SlideShare a Scribd company logo
1 of 42
Develop a multi-state model
to predict multimorbidity of
Cardiovascular disease (CVD),
Type 2 diabetes (T2D), and
Chronic kidney disease (CKD)
Research aim
By:
Manali Ajay Jain
MSc Health Data Science (2022-23)
Develop a multi-state model
to predict multimorbidity of
Cardiovascular disease (CVD),
Type 2 diabetes (T2D), and
Chronic kidney disease (CKD)
Research aim
Many thanks to
Dr Glen Martin
for guiding me
throughout the research
Key elements
to understand
Prediction models
Informs people about their ailment prognosis
01
Multistate models
A stochastic process with multiple discrete states that it can occupy at
any given time
02
Multimorbidity
03
co-existence of two or more chronic illnesses, where one is not necessarily
more significant than the others time
Risk predictions of Multimorbidity
04
newly emerging area of research
! The missing pieces !
Multimorbidity studies were
mainly performed on groups of
individual
The validation sample size of the
risk predictions of multimorbidity
tend to be smaller
An attempt to fill the gap
This multistate model
analysed every single
patient
Sample size for
validation was
relatively larger
Validation approach
were generating
stacked transition
possibilities graphs
Data Source
Clinical Practice Research Datalink (CPRD)
*Advisory note:
 Access to the CPRD dataset was gained only after the
completion of the CPRD resource module training test
 The UoM also provided a Data Protection and Cyber
Security course
Foundation of
the dataset
Data was obtained
from Clinical Practice
Research Datalink
(CPRD)
Total data was
of 2,714,535
observations with 91
variables
Considered only
healthy population
and required variables
to start the analysis
This reduced the data to
2,001,735 observations and
74 variables, out of which 30
were various comorbidities
and 8 were demographic
variables
This data was then split in
70:30 ratio for training and
testing
purposes respectively
70:30
Data in a
glance
Demographic variables
 Age, BMI, Cholesterol ration, and SBP were
continuous variables
 Gender: female, male
 Ethnicity: white, mixed ethnic group, asian/asian
british, black/african/Caribbean/black british,
other ethnic group
 Smoking: never, ex, current
 Index of Multiple Deprivation: 5 stages, most to
least
Pathways
Diagram
3.T2D
Healthy
2.CVD
4.CKD
5 CVD+T2D
7.CKD+T2D
6.CVD+CKD 8.CVD+CKD+T2D
DEATH
Pathways
3.T2D
Healthy
2.CVD
4.CKD
5 CVD+T2D
7.CKD+T2D
6.CVD+CKD 8.CVD+CKD+T2D
DEATH
Matrix indicating 20
possible transitions
Pathways
XQuartz 2.8.5
R 4.1.3-gcc830
RStudio 1.3.1073
R libraries
 dplyr (Hadley Wickham et al. 2014)
 ggplot (Hadley Wickham et al. 2007)
 mstate (de Wreede et al. 2011)
 calibmsm (Alexander Pate et al. unreleased)
Technical
Requirements
No need of standardization
No need of normalization
Missing values were treated
by single stochastic imputation
Splitting was done randomly,
without any criteria
Before we
proceed
Let’s
begin!
• Training dataset was used for model construction
Let’s
begin!
• Training dataset was used for model construction
• Population distribution was studied across transitions
Event frequencies heatmap
Let’s
begin!
• Training dataset was used for model construction
• Population distribution was studied across transitions
• Dataset was converted into a dataset of class msdata (long format)
• id
• from
• to
• trans
• Tstart
• Tstop
• time
• status
• covariates (the 8 demographic variables)
Let’s
begin!
• Training dataset was used for model construction
• Population distribution was studied across transitions
• Dataset was converted into a dataset of class msdata (long format)
• Covariates were expanded – dummy variables were generated based on
the no. of transitions
Let’s
begin!
• Training dataset was used for model construction
• Population distribution was studied across transitions
• Dataset was converted into a dataset of class msdata (long format)
• Covariates were expanded – dummy variables were generated based on
the no. of transitions
• Time was converted from days to years
Let’s
begin!
• Training dataset was used for model construction
• Population distribution was studied across transitions
• Dataset was converted into a dataset of class msdata (long format)
• Covariates were expanded – dummy variables were generated based on
the no. of transitions
• Time was converted from days to years
• Cox model was fitted which had separate baseline hazards for each of the
transitions and no covariates
Let’s
begin!
• Training dataset was used for model construction
• Population distribution was studied across transitions
• Dataset was converted into a dataset of class msdata (long format)
• Covariates were expanded – dummy variables were generated based on
the no. of transitions
• Time was converted from days to years
• Cox model was fitted which had separate baseline hazards for each of the
transitions and no covariates
• Transition hazards estimates and their associated covariances from each
stage were calculated
Healthy stage
 Healthy -> CKD
highest
 Healthy -> T2D
lowest
CVD stage
 CVD -> Death
highest
 CVD -> CVD+T2D
lowest
T2D stage
 T2D -> Death
highest
 T2D -> CVD+T2D
lowest
CKD stage
 CKD -> Death
highest
 CKD -> CKD+T2D
lowest
CVD+T2D
stage
 CVD+T2D -> Death
upper line
 CVD+T2D -> CVD+T2D+CKD
lower line
CVD+CKD
stage
 CVD+CKD -> Death
upper line
 CVD+CKD -> CVD+T2D+CKD
lower line
CKD+T2D
stage
 CKD+T2D -> Death
upper line
 CKD+T2D -> CVD+T2D+CKD
lower line
CVD+T2D+CKD
stage
 This was created from a simple
survfit object since it had just
one transition
Diving
deeper
Transition possibilities estimates were also produced
Diving
deeper
Transition possibilities estimates were also produced
These findings demonstrate how a patient's prognosis is influenced by both their initial
condition and by the moment used as the beginning point for prediction
Stacked transition possibilities
Diving
deeper
 The distance between two
adjacent curves represents
the probability of being in
the corresponding state
Diving
deeper
Transition possibilities estimates were also produced
These findings demonstrate how a patient's prognosis is influenced by both their initial
condition and by the moment used as the beginning point for prediction
To create a lower dimensional representation of the regression coefficients of the whole
model, the reduced rank (RR) model was helpful
Diving
deeper
Transition possibilities estimates were also produced
These findings demonstrate how a patient's prognosis is influenced by both their initial
condition and by the moment used as the beginning point for prediction
To create a lower dimensional representation of the regression coefficients of the whole
model, the reduced rank (RR) model was helpful
RR model generates three items
• Alpha
• Gamma
• Beta
Alpha output of RR model
Misc ethnic group
Ex-smokers
More deprived
Gamma output of RR model
• All the values are mostly negative
• The coefficients for this risk score
in Gamma are negative and of
substantial size for all transitions
into death, same for transitions
starting from healthy
Beta output of RR model
• Combined analysis of alpha and
gamma
• Lower values of Alpha (for instance
mixed ethnicity, ex smoker, more
deprived) correspond to higher
death rates
It’s
TESTING
TIME!
• Built-up model is now fitted into the test
dataset
• Two follow-up durations were used to
evaluate the transition probabilities
• 5 years
• 10 years
• They could then be compared to the train
dataset stacked transition probabilities plot
It’s
TESTING
TIME!
Stacked transition possibilities
after 5 years
Testing
time
 The distance between two
adjacent curves represents the
probability of being in the
corresponding state
Stacked transition possibilities
after 10 years
Testing
time
 The distance between two
adjacent curves represents the
probability of being in the
corresponding state
 Majorly transitions resulting to
death is less over the years
Was it
worth it??
Couldn’t make calibration plots, but somehow
managed to get future prediction probabilities
01
01
Resulted in meaningful analysis which can
potentially be beneficial for the health sector
02
Thank you!

More Related Content

Similar to Multimorbidity Multistate Model

Optimising sepsis treatment with reinforcement learning
Optimising sepsis treatment with reinforcement learningOptimising sepsis treatment with reinforcement learning
Optimising sepsis treatment with reinforcement learningMads Astvad
 
ISCB 2023 Sources of uncertainty b.pptx
ISCB 2023 Sources of uncertainty b.pptxISCB 2023 Sources of uncertainty b.pptx
ISCB 2023 Sources of uncertainty b.pptxBenVanCalster
 
Data analysis ( Bio-statistic )
Data analysis ( Bio-statistic )Data analysis ( Bio-statistic )
Data analysis ( Bio-statistic )Amany Elsayed
 
East ugm-2012-presentation-east-future-mehta
East ugm-2012-presentation-east-future-mehtaEast ugm-2012-presentation-east-future-mehta
East ugm-2012-presentation-east-future-mehtaCytel
 
Eugm 2012 mehta - future plans for east - 2012 eugm
Eugm 2012   mehta - future plans for east - 2012 eugmEugm 2012   mehta - future plans for east - 2012 eugm
Eugm 2012 mehta - future plans for east - 2012 eugmCytel USA
 
Whole Genome Trait Association in SVS
Whole Genome Trait Association in SVSWhole Genome Trait Association in SVS
Whole Genome Trait Association in SVSGolden Helix
 
Risk And Uncertainty Analysis: A Primer for Floodplain Managers
Risk And Uncertainty Analysis:  A Primer for Floodplain ManagersRisk And Uncertainty Analysis:  A Primer for Floodplain Managers
Risk And Uncertainty Analysis: A Primer for Floodplain ManagersMichael DePue
 
Optimising sepsis treatment with reinforcement learning - Matthieu Komorowski
Optimising sepsis treatment with reinforcement learning - Matthieu KomorowskiOptimising sepsis treatment with reinforcement learning - Matthieu Komorowski
Optimising sepsis treatment with reinforcement learning - Matthieu KomorowskiMads Astvad
 
Lab Presentation, iEVORA CpG Biomarkers Overview
Lab Presentation, iEVORA CpG Biomarkers OverviewLab Presentation, iEVORA CpG Biomarkers Overview
Lab Presentation, iEVORA CpG Biomarkers OverviewSean Maden
 
Patient Selection for Primary Prevention Implantable Cardioverter Defibrillat...
Patient Selection for Primary Prevention Implantable Cardioverter Defibrillat...Patient Selection for Primary Prevention Implantable Cardioverter Defibrillat...
Patient Selection for Primary Prevention Implantable Cardioverter Defibrillat...HMO Research Network
 
Patient Selection for Primary Prevention Implantable Cardioverter Defibrillat...
Patient Selection for Primary Prevention Implantable Cardioverter Defibrillat...Patient Selection for Primary Prevention Implantable Cardioverter Defibrillat...
Patient Selection for Primary Prevention Implantable Cardioverter Defibrillat...HMO Research Network
 
A Stochastic Model for the Progression of Chronic Kidney Disease
A Stochastic Model for the Progression of Chronic Kidney DiseaseA Stochastic Model for the Progression of Chronic Kidney Disease
A Stochastic Model for the Progression of Chronic Kidney DiseaseIJERA Editor
 
Prostate cancer Risk stratification and choice of initial treatment final.pptx
Prostate cancer Risk stratification and choice of initial treatment final.pptxProstate cancer Risk stratification and choice of initial treatment final.pptx
Prostate cancer Risk stratification and choice of initial treatment final.pptxAhmed Eliwa
 
Bioinformatics-R program의 실례
Bioinformatics-R program의 실례Bioinformatics-R program의 실례
Bioinformatics-R program의 실례mothersafe
 
Michele Tonutti - Scaling is caring - Codemotion Amsterdam 2019
Michele Tonutti - Scaling is caring - Codemotion Amsterdam 2019Michele Tonutti - Scaling is caring - Codemotion Amsterdam 2019
Michele Tonutti - Scaling is caring - Codemotion Amsterdam 2019Codemotion
 

Similar to Multimorbidity Multistate Model (20)

Optimising sepsis treatment with reinforcement learning
Optimising sepsis treatment with reinforcement learningOptimising sepsis treatment with reinforcement learning
Optimising sepsis treatment with reinforcement learning
 
Curb 65 thorax-2003-lim-377-82
Curb 65 thorax-2003-lim-377-82Curb 65 thorax-2003-lim-377-82
Curb 65 thorax-2003-lim-377-82
 
ISCB 2023 Sources of uncertainty b.pptx
ISCB 2023 Sources of uncertainty b.pptxISCB 2023 Sources of uncertainty b.pptx
ISCB 2023 Sources of uncertainty b.pptx
 
Data analysis ( Bio-statistic )
Data analysis ( Bio-statistic )Data analysis ( Bio-statistic )
Data analysis ( Bio-statistic )
 
East ugm-2012-presentation-east-future-mehta
East ugm-2012-presentation-east-future-mehtaEast ugm-2012-presentation-east-future-mehta
East ugm-2012-presentation-east-future-mehta
 
Eugm 2012 mehta - future plans for east - 2012 eugm
Eugm 2012   mehta - future plans for east - 2012 eugmEugm 2012   mehta - future plans for east - 2012 eugm
Eugm 2012 mehta - future plans for east - 2012 eugm
 
Whole Genome Trait Association in SVS
Whole Genome Trait Association in SVSWhole Genome Trait Association in SVS
Whole Genome Trait Association in SVS
 
Risk And Uncertainty Analysis: A Primer for Floodplain Managers
Risk And Uncertainty Analysis:  A Primer for Floodplain ManagersRisk And Uncertainty Analysis:  A Primer for Floodplain Managers
Risk And Uncertainty Analysis: A Primer for Floodplain Managers
 
Optimising sepsis treatment with reinforcement learning - Matthieu Komorowski
Optimising sepsis treatment with reinforcement learning - Matthieu KomorowskiOptimising sepsis treatment with reinforcement learning - Matthieu Komorowski
Optimising sepsis treatment with reinforcement learning - Matthieu Komorowski
 
Lab Presentation, iEVORA CpG Biomarkers Overview
Lab Presentation, iEVORA CpG Biomarkers OverviewLab Presentation, iEVORA CpG Biomarkers Overview
Lab Presentation, iEVORA CpG Biomarkers Overview
 
Patient Selection for Primary Prevention Implantable Cardioverter Defibrillat...
Patient Selection for Primary Prevention Implantable Cardioverter Defibrillat...Patient Selection for Primary Prevention Implantable Cardioverter Defibrillat...
Patient Selection for Primary Prevention Implantable Cardioverter Defibrillat...
 
Patient Selection for Primary Prevention Implantable Cardioverter Defibrillat...
Patient Selection for Primary Prevention Implantable Cardioverter Defibrillat...Patient Selection for Primary Prevention Implantable Cardioverter Defibrillat...
Patient Selection for Primary Prevention Implantable Cardioverter Defibrillat...
 
B411010819
B411010819B411010819
B411010819
 
A Stochastic Model for the Progression of Chronic Kidney Disease
A Stochastic Model for the Progression of Chronic Kidney DiseaseA Stochastic Model for the Progression of Chronic Kidney Disease
A Stochastic Model for the Progression of Chronic Kidney Disease
 
Prostate cancer Risk stratification and choice of initial treatment final.pptx
Prostate cancer Risk stratification and choice of initial treatment final.pptxProstate cancer Risk stratification and choice of initial treatment final.pptx
Prostate cancer Risk stratification and choice of initial treatment final.pptx
 
B02308013
B02308013B02308013
B02308013
 
B02308013
B02308013B02308013
B02308013
 
Stein cimt for shape 11-05
Stein   cimt for shape 11-05Stein   cimt for shape 11-05
Stein cimt for shape 11-05
 
Bioinformatics-R program의 실례
Bioinformatics-R program의 실례Bioinformatics-R program의 실례
Bioinformatics-R program의 실례
 
Michele Tonutti - Scaling is caring - Codemotion Amsterdam 2019
Michele Tonutti - Scaling is caring - Codemotion Amsterdam 2019Michele Tonutti - Scaling is caring - Codemotion Amsterdam 2019
Michele Tonutti - Scaling is caring - Codemotion Amsterdam 2019
 

Recently uploaded

Building on a FAIRly Strong Foundation to Connect Academic Research to Transl...
Building on a FAIRly Strong Foundation to Connect Academic Research to Transl...Building on a FAIRly Strong Foundation to Connect Academic Research to Transl...
Building on a FAIRly Strong Foundation to Connect Academic Research to Transl...Jack DiGiovanna
 
Schema on read is obsolete. Welcome metaprogramming..pdf
Schema on read is obsolete. Welcome metaprogramming..pdfSchema on read is obsolete. Welcome metaprogramming..pdf
Schema on read is obsolete. Welcome metaprogramming..pdfLars Albertsson
 
Call Girls in Defence Colony Delhi 💯Call Us 🔝8264348440🔝
Call Girls in Defence Colony Delhi 💯Call Us 🔝8264348440🔝Call Girls in Defence Colony Delhi 💯Call Us 🔝8264348440🔝
Call Girls in Defence Colony Delhi 💯Call Us 🔝8264348440🔝soniya singh
 
04242024_CCC TUG_Joins and Relationships
04242024_CCC TUG_Joins and Relationships04242024_CCC TUG_Joins and Relationships
04242024_CCC TUG_Joins and Relationshipsccctableauusergroup
 
VIP Call Girls in Amravati Aarohi 8250192130 Independent Escort Service Amravati
VIP Call Girls in Amravati Aarohi 8250192130 Independent Escort Service AmravatiVIP Call Girls in Amravati Aarohi 8250192130 Independent Escort Service Amravati
VIP Call Girls in Amravati Aarohi 8250192130 Independent Escort Service AmravatiSuhani Kapoor
 
Customer Service Analytics - Make Sense of All Your Data.pptx
Customer Service Analytics - Make Sense of All Your Data.pptxCustomer Service Analytics - Make Sense of All Your Data.pptx
Customer Service Analytics - Make Sense of All Your Data.pptxEmmanuel Dauda
 
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...Sapana Sha
 
100-Concepts-of-AI by Anupama Kate .pptx
100-Concepts-of-AI by Anupama Kate .pptx100-Concepts-of-AI by Anupama Kate .pptx
100-Concepts-of-AI by Anupama Kate .pptxAnupama Kate
 
Delhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip CallDelhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Callshivangimorya083
 
RadioAdProWritingCinderellabyButleri.pdf
RadioAdProWritingCinderellabyButleri.pdfRadioAdProWritingCinderellabyButleri.pdf
RadioAdProWritingCinderellabyButleri.pdfgstagge
 
VIP High Profile Call Girls Amravati Aarushi 8250192130 Independent Escort Se...
VIP High Profile Call Girls Amravati Aarushi 8250192130 Independent Escort Se...VIP High Profile Call Girls Amravati Aarushi 8250192130 Independent Escort Se...
VIP High Profile Call Girls Amravati Aarushi 8250192130 Independent Escort Se...Suhani Kapoor
 
Call Girls In Mahipalpur O9654467111 Escorts Service
Call Girls In Mahipalpur O9654467111  Escorts ServiceCall Girls In Mahipalpur O9654467111  Escorts Service
Call Girls In Mahipalpur O9654467111 Escorts ServiceSapana Sha
 
(PARI) Call Girls Wanowrie ( 7001035870 ) HI-Fi Pune Escorts Service
(PARI) Call Girls Wanowrie ( 7001035870 ) HI-Fi Pune Escorts Service(PARI) Call Girls Wanowrie ( 7001035870 ) HI-Fi Pune Escorts Service
(PARI) Call Girls Wanowrie ( 7001035870 ) HI-Fi Pune Escorts Serviceranjana rawat
 
Spark3's new memory model/management
Spark3's new memory model/managementSpark3's new memory model/management
Spark3's new memory model/managementakshesh doshi
 
Brighton SEO | April 2024 | Data Storytelling
Brighton SEO | April 2024 | Data StorytellingBrighton SEO | April 2024 | Data Storytelling
Brighton SEO | April 2024 | Data StorytellingNeil Barnes
 
Data Warehouse , Data Cube Computation
Data Warehouse   , Data Cube ComputationData Warehouse   , Data Cube Computation
Data Warehouse , Data Cube Computationsit20ad004
 
Call Girls In Noida City Center Metro 24/7✡️9711147426✡️ Escorts Service
Call Girls In Noida City Center Metro 24/7✡️9711147426✡️ Escorts ServiceCall Girls In Noida City Center Metro 24/7✡️9711147426✡️ Escorts Service
Call Girls In Noida City Center Metro 24/7✡️9711147426✡️ Escorts Servicejennyeacort
 

Recently uploaded (20)

Building on a FAIRly Strong Foundation to Connect Academic Research to Transl...
Building on a FAIRly Strong Foundation to Connect Academic Research to Transl...Building on a FAIRly Strong Foundation to Connect Academic Research to Transl...
Building on a FAIRly Strong Foundation to Connect Academic Research to Transl...
 
Schema on read is obsolete. Welcome metaprogramming..pdf
Schema on read is obsolete. Welcome metaprogramming..pdfSchema on read is obsolete. Welcome metaprogramming..pdf
Schema on read is obsolete. Welcome metaprogramming..pdf
 
Call Girls in Defence Colony Delhi 💯Call Us 🔝8264348440🔝
Call Girls in Defence Colony Delhi 💯Call Us 🔝8264348440🔝Call Girls in Defence Colony Delhi 💯Call Us 🔝8264348440🔝
Call Girls in Defence Colony Delhi 💯Call Us 🔝8264348440🔝
 
Delhi 99530 vip 56974 Genuine Escort Service Call Girls in Kishangarh
Delhi 99530 vip 56974 Genuine Escort Service Call Girls in  KishangarhDelhi 99530 vip 56974 Genuine Escort Service Call Girls in  Kishangarh
Delhi 99530 vip 56974 Genuine Escort Service Call Girls in Kishangarh
 
04242024_CCC TUG_Joins and Relationships
04242024_CCC TUG_Joins and Relationships04242024_CCC TUG_Joins and Relationships
04242024_CCC TUG_Joins and Relationships
 
VIP Call Girls in Amravati Aarohi 8250192130 Independent Escort Service Amravati
VIP Call Girls in Amravati Aarohi 8250192130 Independent Escort Service AmravatiVIP Call Girls in Amravati Aarohi 8250192130 Independent Escort Service Amravati
VIP Call Girls in Amravati Aarohi 8250192130 Independent Escort Service Amravati
 
Customer Service Analytics - Make Sense of All Your Data.pptx
Customer Service Analytics - Make Sense of All Your Data.pptxCustomer Service Analytics - Make Sense of All Your Data.pptx
Customer Service Analytics - Make Sense of All Your Data.pptx
 
꧁❤ Aerocity Call Girls Service Aerocity Delhi ❤꧂ 9999965857 ☎️ Hard And Sexy ...
꧁❤ Aerocity Call Girls Service Aerocity Delhi ❤꧂ 9999965857 ☎️ Hard And Sexy ...꧁❤ Aerocity Call Girls Service Aerocity Delhi ❤꧂ 9999965857 ☎️ Hard And Sexy ...
꧁❤ Aerocity Call Girls Service Aerocity Delhi ❤꧂ 9999965857 ☎️ Hard And Sexy ...
 
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...
 
100-Concepts-of-AI by Anupama Kate .pptx
100-Concepts-of-AI by Anupama Kate .pptx100-Concepts-of-AI by Anupama Kate .pptx
100-Concepts-of-AI by Anupama Kate .pptx
 
Delhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip CallDelhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
 
RadioAdProWritingCinderellabyButleri.pdf
RadioAdProWritingCinderellabyButleri.pdfRadioAdProWritingCinderellabyButleri.pdf
RadioAdProWritingCinderellabyButleri.pdf
 
VIP Call Girls Service Charbagh { Lucknow Call Girls Service 9548273370 } Boo...
VIP Call Girls Service Charbagh { Lucknow Call Girls Service 9548273370 } Boo...VIP Call Girls Service Charbagh { Lucknow Call Girls Service 9548273370 } Boo...
VIP Call Girls Service Charbagh { Lucknow Call Girls Service 9548273370 } Boo...
 
VIP High Profile Call Girls Amravati Aarushi 8250192130 Independent Escort Se...
VIP High Profile Call Girls Amravati Aarushi 8250192130 Independent Escort Se...VIP High Profile Call Girls Amravati Aarushi 8250192130 Independent Escort Se...
VIP High Profile Call Girls Amravati Aarushi 8250192130 Independent Escort Se...
 
Call Girls In Mahipalpur O9654467111 Escorts Service
Call Girls In Mahipalpur O9654467111  Escorts ServiceCall Girls In Mahipalpur O9654467111  Escorts Service
Call Girls In Mahipalpur O9654467111 Escorts Service
 
(PARI) Call Girls Wanowrie ( 7001035870 ) HI-Fi Pune Escorts Service
(PARI) Call Girls Wanowrie ( 7001035870 ) HI-Fi Pune Escorts Service(PARI) Call Girls Wanowrie ( 7001035870 ) HI-Fi Pune Escorts Service
(PARI) Call Girls Wanowrie ( 7001035870 ) HI-Fi Pune Escorts Service
 
Spark3's new memory model/management
Spark3's new memory model/managementSpark3's new memory model/management
Spark3's new memory model/management
 
Brighton SEO | April 2024 | Data Storytelling
Brighton SEO | April 2024 | Data StorytellingBrighton SEO | April 2024 | Data Storytelling
Brighton SEO | April 2024 | Data Storytelling
 
Data Warehouse , Data Cube Computation
Data Warehouse   , Data Cube ComputationData Warehouse   , Data Cube Computation
Data Warehouse , Data Cube Computation
 
Call Girls In Noida City Center Metro 24/7✡️9711147426✡️ Escorts Service
Call Girls In Noida City Center Metro 24/7✡️9711147426✡️ Escorts ServiceCall Girls In Noida City Center Metro 24/7✡️9711147426✡️ Escorts Service
Call Girls In Noida City Center Metro 24/7✡️9711147426✡️ Escorts Service
 

Multimorbidity Multistate Model

  • 1. Develop a multi-state model to predict multimorbidity of Cardiovascular disease (CVD), Type 2 diabetes (T2D), and Chronic kidney disease (CKD) Research aim By: Manali Ajay Jain MSc Health Data Science (2022-23)
  • 2. Develop a multi-state model to predict multimorbidity of Cardiovascular disease (CVD), Type 2 diabetes (T2D), and Chronic kidney disease (CKD) Research aim Many thanks to Dr Glen Martin for guiding me throughout the research
  • 3. Key elements to understand Prediction models Informs people about their ailment prognosis 01 Multistate models A stochastic process with multiple discrete states that it can occupy at any given time 02 Multimorbidity 03 co-existence of two or more chronic illnesses, where one is not necessarily more significant than the others time Risk predictions of Multimorbidity 04 newly emerging area of research
  • 4. ! The missing pieces ! Multimorbidity studies were mainly performed on groups of individual The validation sample size of the risk predictions of multimorbidity tend to be smaller
  • 5. An attempt to fill the gap This multistate model analysed every single patient Sample size for validation was relatively larger Validation approach were generating stacked transition possibilities graphs
  • 6. Data Source Clinical Practice Research Datalink (CPRD) *Advisory note:  Access to the CPRD dataset was gained only after the completion of the CPRD resource module training test  The UoM also provided a Data Protection and Cyber Security course
  • 7. Foundation of the dataset Data was obtained from Clinical Practice Research Datalink (CPRD) Total data was of 2,714,535 observations with 91 variables Considered only healthy population and required variables to start the analysis This reduced the data to 2,001,735 observations and 74 variables, out of which 30 were various comorbidities and 8 were demographic variables This data was then split in 70:30 ratio for training and testing purposes respectively 70:30
  • 8. Data in a glance Demographic variables  Age, BMI, Cholesterol ration, and SBP were continuous variables  Gender: female, male  Ethnicity: white, mixed ethnic group, asian/asian british, black/african/Caribbean/black british, other ethnic group  Smoking: never, ex, current  Index of Multiple Deprivation: 5 stages, most to least
  • 11. XQuartz 2.8.5 R 4.1.3-gcc830 RStudio 1.3.1073 R libraries  dplyr (Hadley Wickham et al. 2014)  ggplot (Hadley Wickham et al. 2007)  mstate (de Wreede et al. 2011)  calibmsm (Alexander Pate et al. unreleased) Technical Requirements
  • 12. No need of standardization No need of normalization Missing values were treated by single stochastic imputation Splitting was done randomly, without any criteria Before we proceed
  • 13. Let’s begin! • Training dataset was used for model construction
  • 14. Let’s begin! • Training dataset was used for model construction • Population distribution was studied across transitions
  • 16. Let’s begin! • Training dataset was used for model construction • Population distribution was studied across transitions • Dataset was converted into a dataset of class msdata (long format) • id • from • to • trans • Tstart • Tstop • time • status • covariates (the 8 demographic variables)
  • 17. Let’s begin! • Training dataset was used for model construction • Population distribution was studied across transitions • Dataset was converted into a dataset of class msdata (long format) • Covariates were expanded – dummy variables were generated based on the no. of transitions
  • 18. Let’s begin! • Training dataset was used for model construction • Population distribution was studied across transitions • Dataset was converted into a dataset of class msdata (long format) • Covariates were expanded – dummy variables were generated based on the no. of transitions • Time was converted from days to years
  • 19. Let’s begin! • Training dataset was used for model construction • Population distribution was studied across transitions • Dataset was converted into a dataset of class msdata (long format) • Covariates were expanded – dummy variables were generated based on the no. of transitions • Time was converted from days to years • Cox model was fitted which had separate baseline hazards for each of the transitions and no covariates
  • 20. Let’s begin! • Training dataset was used for model construction • Population distribution was studied across transitions • Dataset was converted into a dataset of class msdata (long format) • Covariates were expanded – dummy variables were generated based on the no. of transitions • Time was converted from days to years • Cox model was fitted which had separate baseline hazards for each of the transitions and no covariates • Transition hazards estimates and their associated covariances from each stage were calculated
  • 21. Healthy stage  Healthy -> CKD highest  Healthy -> T2D lowest
  • 22. CVD stage  CVD -> Death highest  CVD -> CVD+T2D lowest
  • 23. T2D stage  T2D -> Death highest  T2D -> CVD+T2D lowest
  • 24. CKD stage  CKD -> Death highest  CKD -> CKD+T2D lowest
  • 25. CVD+T2D stage  CVD+T2D -> Death upper line  CVD+T2D -> CVD+T2D+CKD lower line
  • 26. CVD+CKD stage  CVD+CKD -> Death upper line  CVD+CKD -> CVD+T2D+CKD lower line
  • 27. CKD+T2D stage  CKD+T2D -> Death upper line  CKD+T2D -> CVD+T2D+CKD lower line
  • 28. CVD+T2D+CKD stage  This was created from a simple survfit object since it had just one transition
  • 30. Diving deeper Transition possibilities estimates were also produced These findings demonstrate how a patient's prognosis is influenced by both their initial condition and by the moment used as the beginning point for prediction
  • 31. Stacked transition possibilities Diving deeper  The distance between two adjacent curves represents the probability of being in the corresponding state
  • 32. Diving deeper Transition possibilities estimates were also produced These findings demonstrate how a patient's prognosis is influenced by both their initial condition and by the moment used as the beginning point for prediction To create a lower dimensional representation of the regression coefficients of the whole model, the reduced rank (RR) model was helpful
  • 33. Diving deeper Transition possibilities estimates were also produced These findings demonstrate how a patient's prognosis is influenced by both their initial condition and by the moment used as the beginning point for prediction To create a lower dimensional representation of the regression coefficients of the whole model, the reduced rank (RR) model was helpful RR model generates three items • Alpha • Gamma • Beta
  • 34. Alpha output of RR model Misc ethnic group Ex-smokers More deprived
  • 35. Gamma output of RR model • All the values are mostly negative • The coefficients for this risk score in Gamma are negative and of substantial size for all transitions into death, same for transitions starting from healthy
  • 36. Beta output of RR model • Combined analysis of alpha and gamma • Lower values of Alpha (for instance mixed ethnicity, ex smoker, more deprived) correspond to higher death rates
  • 38. • Built-up model is now fitted into the test dataset • Two follow-up durations were used to evaluate the transition probabilities • 5 years • 10 years • They could then be compared to the train dataset stacked transition probabilities plot It’s TESTING TIME!
  • 39. Stacked transition possibilities after 5 years Testing time  The distance between two adjacent curves represents the probability of being in the corresponding state
  • 40. Stacked transition possibilities after 10 years Testing time  The distance between two adjacent curves represents the probability of being in the corresponding state  Majorly transitions resulting to death is less over the years
  • 41. Was it worth it?? Couldn’t make calibration plots, but somehow managed to get future prediction probabilities 01 01 Resulted in meaningful analysis which can potentially be beneficial for the health sector 02

Editor's Notes

  1. In long format each row represented each transition of every patient