family members

HTx

Centre for Inherited Cardiovascular Diseases - IRCCS Policlinico San Matteo - Pavia

DCM: the past and wrong paradigm of post-viral disease

slide-34
SLIDE 34

“DCM”

Dystrofinopathies Laminopathies Desminopathies Mitocondriopathies Epicardinopathies Actinopathies Zaspopathies Desmosonopathies

From DCM to…

Clinically oriented genetic investigation

Centre for Inherited Cardiovascular Diseases - IRCCS Policlinico San Matteo - Pavia

slide-35
SLIDE 35

Concept

 More than 35 genes may cause DCM  DCM is sometimes accompanied by gene-

specific traits  red flags

 Grouping patients according to phenotypes

  • DCM + type of inheritance + cardiac

markers + extracardiac markers + any clinical data that may “specify” the subgroups

slide-36
SLIDE 36

ECG Rest, effort, holter Pedigree Family screening Symptoms Duration Physical evaluation Non Familial Familial: AD, AR, X-LR, MT Cardiac, Extra Cardiac,Recent Onset, Long term Muscle, Skin Eyes, Kidney, Liver, Lung LAB Imaging: echo, MRI RV Cath AVB, PR, WPW, etc, CPK, Leukocytes, Enzymes, Metab. Etc LVNC, DE

EMB Family screening Clinical markers

Diagnostic Hypothesis: Before Genetic Testing Increasing the number

  • f genotyped CMP

One gene ---> one disease

slide-37
SLIDE 37

Noonan syndrome

Case-based-ranking

Assign a score to genes based on similarity of the clinical case with previous, and already known, clinical cases PTPN11 → DCM, HCM EYA4 → DCM

Case base Patient 1 – gene PTPN11 Patient 2 – gene EYA4 …

Current patient

slide-38
SLIDE 38

Acknowledgements

Bioinformatics and Data Mining group (http://bioinfo.unipv.it) University of Ljubljana Harvard Medical School IRCCS Fondazione S. Maugeri IRCCS Fondazione C. Mondino

slide-39
SLIDE 39

Laboratory for Biomedical Informatics

NETTAB 2011: CLINICAL BIOINFORMATICS PAVIA

slide-40
SLIDE 40

PAVIA: UNIVERSITY AND HOSPITALS

slide-41
SLIDE 41

Organizers

 Paolo Romano

(IST Genova)

 Riccardo Bellazzi

(University of Pavia)

 Isaac (Zak) Kohane

(Harvard Medical School)

slide-42
SLIDE 42

Location: Collegio Ghislieri

Lardirago Castle Aula Magna Quadriportico

slide-43
SLIDE 43

Clinical by Informatics & Translational Bioinformatics

Future Developments of Medical Informatics from the Viewpoint of Networked Clinical Research. http://www.ncbi.nlm.nih.gov/pubmed/19151883 Perspective for medical informatics. Reusing the electronic medical record for clinical research. http://www.ncbi.nlm.nih.gov/pubmed/19151882?dopt=Abstract Biomedical informatics and translational medicine. http://www.ncbi.nlm.nih.gov/pubmed/20187952 Translational informatics: enabling high-throughput research paradigms. http://www.ncbi.nlm.nih.gov/pubmed/19737991