clinical decision making with machine learning
TRANSCRIPT
Clinical decision making with Machine Learning
Oleksii Barash, Ph.D.
Reproductive Science Center of San Francisco Bay Area
Disclosure
We have no financial relationship with any commercial interest related to the content
of this activity
Reproductive Science Center of the SF Bay Area
• Founded in 1983• In top 30 largest IVF (In Vitro
Fertilization) clinics in USA*• In top 20 clinics with the best clinical
outcomes*• Over 2000 treatment cycles (fresh and
frozen) in 2017
* - CDC Report 2015
What is infertility?
WHO - Infertility definitions and terminology
• Failure to conceive within 12 months of regular unprotected intercourse.
• Primary or secondary.
• 84% of couples will conceive within 1 year and 92% within 2 years.
Scope of the problem
• Infertility affects 12% of the reproductive age population in the US (≈12 million people)
• Infertility affects men and women equally
• More than 50% of infertility patients will have a baby with treatment
• Over 1.5M IVF cycles per year worldwide (≈ 200,000 in USA) in 2014
• Cost of one IVF cycle in US: 10K – 100K
Global fertility Market
Equity Research Reports, 2012
Key growth drivers:1. Aging and Infertility2. Increasing prevalence of Obesity3. Cultural shifts (“Celebrities” and LGBTQ)
Unreasonable expectations…
• 59% of childless women aged 35‐39 still planned tohave a baby• 30% aged 40‐45 did too!(Sobotka, Austrian survey data)
• 58% said they wanted 2 children (aged 21‐23)• Only 36% had achieved that by age 36‐38(Smallwood and Jeffries,UK Population Trends)
Biological clock
Speroff, 2004
IVF treatment overview
IVF is essentially manufacturing
• Complex multidimensional process;
• Constant intake flow of the patients;
• Cutting edge labor and equipment;
• Hundreds of contributing factors (Lab + Clinical);
• Every patient is unique – limited standardization
Ultimate goal –
single healthy baby
Manufacturing outcome prediction
IVF produces a lot of data?
• Main shareholders are open to cutting edge technologies
• Wide Electronic Medical Records adoption;
• IoT devices – sensors, incubators, microscopes, lasers
• Morpho-kinetics (time-lapse)
• Preimplantation Genetic Testing
• “Omics”
Transforming data into knowledge
• Increasing number of publications
• Retrospective and small
• Rare RCTs
Evidence based medicine
Conscientious, explicit and judicious use of current best evidence in making decisions about the care of an individual patient.*
* - Sackett. BMJ 1996;312:311-2
Meta-Analysis
Fertility and Sterility 2010; 94:936-945
• Small number of samples
• Diverse experimental conditions
Personalized decisions to be made in each IVF cycle
• Hormonal Stimulation protocol / dosage / duration
• Lutheal support
• How many embryos to transfer (1, 2 or 3)
• Embryo selection for the transfer (morphological and genetic)
• Financial products (risk sharing programs, money back)
Do You Know Your Embryo Biology?
Time-lapse and Machine learning
Embryo selection for the transfer
• From 1 to 30+ embryos per IVF cycle
• Many morphological and kinetic features per embryo
• Critical choice – no second chance
Traditional embryo evaluation
M. Montag, 2014
Time-lapse monitoring
M. Montag, 2014
Non-invasive imaging and predictions
EEVA (Early Embryo Viability Assessment)
• Xtend algorithm:– over 1,000 combinations of potential parameters
– includes egg age, cell count and Post P3 analysis – which measures cell activity after the four cell stage
– Post P3 is the result of a proprietary analysis based on 74 computer-based attributes that are combined into one parameter
– each embryo gets a developmental potential score ranging from 1 (highest) to 5 (lowest).
– 84% specificity vs 52% by traditional assessment
– The odds ratio of predicting blastocyst formation is 2.57 vs 1.67 by traditional assessment
EEVA (Early Embryo Viability Assessment)
Unusual cleavage patterns
EEVA Xtend algorithm
EEVA Xtend algorithm
Preimplantation Genetic Testing
Oocyte aneuploidy and maternal age
Handyside, 2015
• All primary oocytes are formed before baby-girl is born.
Preimplantation Genetic Testing
Handyside, 2015
DNA sequencing
DNA flow cell
Preimplantation Genetic screening
National Human Genome Research Institute, 2014
• Log scale!
Preimplantation Genetic Testing
National Human Genome Research Institute, 2017
• Log scale!
Single Nucleotide Polymorphism (SNP) algorithm
• 300,000 probs per embryo
• Per chromosome confidence
• Highly accurate and comprehensive results
• Parental genomic information
• Cumulative distribution function (cdf) curves
Cumulative live birth rate after SET,PGS, N=1024
# Cycles Live births Total ETs 1-l/n S(t)
1 178 313 0.43131 0.56869
2 22 59 0.627119 0.72952
3 7 15 0.533333 0.85574
4 1 2 0.5 0.92787
5 1 1 0 1
Presented by RSC team at ASRM 2016
Gene expression, stage & multinucleation
ML-based solutions for IVF
Univfy
Univfy algorithm:• Takes patient data
• Predictive model
based on 13,000 IVF
cycles;
• Chances for positive
outcome
• Chances of twins if 2
embryos were
transferred
Celmatix
Celmatix algorithm:
• Incorporated in our EMR
(ARTworks)
• Software as a service
(SaaS model)
• Data analytics platform to
help optimize patient
management and
counseling
Celmatix - Fertilome
Celmatix algorithm:• 25,000 peer-reviewed studies• 1,713 genes• 427 variant/diagnosis combinations• 201 gene-diagnosis combinations• 32 target genes in the kit
Endometrial Receptivity Analysis (ERA) by Igenomix
Patented in 2009: PCT/ES 2009/000386
Customized microarray (238 genes)
Bioinformatic analysis of data obtained by the customized microarray
Classification and prediction from gene expression.
Endometrial Receptivity Analysis (ERA)
Receptive
Model Classifies the Molecular Receptivity
Status of the Endometrium
Post-ReceptivePre-Receptive
0%
10%
20%
30%
40%
50%
60%
70%
80%
90%
100%
2010 2011 2012 2013 2014 2015 2016
% o
f cy
cles
ETx1
ETx2
ETx3
ETx4
ETx5
~ Average age – 36.0 ± 5.5 y.o.
~ 39.3% of all patients are over 38 y.o.
SET rate in non-PGT cycles(2010-2016), fresh D5 ET, N=3925
Preimplantation Genetic Testing (PGT) at RSC
~ SET frequency in PGS IVF cycles (average age – 37.5 ± 4.29 y.o. ) – 89.9%
FISH SNP – aCGH - NGS
661
1387
4
735
0
200
400
600
800
1000
1200
1400
0
200
400
600
800
1000
1200
1400
1600
2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017
Nu
mb
er o
f IV
F cy
cles
Total volume
PGT cases
78
Live birth rate
Maternal age
Number of embryos for
biopsy
Morphology of the
embryos
SET vs eSET
D5 vs D6
BiopsyTotal
gonadotropin dosage
Number of previous
failed cycles
Number of normal
embryos per cycle
Number of eggs
Euploidy rate
Presented by RSC team: ASRM 2016, 2015, 2014; ESHRE 2015, 2016; PCRS 2014, 2015, 2016; PGDIS 2015, 2017
Factors affecting PGT outcomes
Live birth rate
Embryo_Age
Blastulation_rat
eDonor_
eggs Euploidy_rate Number
_of_normal
d5_to_total_rat
io Total_day_5_bx
Total_day_6_bx
Total_for_biosy
Bx_Day
Emb_Expansion
ICM
TE
Gender
Best_Embryo_For_ET
Elective_SET
Cycle_number
Number_of_Foll
icles
Zygotes
Fert_rate
Unfert
M2
M1
GV
ATR
Multi_PN
PN_1
Degenerated
Cleaved
Cleavage_rate
Number_ext_cu
ltureGood_ext_cultu
reNumber_to_blNumber
_CryoGood_d3_rateTVA_M
D
Number_of_tarnsfers_to_deliv
ery
Semen_Source
Fresh_Frosen_s
p
BMI
PATIENTTYPET
EXT
NO_OF_DAYS
SUMSTIM
ASPIRATED_OOCYTES
HCG_DRUG
TOTAL2PN
GRAVIDITY
PREM
TERM
SAB
BIOCHEMICAL
LIFETIME_SMO
KED
PRIORIVF
PRIORFET
PRIORIUI
HEIGHT
WEIGHT
PRIMARYDIAGN
OSIS
SEMENSOURCE
FSHLEVEL
NEAREST_AMH
MED1
Peak_E2
TOTALIUS
FOLLICLES_BIGGER_THAN_14
ASPIRATED_OOCYTES
NO_FROZEN
NO_VIT
INITIALCONSULT_PREM
INITIALCONSULT_GRAV
IDITY
INITIALCONSULT_SAB
INITIALCONSULT_TERM
INITIALCONSULT_BIOCHEMICA
L
Stim protoco
l
Factors affecting PGT outcomes
More factors?
Bias?
Reproducibility of the
results?
Factors affecting PGT outcomes
What if we can evaluate ALL available factors?
What if we can assess ALL available factors?
20 factors:
202 = 400 plots
381 factors
3812 = 145,161
plots
20 x 20
Machine Learning
Algorithm
Timeframe: Jan 2013 – Jul 2017
Retrospective analysis
Number of PGS transfers: 918
Average age: 35.6 ± 4.8
ONLY Single embryo transfers
Machine learning methods:
• GLM (Generalized Linear Models)
• RPART (Classification and Regression Trees)
• GBM (Generalized Boosted Regression Models)
IVF labEmbryo_Age
Blastulation_rateDonor_eggs
Euploidy_rateNumber_of_normald5_to_total_ratioTotal_day_5_bxTotal_day_6_bxTotal_for_biopsy
Bx_DayEmbryo_Morphology
ExpansionICMTE
GenderClinical_Outcome
BEST_ EMBRYO_FOR_ETELECTIVE_SET
Number_of_tarnsfers_to_deliveryBiopsy tech
CYCLE #PEAK E2TVA MD
TVA TECH# Follicles >12 mm
# EGGS# INSEM
# 2PN % FERT
# UNFERT#M2 or mature
# INT# IMM# ATR
# > 2PN# 1PN# DEG
FERT CK TECHICSI TECH
SEMEN SOURCEFRESH/FROZEN SP
CLEAVED% CLEAVED
HATCH TECH# EXT CULTURE
# GOOD EXT CULT# TO BLAST
# CRYO% OF GOOD QUALITY EMBRYOS
…
clinicalBMI
PRIMARY_DXPATIENTTYPETEXT
LUPRONSTIM
GNRHAMED1
SUMSTIMTRANSFER_DATE
HCG_DRUGGRAVIDITY
PREMTERMSAB
BIOCHEMICALPATIENTRACE
LIFETIME_SMOKEDSMOKING_FREQ
PRIORIVFPRIORFETPRIORIUIHEIGHTWEIGHT
STIMPROTOCOLLUPRONPROTOCOLPRIMARYDIAGNOSIS
SECONDARYDIAGNOSISTERTIARYDIAGNOSIS
SEMENSOURCEPATIENTTYPE
FSHLEVELE2LEVEL
NEAREST_AMHAFC
MED1MED2MED3MED4
MAX_E2TOTALIUS
FERT_METHOD_ICSIFERT_METHOD_IVF
INITIALCONSULT_PREMINITIALCONSULT_GRAVIDITY
INITIALCONSULT_SABINITIALCONSULT_TERM
INITIALCONSULT_BIOCHEMICALStim protocol
…
381 variables per SET:
Lab factors, 918 SETs
Pregnant, %Non-Pregnant, %
% of total SETs
Yes No
Lab + Clinical, 918 SETs
Relevant feature selection algorithm* (Lab factors)
*Number of CART trees = 100
Relevant feature selection algorithm* (Lab + Clinical)
*Number of CART trees = 100
Building the model to predict IVF outcome
Only weak predictors are present
Relatively small sample size (10K)
A lot of features (>300)
Accuracy of predictions = 0.73AUC = 0.76 (Sensitivity/specificity balance)
Building the model to predict IVF outcome(PGT only)
• Benchmark AUC – Starting point• Feature engineering• Feature importance• Feature transformations• Non-important features• Model interpretation
Building the model to predict IVF outcome(FETs only)
Relative Importance
Feature Description
0.95784403_NumCatTE_Prior full term_Prior pre-term_TE_0
Out-of-fold mean of the response grouped by: ['Prior full term', 'Prior pre-term', 'TE'] using 5 folds (numeric columns are bucketed into 25 equally populated bins)
0.55907
164_CV_TE_# EXT CULTURE_FACNAME_LUPRON_PGD.1_Retrieval MD_Retrievaltechnician_Thawingtechnician_0
Out-of-fold mean of the response grouped by: ['# EXT CULTURE', 'FACNAME', 'LUPRON', 'PGD.1', 'Retrieval MD', 'Retrieval technician', 'Thawing technician'] using 5 folds
0.35233 217_BIOCHEMICAL BIOCHEMICAL (original)
Ongoing PR after SET with different blastocyst morphology (918 SETs)
Blastocyst morphology
AA AB BA BB B-/-B p-Value
Total SETs 266 292 33 232 95 n/a
Positive hCG 222 240 26 178 61 n/a
Negative hCG 44 52 7 54 34 n/a
Biochemical 25 23 1 36 16 n/a
Miscarriages 18 17 3 14 6 n/a
Ongoing PR per ET, % 67.3 68.5 66.7 55.2 41.1 p<0.05
Birth outcomes (2013-2015)
107 135 8 117 61 n/a
Live births 66 82 4 56 26 n/a
Live birth rate, % 61.7 60.7 50.0 47.9 42.6 p<0.05
http://www.ivfbigdata.com/pgt-calculator/
eSET FUTURESET vs DET in PGS cycles (2013-2016)
ETx1 ETx2 P-value
Total FETs 569 89
Positive HCG 442 78
Negative HCG 127 11
Ongoing pregnancies 335 66
Ongoing PR, % 58.9% 74.2% p<0.00599
Live birth rate,% 53.5% 71.6% p<0.00523
Twins 3 33 (1 triplet)
Twin rate 0.9% 50.0% p<0.00001
Presented by RSC team at ASRM 2016
The 5 Steps Towards Evidence Based Practice
1. Ask the right clinical question: Formulate a searchable question
2. Collect the most relevant publications: Efficient Literature SearchingSelect the appropriate & relevant studies
3. Critically appraise and synthesize the evidence.4. Integrate best evidence with personal clinical expertise, patient preferences and values:
Applying the result to your clinical practice and patient.5. Evaluate the practice decision or change:
Evaluating the outcomes of the applied evidence in your practice or patient.
The 5 Steps Towards Evidence Based Practice
1. Ask the right clinical question: Formulate a searchable question
2. Collect the most relevant DATA:
Efficient Literature SearchingSelect the appropriate & relevant studies
3. Critically appraise and synthesize the evidence.4. Integrate best evidence with personal clinical expertise, patient preferences and values:
Applying the result to your clinical practice and patient.5. Evaluate the practice decision or change:
Evaluating the outcomes of the applied evidence in your practice or patient.
The current problem with the models: A vs B
Conclusion
1. Machine learning is not yet widely used in clinical practice
2. Augmented decision making with machine learning
3. Auto ML for rapid experimentation knowledge discovery
Thank you!
Lab:
K. A. Ivani, Ph.D.
O. O. Barash, Ph.D.
N. Huen
S. C. Lefko
C. MacKenzie
J. Ciolkosz
E. Homen
E. Jaramillo
MDs:
L. N. Weckstein
S. P. Willman
M. R. Hinckley
D. S. Wachs
E. M. Rosenbluth
S. P. Reid
M. V. Homer
E. I. Lewis