03 ames predictive - ucsf cme · 2019. 10. 25. · research to implementation spine frailty is now...

15
Predictive Analytics: Making Adult Spinal Deformity Surgery Sustainable Christopher P Ames MD Professor of Neurosurgery and Orthopaedic Surgery Director of Spinal Deformity and Spinal Tumor Surgery University of California San Francisco Benzel AANS 2019 COI/Disclosures Chris Ames, MD has financial interests to disclose. Royalty: Biomet Zimmer, Stryker, Depuy Synthes, K2M, Next Spine, Medicrea, Astura Consulting: Medtronic, Biomet Zimmer, Depuy Synthes, K2M, Medicrea Research: Titan Spine, Depuy Synthes ISSG Editorial Board: Operative Neurosurgery Grant Funding: SRS Executive Committee: ISSG How much has implant innovation changed complication rates and improved outcomes since the first multiaxial screw was designed? How much more can spine surgeon technical performance improve? Will the next generation be more technically facile than Ed Benzel or Volker Sonntag? Bounds of human technical performance can be predicted using data analytics Filippo Radicci (Indiana) predicted exactly the new 100m record of Usain Bolt at 9.63 s and using analytics predicts the ultimate bound of human performance is 8.28 s

Upload: others

Post on 20-Jan-2021

1 views

Category:

Documents


0 download

TRANSCRIPT

Page 1: 03 Ames Predictive - UCSF CME · 2019. 10. 25. · Research to Implementation Spine Frailty is now in UCSF EHR Augmented Intelligence EHR work flows Datify the Procedure…. Mirza

Predictive Analytics: Making Adult Spinal Deformity Surgery Sustainable

Christopher P Ames MD Professor of Neurosurgery and Orthopaedic Surgery

Director of Spinal Deformity and Spinal Tumor Surgery

University of California San Francisco

Benzel AANS 2019

COI/Disclosures Chris Ames, MD has financial interests to

disclose. Royalty: Biomet Zimmer, Stryker, Depuy Synthes,

K2M, Next Spine, Medicrea, Astura Consulting: Medtronic, Biomet Zimmer,

Depuy Synthes, K2M, Medicrea Research: Titan Spine, Depuy Synthes ISSG Editorial Board: Operative Neurosurgery Grant Funding: SRS Executive Committee: ISSG

How much has implant innovation changed complication

rates and improved outcomes since the first multiaxial screw

was designed?

How much more can spine surgeon technical performance

improve?

Will the next generation be more technically facile than Ed Benzel or Volker Sonntag?

Bounds of human technical performance can be predicted using data analytics

Filippo Radicci (Indiana) predicted exactly the new 100m record of Usain Bolt at 9.63 s and using analytics predicts the ultimate bound of human performance is 8.28 s

Page 2: 03 Ames Predictive - UCSF CME · 2019. 10. 25. · Research to Implementation Spine Frailty is now in UCSF EHR Augmented Intelligence EHR work flows Datify the Procedure…. Mirza

Why is disruptive technology needed now?

53 million people over age 65 now and increasing

80 million over 65 by 2050

60% prevalence of spinal deformity (cobb greater than 10 degrees)

32 million people with ASD in US

Economic Burden of Aging Musculoskeletal System

Total Health care cost 3.5 trillion 2017

Musculoskeletal disease cost >800 billion/year

Spinal Deformity $80 billion (2011)

Number of USA ASD Procedures increased by 157% in 10 years

0

50,000

100,000

150,000

200,000

250,000

1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009

Number of discharges with at least one diagnosis of spinal curvature' (ICD‐9 code 737.0 to 737.9)

Children

Adult

Healthcare Costs and Utilization Project (HCUP http://hcupnet.ahrq.gov),

Page 3: 03 Ames Predictive - UCSF CME · 2019. 10. 25. · Research to Implementation Spine Frailty is now in UCSF EHR Augmented Intelligence EHR work flows Datify the Procedure…. Mirza

Do not go gentle …

Modern expectations of high function in old age

Complexity IncreasingUtilization of wedge osteotomies

200

300

400

500

600

700

800

2003 2004 2005 2006 2007 2008 2009 2010

# Wedge Osteotomies(77.29 ICD‐9‐CM)

0%

10%

20%

30%

40%

50%

60%

70%

80%

90%

100%

2003 2004 2005 2006 2007 2008 2009 2010

Wedge Osteotomies by age group

>65

45‐64

18‐44

Increases on 275% in less than 10 years~250 procedures in 2003~700 procedures in 2012

Increase proportion of patients >65yo~20% in 2003~40% in 2012

Surgery improves disability

Disease State PCS; mean NBS

points

MCS; mean NBS

pointsUS Total Population

50 49.9

US Healthy Population

55.4 52.9

ASD 40.9 49.4Back Pain 45.7 47.6Cancer 40.9 47.6Depression 45.4 36.3Diabetes 41.1 47.8Heart Disease 38.9 48.3Hypertension 44.0 49.7Limited Use Arms Legs

39.0 43.0

Lung Disease 38.3 45.6

Spine J 2014

Page 4: 03 Ames Predictive - UCSF CME · 2019. 10. 25. · Research to Implementation Spine Frailty is now in UCSF EHR Augmented Intelligence EHR work flows Datify the Procedure…. Mirza

Failures destroy cost effectiveness

Failure Prevention

Double pelvis

Double rods

VCR rod

BMP-2

Ligament repair

Vertebroplasty

2 surgeons

Plastic Surgery

Eliminates provider variability Appropriateness criteria for all surgeons Transparency Multidisciplinary Best practices 3 fold improvement in the worst complications 12 fold decrease in return to surgery in the first three months postop

Page 5: 03 Ames Predictive - UCSF CME · 2019. 10. 25. · Research to Implementation Spine Frailty is now in UCSF EHR Augmented Intelligence EHR work flows Datify the Procedure…. Mirza

Collective Intelligence

The 56 person group average better than any individual and came within 3% of total

Only 1 individual “guessed” better

Eliminates outliers

Reduce Complications by Limiting Care

Of course we decrease complications by operating on more robust patients

But, patients who experience major complications still do well

Most disabled patients with high frailty scores improve the most

Approved:Low risk

High Risk butGood Outcome

Older had Greater improvement after PSO in general health

Big Data-Datify the Patient

“Painting true picture of patient with many data points”

Page 6: 03 Ames Predictive - UCSF CME · 2019. 10. 25. · Research to Implementation Spine Frailty is now in UCSF EHR Augmented Intelligence EHR work flows Datify the Procedure…. Mirza

FICO Score….Preop Risk Score?

Results

25%

44%

62%

0%

10%

20%

30%

40%

50%

60%

70%

Not Frail Pre-Frail Frail

Major Complication Incidence

Pearson Chi2 = 29.7 Pr = 0.000

Frailty is a Predictive ROS 1) Bladder incontinence☐ Yes☐ No

2) Bowel incontinence☐ Yes☐ No

3) Leg weakness☐ Yes☐ No

4) Loss of Balance☐ Yes☐ No

5) Do you currently smoke?☐ Yes☐ No

6) Are you currently on disability?☐ Yes☐ No

7) Current height and weight (BMI)☐ <18.5☐ 18.5-30☐ >30

8-18) Medical History (check all that apply):☐ Cancer☐ Heart Disease☐ Diabetes☐ Hypertension☐ Liver disease☐ Lung disease☐ Kidney disease☐ Osteoporosis☐ Peripheral vascular disease☐ Prior DVT/PE/Stroke (blood clot)☐ Greater than 3 medical problems

19) Would you say your current health is:☐ the same or better than last year☐ worse than this time last year

20) Would you say your current health is:☐ Excellent or Good☐ Fair or Poor

How much difficulty do you have with each of the following activities:

21) Climbing 1 flight of stairs☐ Moderate/Little/No difficulty☐ Extreme difficulty/Require assistance or assistive device/Unable to do

22) Driving a car☐ Moderate/Little/No difficulty☐ Extreme difficulty/Require assistance or assistive device/Unable to do

23) Getting dressed☐ Moderate/Little/No difficulty☐ Extreme difficulty/Require assistance or assistive device/Unable to do

24) Getting in and out of bed☐ Moderate/Little/No difficulty☐ Extreme difficulty/Require assistance or assistive device/Unable to do

25) Walking 100 yards☐ Moderate/Little/No difficulty☐ Extreme difficulty/Require assistance or assistive device/Unable to do

26) Get around the house without an assistive device☐ Moderate/Little/No difficulty☐ Extreme difficulty/Require assistance or assistive device/Unable to do

27) Performing light activity (vacuuming, playing golf)☐ Moderate/Little/No difficulty☐ Extreme difficulty/Require assistance or assistive device/Unable to do

28) Bathing yourself☐ Moderate/Little/No difficulty☐ Extreme difficulty/Require assistance or assistive device/Unable to do

29) Normal work or schoolwork or housework☐ Moderate/Little/No difficulty☐ Extreme difficulty/Require assistance or assistive device/Unable to do

30) Lift medium weight objects☐ Moderate/Little/No difficulty☐ Extreme difficulty/Require assistance or assistive device/Unable to do

31) Travel more than 1 hour☐ Moderate/Little/No difficulty☐ Extreme difficulty/Require assistance or assistive device/Unable t

32) Perform all personal care☐ Moderate/Little/No difficulty☐ Extreme difficulty/Require assistance or assistive device/Unable t

How often in the last month have you experienced the following:

33) Feeling downhearted and depressed☐ All or most of the time☐ Some, little or none of the time

34) Feeling so down in the dumps you cannot cheer up no matter what you☐ All or most of the time☐ Some, little or none of the time

35) Feeling tired/exhausted☐ All or most of the time☐ Some, little or none of the time

36) Feeling worn out/used up☐ All or most of the time☐ Some, little or none of the time

37) Difficulty remembering things you used to have no trouble with☐ All or most of the time☐ Some, little or none of the time

38) Feeling like your thinking is slow or clouded☐ All or most of the time☐ Some, little or none of the time

39) What is your current level of activity?☐ Bedridden or primarily no activity☐ Light to full sports/activities

40) How is your social life?☐ My social life is restricted to my home or non-existent☐ My social life is normal or mildly restricted

Page 7: 03 Ames Predictive - UCSF CME · 2019. 10. 25. · Research to Implementation Spine Frailty is now in UCSF EHR Augmented Intelligence EHR work flows Datify the Procedure…. Mirza

Research to ImplementationSpine Frailty is now in UCSF

EHR

Augmented Intelligence EHR work flows

Datify the Procedure…. Mirza ASD-S ASD-R

R2 EBL 0.22 0.28 0.34 p value

EBL 0.0012 <0.001 <0.001

R2 Op time

0.18 0.26 0.34

p value OP time

0.007 0.0002 < 0.0001

Neurosurgery 2017

Ok for RISK but ….What drives OUTCOMES?

Previous work has sought answers in correlations

Outcome driven by alignment

But what does the new Information Age and AI tell us??

There is much more

Page 8: 03 Ames Predictive - UCSF CME · 2019. 10. 25. · Research to Implementation Spine Frailty is now in UCSF EHR Augmented Intelligence EHR work flows Datify the Procedure…. Mirza

Baseline SVA vs ODI

All pts, op and nonop, n=1622 R2 = .19

2yr SVA fused to Pelvis vs ODI

All 2yr follow up Op pts, n= 502 R2 = .04

Predictive Analytics

Pt

Apical FusionT10-pelvisT3-pelvis PSO

Frailty

+

All data fields analyzed separately 25% MCID pain10% MCID appearance50% revision 5% medical complication90% play tennis

60% MCID pain80% MCID appearance10% revision25% major complication5% play tennis

ComplicationAvoidance

First Generation Models-Q/O

3 successful binary output models constructed Proximal junctional kyphosis/failure *Spine 2016

Major intra/periop complications *JNS Spine 2017

Oswestry Disability Index (ODI) minimal clinical important difference *Spine Deformity 2018

Methods

5 different bootstrapped decision trees

Internal validation 70:30 data split for training/testing

Accuracy, and the area under a receiver operator characteristic (ROC) calculated

Page 9: 03 Ames Predictive - UCSF CME · 2019. 10. 25. · Research to Implementation Spine Frailty is now in UCSF EHR Augmented Intelligence EHR work flows Datify the Procedure…. Mirza

Second generation models-Q/V

Pseudoarthrosis (with/without biologics as modifiable variable) 91% accuracy

LOS model –first attempt at a continuous output model (from yes/no to 3,4, 5,6 days etc) 75% accuracy

Cost effectiveness model: what if we used our MCID model for patient selection ?

• World Neurosurgery 2018• Clinical Spine Surgery 2018• Neurosurgical Focus 2018

Results: QALY

Surgical Decisions according to model vs Surgical Decisions by Surgeon – Simulation

Greater Qaly Gain using model

2019 : Results in Combined Dataset patients from 17 hospitals

ISSG and ESSG Data Time frame: 2008-2015 >1600 patients > 2000 patient years 17 sites, 11 US, 2 Spain, 2 Turkey, 1 France and 1

Switzerland 35 surgeons R (Miquel Serra PhD) Kernel Analytics for Web Deployment and Machine

Learning

Page 10: 03 Ames Predictive - UCSF CME · 2019. 10. 25. · Research to Implementation Spine Frailty is now in UCSF EHR Augmented Intelligence EHR work flows Datify the Procedure…. Mirza

Complications, Reop, ReadmissionAccepted JNS Spine 2019

Individual informed consent

Individual cumulative risk estimates for MC at 2y ranged from 3.9%-74.1%

Surgical invasiveness (LIV-pelvic fixation, length of fusion, prior surgery), age, sagittal deformity, patient frailty (walking and lifting capacity) and blood loss most strongly predict MC

* Pellise et al ISSG ESSG analytics collaboration SRS 2019 submitted

Dynamics of Complications Prediction

Before Surgery After SurgeryBlood & Time

Discharge

Patient Characteristics

Surgery Characteristics

Hospital

Surgeon

64% 70% 73%

65% 71% 75%

79%74%70%

80%79%76%

Identify pts at risk Of bounce back

** predictive analytics-driven interventions directed at high-risk individuals reduced emergency room and specialist visits

Major Complication Risk Calculator 2018v1

Patient-related factors, >1/3 of which are potentially modifiable, account for 55% of the predictive model weight.

Surgeon and site represent 4-10% for MC, but are most relevant for READMIT and UNPLAN

Page 11: 03 Ames Predictive - UCSF CME · 2019. 10. 25. · Research to Implementation Spine Frailty is now in UCSF EHR Augmented Intelligence EHR work flows Datify the Procedure…. Mirza

Baseline & outcome heterogeneity, n=2,207, 4078.57 observation-years

Outcomes—Are YOU average?

* Only 5% of patients had “average improvement”

Can we Predict Outcome?

75 variables were used in the training of the models including demographic data, comorbidities, frailty, modifiable surgical variables, baseline health-related quality of life, coronal and sagittal radiographic parameters, hospital and surgeon

8 different prediction algorithms were trained with 3-time horizons, baseline-1year, baseline-2years and 1year-2years

SRS 22R, DOMAINS AND TOTAL, ODI, SF-36 PCS and MCS

* Spine 2019

Top Outcome Predictors:

Up to 82.5 % predictive power

Preop scores most important

Surgeon and Site 1.8% of variation

Calculator Output SRS 22

Page 12: 03 Ames Predictive - UCSF CME · 2019. 10. 25. · Research to Implementation Spine Frailty is now in UCSF EHR Augmented Intelligence EHR work flows Datify the Procedure…. Mirza

BUT, Patients don’t want to know how their SRS Total will improve!

Will I walk better?

Will I be able to return to work?

Will my pain improve?

Will my mood improve?

Will I feel better about how I look?

Will I really be satisfied with surgical treatment?

Individual SRS 22 responses with wait for surgery simulations

75-85% Predictive Power

The Age of Artificial Intelligence Driven Decision Support

Every patient is different and represents a unique combination of frailty, disability, mental health …

Every surgeon is different and every surgery plan is unique ….

How the Machine sees it

HOW THE SURGEON SEES IT

Frailty= .5ODI 42CCI 4ASA 3BMI 25BMD -1.5Cc: low back painMed: norco

SVA 12cmPI-LL 28PT 35TK 55CSVA 0

>100 variables

Page 13: 03 Ames Predictive - UCSF CME · 2019. 10. 25. · Research to Implementation Spine Frailty is now in UCSF EHR Augmented Intelligence EHR work flows Datify the Procedure…. Mirza

A.I. Nearest Neighbor Recall Clusters and R/B

Spine 2019

New AI driven ASD Classification

Outcome and Complications

Based on Clustering of Surgical Types and Patient Types

Rather than a classification based on R2 to one parameter class which varies by age

Results: Outcomes Grid

52

Page 14: 03 Ames Predictive - UCSF CME · 2019. 10. 25. · Research to Implementation Spine Frailty is now in UCSF EHR Augmented Intelligence EHR work flows Datify the Procedure…. Mirza

Results: Efficiency Plots

Preop Risk vs Benefit Plotting

53

Preoperative Prediction of Cost and Catastrophic Cost in Adult Spine Deformity Surgery: Feasibility Analysis of Predictive Analytics to Establish 90 day

bundled payments Models Predicted 90 day dollar

cost with 70.1 % accuracy

Out of the total variance explained, 22.63% was only explained by site and surgeon fixed-effects

The top 4 predictors of cost by order were; surgeon, number of levels fused, IBF, site

CC > $ 100,000 was predicted preoperatively with a 90.41% accuracy

Predicting ASD Surgeries That Exceed Medicare Allowable Payment Thresholds

AUC 94.48%)

56.8% increased likelihood getting reimbursed more than the cost of surgery (iEOC<MA) if done at an academic center.

SRS 2019

Where is ASD? & the ladder

56

The Ladder of Causation – J. Pearl

ASD surgery, PubMed literature 1950-2018, n=6,621 articles

Page 15: 03 Ames Predictive - UCSF CME · 2019. 10. 25. · Research to Implementation Spine Frailty is now in UCSF EHR Augmented Intelligence EHR work flows Datify the Procedure…. Mirza

Clustering of patients v2 – “Young coronal” vs “worst patients”

n=19316%27.55-6.641.69

48.8217.263.47

44.96

47.14

n=11847%65.57

140.4971.2438.4257.272.39

43.25

25.31

Clinical Trials

N=729 N=35

Clustering of patients – Effectsize & Power for trials

Pseudoarthrosis Trends ISSG—Average or Benchmarking

THANK YOU !!!