Test-free Zero-contact Point-of-Care Universal Screening of Complex Diseases

Ishanu Chattopadhyay, PhD

Assistant Professor of Biomedical Informatics & Computer Science

University of Kentucky

ishanu_ch@uky.edu

Applied Healthcare Summit 2026

Zero-Burden Co-morbid Risk Score (ZCoR*)

Zero Burden Risk Assessment (ZeBRA)

  • Universal point-of-care screening via AI-driven pattern recognition
  • No new tests or blood-work
  • Uses routine data (EHR) already in patient file
  • No specific data demands

CKD

PF

ZeBRA

ICD

Enable early diagnosis

Seamless background integration with EHR workflows

Primary care

*Onishchenko, Dmytro, Robert J. Marlowe, Che G. Ngufor, Louis J. Faust, Andrew H. Limper, Gary M. Hunninghake, Fernando J. Martinez, and Ishanu Chattopadhyay. "Screening for idiopathic pulmonary fibrosis using comorbidity signatures in electronic health records." Nature Medicine 28, no. 10 (2022): 2107-2116.

Raising Flags before patient or their doctor notice symptoms

downstream care modulation

widely published, retrospectively validated*

TimestampedDiagnostic procedural codes & prescriptions

MASH

Rx

Px

Publications

 

AI-driven Test-Free Prediction of ICU Admission, Insulin Dependence, and Exocrine Dysfunction after Acute Pancreatitis

Under Review

Technology Overview

2. Conventional AI attempts to model the physician

Current State of Art

1. Use of AI in point-of-care diagnostic workflow is limited

ZeBRA

  1. Use under-utilized diagnostic modalities
  2. Discover co-morbidity patterns
  3. Go beyond know risk factors
  4. Personalized risk patterns

*Chattopadhyay, Ishanu, and Hod Lipson. "Abductive learning of quantized stochastic processes with probabilistic finite automata." Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences 371, no. 1984 (2013): 20110543.

Curated Disease-agnostic Features | Odds ratio dictionaries combined with multi-stage LGBMs | Specialized HMM based Longitudinal Tracking*

Predictive AI platforms, including those from Merative, PathAI, Tempus, Google Health, and Microsoft, often rely on imaging data for early detection.

Standard AI

State of the art screening approaches are inadequate for point-of-care diagnosis

Non-specific Symptoms                                                    

Pulmonary Fibrosis

Rare disease

~5 in 10,000

Post-Dx

Survival

~4 years

At least one misdiagnosis

~55%

Two or more misdiagnosis

38%

Initially attributed to age related symptoms:

72%

  • >50 years old
  • more men than women

shortness of breath

dry cough

doctor can hear velcro crackles

Cannot always be seen on CXR

PCP workflow demands

Problem

  • Late/missed diagnosis
  • No universal point-of-care screening

~ 4yrs

current  survival ~4yrs

~ 4yrs

current clinical DX

ZeBRA    screening

Onishchenko, D., Marlowe, R.J., Ngufor, C.G. et al. Screening for idiopathic pulmonary fibrosis using comorbidity signatures in electronic health records. Nat Med 28, 2107–2116 (2022). https://doi.org/10.1038/s41591-022-02010-y

n=~3M

AUC~90%

Likelihood ratio ~30

Predictive Performance*

High AUC across high and low risk sub-cohorts

Highlights:

  • 1 yr out AUC ~88%
  • Positive Likelihood ration ~40

*Onishchenko, D., Marlowe, R.J., Ngufor, C.G. et al. Screening for idiopathic pulmonary fibrosis using comorbidity signatures in electronic health records. Nat Med 28, 2107–2116 (2022). https://doi.org/10.1038/s41591-022-02010-y

Model

time

Patient A

Patient B

Personalized Risk Factors

& Patient Journeys

ZeBRA score

EHR integrated tool to continuously chart risk over time

Personalized Risk and Patient Journey

Comorbidity Spectra

Interstitial Lung Disease (ILD)

US prevalence: 1 in 500

IPF prevalence:  10-25% of ILD

ILD

IPF

Interstitial Lung Disease (ILD)

US prevalence: 1 in 500

IPF prevalence:  10-25% of ILD

ILD

Age group: 50-85 years old  

Observation window:  

1+ years of records   

Prediction window: 1 year  

Used dataset size:   

Case: 25.4k, Control: 15.1M 

 

Performance (95% Specificity):  

Males:  

AUC 82.2% (82.0%, 82.5%)  

Sensitivity 39.7% (39.3%, 40.1%)  

Positive LR: 7.81 (7.85, 8.01)  

Negative LR: 0.64 (0.64, 0.63)  

  

Females:  

AUC 82.1% (81.8%, 82.3%)  

Sensitivity 39.1% (38.7%, 39.5%)  

Positive LR: 7.77 (7.74, 7.90)  

Negative LR: 0.64 (0.65, 0.64) 

Interstitial Lung Disease (ILD)

US prevalence: 1 in 500

95% specificity/39% sensitivity99% specificity/17% sensitivity99.5% specificity/12.5% sensitivity
Additional ILD diagnoses from ZeBRA546238175
Total ILD diagnoses per year with ZeBRA746438375
Additional transplant-eligible patients with ZeBRA1647153
Expected False Positives29,9305,9862,993
Net annual contribution margin*$46,613,500$12,706,700$7,703,350

Case Study: University of Kentucky Heath-care (UKHC)

Patient population: 600K unique patients per year
Current ILD diagnoses: 200 per year

* diagnostic workup margin (CT+PFT): $950, lunng transplant contribution margin: $120,000, incremental program operating cost: -$1.5M

Reduce Screen failures by ZeBRA-leveraged Cohort  Selection

PF clinical trails have 30-60% screen failure rate*

ZeBRA can reduce screen failure < 8%

*Strambu, Irina Ruxandra, Liesbeth Fagard, Paul Ford, Tom Van Der Aa, Angela De Haas-Amatsaleh, Eva Santermans, and Christian Seemayer. "Idiopathic pulmonary fibrosis (IPF): observations from a Phase 2 trial of GLPG1205 (PINTA)." (2020).

  • Reduce screening-related costs by approximately $1M to $3.5M per IPF/ILD trial

  •  ~ $60M to $175M in annual savings across the current global trial market, excluding additional gains from faster enrollment and reduced site burden.

Clinical Trial Cohort Selection

Off-the-shelf AI does not suffice

Sample complexity | Model capacity

More complex the model, more parameters need to be trained, requiring more data

Optimal trade-off between model capacity and sample complexity

Alzheimer's Disease and Related Dementia

About 1 in 9 U.S. adults age 65 and older, approximately 11%, has Alzheimer’s Disease.

Current diagnosis: based on cognitive assessments, often delayed or missed

Alzheimer's Disease and Related Dementia

  • Three different databses

  • 12,971,695 patients

  • Diverse demographics

  • Stable performance

PPV ~ 60%

LR+ ~ 5-10

AUC ~ 85-90%

white

AA

Alzheimer's Disease and Related Dementia

Stable prediction 6-10 years in future 

Acute Pancreatitis Prognosis

Acute Pancreatitis Prognosis

Number of Patients used. (MarketScan)

Acute Pancreatitis Prognosis

Opening the Black Box: Which co-morbidities are driving the risk?

  1. Many small-effect-size drivers

  2. There are "protective effect", which are typically diagnoses or procedures that reduce the risk of acute pancreatitis (e.g. gall-bladder removal)

Target AUC
Frailty / Physical Debility 96.2%
Alzheimer's Disease and Related Dementia (ADRD) 93.4%
Chronic Fatigue Syndrome / ME 93.2%
Acute Pancreatitis: ICU Visit 92.3%
Chronic Pancreatitis: Exocrine Pancreatic Insufficiency 92.1%
Idiopathic Pulmonary Fibrosis (IPF) 91.6%
Sarcopenia 91.0%
Parkinson's Disease 87.9%
Dementia / Degenerative Neurologic Disease 87.8%
Acute Pancreatitis: Insulin Dependence 87.2%
Suicide Attempts / Suicidal Ideations (Males 50--75) 86.0%
Chronic Inflammation 85.9%
Heart Failure with Preserved Ejection Fraction (HFpEF) 84.9%
Suicide Attempts / Suicidal Ideations (Males 25--50) 84.0%
Interstitial Lung Diseases (ILD) 82.2%
Age-related Macular Degeneration 82.1%
Autism Spectrum Disorder (ASD) 81.8%
Chronic Kidney Disease (CKD) 81.8%
Cerebral Infarction 81.1%
Chronic Obstructive Pulmonary Disease (COPD) 81.0%
Major Depressive Disorder 80.5%
Myocardial Infarction / Cardiac Arrest post-arthroplasty 80.1%
CKD Progression to Stage 4+ 80.1%
Prostate Cancer 80.0%
Osteoporosis 79.5%
Post-Traumatic Stress Disorder (PTSD) 78.1%
Hearing Loss 72.7%
Osteoarthritis 72.5%
Systemic Connective Tissue Disorders 72.0%

ZeBRA Model Family (expanding list)

[
    {
        "patient_id": "P000038",
        "sex": "F",
        "birth_date": "01-01-2006",
        "DX_record": [
            {"date": "07-31-2006", "code": "Z38.00"},
            {"date": "08-07-2006", "code": "P59.9"},
            {"date": "08-29-2016", "code": "J01.90"},
            {"date": "09-10-2016", "code": "J01.90"},
            {"date": "11-14-2016", "code": "J01.91"}
        ],
        "RX_record": [
            {"date": "10-29-2011", "code": "rxLDA017"},
            {"date": "05-16-2015", "code": "rxIDG004"},
            {"date": "08-08-2015", "code": "rxIDG004"},
            {"date": "06-04-2016", "code": "rxIDD013"}
        ],
        "PROC_record": [
            {"date": "02-05-2007", "code": "90723"},
            {"date": "11-05-2007", "code": "J1100"}
        ]
    }
]
{
  "predictions": [
    {
      "error_code": "",
      "patient_id": "P000012",
      "predicted_risk": 0.005794344620009157,
      "probability": 0.8253881317184486
    }
  ],
  "target": "TARGET"
}

Data Out

Data In

Current state: Fully functional API tested in cloud deployments*

  • user-specific API
  • Custom models targeting range of disorders
  • Scalable

*Documentation:  https://github.com/zeroknowledgediscovery/paraknowledgedoc

Model ready to deploy behind UK firewall

CKD

PF

ZeBRA

ICD

Primary care

TimestampedDiagnostic procedural codes & prescriptions

MASH

Rx

Px

Future

Comprehensive Digital Twins that integrate genomic and life-style/clinical information

ZeBRA+

ishanu_ch@uky.edu

@ishanu_ch

Questions?

ZeBRA_AISUMMIT

By Ishanu Chattopadhyay

ZeBRA_AISUMMIT

Brief talk on the ZeBRA Platform

  • 5

More from Ishanu Chattopadhyay