Blog

Can You Trust an LLM with Clinical Decisions?

A Deterministic Approach Using DMN

Read Time: 5 Minutes

The Problem

Large language models (LLMs) are increasingly used to support clinical decision-making. The appeal is obvious. They offer a flexible natural language interface and can synthesize complex convoluted inputs quickly.

LLMs are inherently probabilistic and non-deterministic. That is a risk.

In regulated domains such as healthcare, this creates a fundamental problem. Clinical decisions must be explainable and auditable. An LLM alone cannot meet these requirements today.

The April Challenge from the Decision Management Community explores how LLMs can orchestrate decision services using a clinical scenario: prescribing antibiotics for acute sinusitis.

The interesting question is not whether this works. The real question is whether it can be trusted.

Clinical Caveat

This challenge defines a prescriptive clinical context, which introduces regulatory and liability concerns from the start.

There are also gaps in the provided challenge scenario. The Cockcroft-Gault equation is incomplete, omitting the adjustment typically applied for female patients. Some treatment choices, such as the use of fluoroquinolones in pediatric cases, are also questionable. The duration of therapy is fixed without clear justification. There are no cited references to validate the rules, and only a single test case is provided.

These limitations matter if the solution is interpreted as clinically authoritative.

However, the intent of the challenge is not to define best clinical practice. Its value lies in exploring how decisions can be structured, executed, and orchestrated while leveraging the strengths of a large language model.

Our Position

LLMs should not make clinical decisions.

They should act as an interface and interaction layer, while deterministic decision models define and govern the outcome.

This separation is not optional in regulated environments. It is the only way to maintain control.

In practice, this means:

The LLM handles user interactions
DMN models define the decisions
BPMN and CMMN models orchestrate execution when control matters

The result is a system that combines flexible interaction with deterministic control.

Solution Overview

Our solution implements three decision services using DMN:

Creatinine clearance calculation

Antibiotic selection and dosing

Drug interaction checking

Each service is modeled independently and exposed as a callable endpoint.

The LLM connects to these services through Model Context Protocol (MCP), allowing it to discover and invoke them as tools.

The key constraint is simple. The LLM does not decide. It calls models that make the decisions.

Decision Modeling Approach

We start with the simplest case: a single, explicit calculation.

The Creatine Clearance is straightforward, with a single literal expression used to calculate the value. As noted above, the equation does not include a factor for female sex as specified in the original formula that was referenced.

Decomposition and Traceability

The antibiotic prescription service is particularly interesting. It is decomposed into multiple intermediate decisions. Each step is modeled explicitly using decision tables. This ensures that every outcome can be traced back to its inputs and rules.

This is not just a modeling preference. It is what makes the solution reviewable.

If something goes wrong, you can trace the outcome back to a specific rule.

A single, monolithic rule set would be harder to validate and maintain. Breaking it down into selection, standard dosing, dose adjustment, and final assembly keeps each decision focused.

For the creatine clearance adjustment, a note was added to the result to explain the change. The decision model does not include the rule component 1.4 mg/dL> since no evidence for its inclusion was provided.

Reuse and Iteration

The final step is to check for drug interactions. The CSV file provided in the challenge was used to generate a decision table, with the antibiotic name and medication name as inputs and the interaction as the output. Here is an excerpt of the table:

Since a patient may take more than one medication, this logic was implemented in a Business Knowledge Model (BKM). The BKM is then called for each medication.

A boxed iteration (a DMN construct for iterating over a list) is used to build the list of interactions. Unlike traditional code, this iteration is expressed visually, making it easier to read and understand.

This is a simple pattern, but it is often missed. Instead of embedding loops in code, the logic remains visible and declarative.

Orchestration and Control

The challenge suggests that the LLM should orchestrate the process. In practice, this is not the preferred approach for regulated environments and not one we recommend.

A BPMN or CMMN model would provide deterministic orchestration, explicit sequencing or task selection, and full auditability.

However, to comply with the challenge constraints, the LLM is used as the orchestrator.

This highlights an important distinction:

LLM orchestration is flexible but not inherently governed
BPM+ Model-driven orchestration is explicit and enforceable

This solution demonstrates the former while advocating for the latter.

Governing the LLM

The LLM is configured as an agent with access to the DMN services through MCP.

It is instructed to use those services and not to generate its own clinical conclusions.

While this constraint is implemented through instructions, it exposes a key limitation: instruction-based governance is not sufficient.

True governance requires:

Explicit control over which services can be invoked
Validation of inputs and outputs
Defined execution paths
Auditability of every step

These controls are best implemented through BPM+ model-driven orchestration, not prompt engineering.

These controls belong in models, not prompts. Period.

Example Interaction

A user provides patient data in natural language. The LLM interprets the request and invokes the decision services in sequence.

First, creatinine clearance is calculated. Then antibiotic selection and dosing are determined. Finally, drug interactions are evaluated.

Each step is a deterministic service call. The results are combined into a final response.

The interaction feels conversational. The decisions are not.

What This Demonstrates

This solution is not about solving sinusitis treatment. It is about demonstrating a pattern for combining LLMs with decision automation.

Two points matter more than anything else:

LLMs are effective interfaces, not decision authorities
Decision logic must remain explicit, testable and governed

For DMN practitioners, this shows how decision services can be exposed and reused in an agent context.

For clinicians, the message is simpler. The system can remain explainable and auditable even when natural language interfaces are introduced.

What Comes Next

Moving from demonstration to production requires tightening the architecture:

Replace LLM orchestration with BPMN or CMMN controlled execution to inforce deterministic service usage instead of relying on instructions Add validation, testing, and monitoring Define escalation paths and human oversight

These are not optional in regulated environments.

Conclusion

LLMs can be useful in clinical systems, but only within the clear boundaries of a governed architecture.

The combination of DMN for decision logic and BPM+ standards-based integration provides a path forward. When decision logic is externalized and governed, you can take advantage of LLM flexibility without losing control. It allows organizations to adopt AI while maintaining control, traceability, and trust.

The challenge highlights the opportunity. Our solution points to what is required to do it safely.

Can You Trust an LLM with Clinical Decisions? A Deterministic Approach Using DMN

Blog

By John Svirbely

(Read Time: 5 Minutes)

Are You Standing on Thin Ice When Using AI for Healthcare

Blog

By John Svirbely

(Read Time: 2 Minutes)

A New Year’s Checklist for Building Better Clinical Models

Blog

By John Svirbely

(Read Time: 2 Minutes)

Why Bring Your Own AI (BYOAI)?

Blog

By John Svirbely

(Read Time: 3 Minutes)

From Pain to Gain: Turning CMS-0057-F Mandates into Workflow Wins with BPM+

Blog

By John Svirbely

(Read Time: 3 Minutes)

Suicide Prevention with Modeling Tools

Blog

By John Svirbely

(Read Time: 3 Minutes)

Getting FHIRed Up with SDMN

Blog

By John Svirbely

(Read Time: 2 Minutes)

Modelling Preauthorization Part II: Modelling a Solution

Blog

By John Svirbely

(Read Time: 3 Minutes)

Modelling Preauthorization Part I: The Problem

Blog

By John Svirbely

(Read Time: 3 Minutes)

Healthcare Orchestration versus Healthcare: Handling Interactions Between Processes

Blog

By John Svirbely

(Read Time: 3 Minutes)

In Healthcare: To Automate or Not to Automate, that is the Question

Blog

By John Svirbely

(Read Time: 3 Minutes)

Are you looking for Diagrams or Models of your Clinical Guidelines?

Blog

By John Svirbely

(Read Time: 3 Minutes)

Clinical Models at Scale

Blog

By John Svirbely

(Read Time: 3 Minutes)

Do Healthcare Process Models Need Attended Tasks?

Blog

By John Svirbely

(Read Time: 2 Minutes)

Orchestrating Generative AI in Business Process Models

Blog

By John Svirbely

(Read Time: 2 Minutes)

Going from Zero to Success using BPM+ for Healthcare. Part III: Going from Paper to Practice

Blog

By John Svirbely

(Read Time: 3 Minutes)

Going from Zero to Success using BPM+ for Healthcare. Part II: Getting Started

Blog

By John Svirbely

(Read Time: 3 Minutes)

Going from Zero to Success using BPM+ for Healthcare. Part I: Learning Modeling and Notation Tools

Blog

By John Svirbely

(Read Time: 3 Minutes)

In Healthcare, Interoperability is Just the Start

Blog

By John Svirbely

(Read Time: 3 Minutes)

Transforming Healthcare with Trisotech

Blog

By John Svirbely

(Read Time: 5 Minutes)

AI Agents You Can Actually Trust in Healthcare: From Opaque to Governed Automation

Presented By

John Svirbely, CMIO Trisotech
Denis Gagne, CEO & CTO Trisotech

Description

Healthcare AI is only as valuable as the trust clinicians and patients place in it. The barrier isn’t capability, it’s reliability and governance.

When AI behavior is opaque, like a black box, outcomes are unpredictable, and accountability is unclear. Clinical adoption fails.

Whether you are a clinician concerned about accountability, an informatician managing governance, or an architect designing the control plane, this session is for you.

This session introduces a production-ready alternative. Using BPM+ standards, orchestration, decisions, and AI capabilities are kept separate. Decisions are externalized and versioned.

AI outputs are treated as data, not outcomes. Clinical policies can evolve without rewriting code. The result is AI that is predictable, auditable, and interoperable with FHIR-based EHR environments.

Grounded in HL7 Award-recognized work from Trisotech, you will leave with a concrete and actionable blueprint for moving AI safely from experimentation to trusted clinical operations.

View the slides

How Dana-Farber Enables Earlier Cancer Symptom Intervention at Scale

Presented By

Michael Scalzo, Dana-Farber Cancer Institute

Description

Dana-Farber Cancer Institute is extending clinical pathways into automated, real-time nurse interventions for cancer treatment side effect management. Orchestrated pathways and CDS Hooks embedded in Epic support nurse navigation, enabling earlier, scalable symptom escalation and timely intervention within routine care workflows.

By operationalizing pathways at the point of care, Dana-Farber enables earlier, scalable symptom escalation and timely intervention while maintaining clinical oversight and governance. Attendees will gain practical insight into how standards-based orchestration can turn pathway intent into executable nursing actions that improve consistency and responsiveness in oncology care.

View the slides

case study

Intermountain^® Health’s

New Interoperability Platform Saves Lives and Reduces Costs

Intermountain Health is widely recognized as a leader in transforming healthcare by using evidence-based best practices to consistently deliver high-quality outcomes at sustainable costs. A non-profit organization headquartered in Utah, Intermountain Health has locations in 8 western states including 33 hospitals, 385 clinics, and more than 1 million members.

Saving lives
more then 100 lives annually

Deployment speed
from months to days

case study

Mayo Clinic

Mayo Expert Decision Advisor:
Revolutionizing Health IT with a Model-Driven Strategy, Enabling Rapid EHR Workflow Updates in Days, Not Months

The Mayo Clinic, a world-renowned nonprofit healthcare organization founded in Rochester, Minnesota, specializes in clinical practice, education, and research, employing physicians scientists, and staff across campuses in Minnesota, Florida, and Arizona, with additional affiliated facilities nationwide. It consistently ranks as the top hospital by U.S. News & World Report. Its knowledge management program focuses on consolidating evidence-based best practices for enterprisewide application.

The Mayo Expert Decision Advisor, as detailed in Mayo Clinic Proceedings, integrates Mayo-vetted knowledge with patient data in Electronic Health Records. This tool streamlines patient data analysis, offering clinician-like interpretation, thereby reducing clinician cognitive load, and enhancing patient care efficiency.

Mayo-vetted knowledge
dynamically integrated with patient data.

Dissemination of changes
to knowledge within days rather than months.

case study

Dana-Farber Cancer Institute

Preemptively managing the side effects of cancer treatment through model-driven clinical decision support

Located in Boston and the surrounding communities, Dana-Farber Cancer Institute brings together world renowned clinicians, innovative researchers and dedicated professionals, allies in the common mission of conquering cancer, HIV/AIDS, and related diseases. Combining extremely talented people with the best technologies in a genuinely positive environment, they provide compassionate and comprehensive care to patients of all ages; they conduct research that advances treatment; they educate tomorrow’s physicians and researchers; they reach out to underserved members of their community; and they work with amazing partners, including other Harvard Medical School-affiliated hospitals.

Cancer care is complex. The treatment landscape is constantly changing, and it will soon become impossible for oncology providers to appropriately manage their patients without decision support. To address this need for a new cancer care delivery model, Dana-Farber launched Dana-Farber Pathways in 2012. This multidisciplinary program brought together a dedicated group of clinicians, informaticists, and analysts with the common goal of developing an electronic roadmap for quality cancer care. To date, Dana-Farber has built a portfolio of over 70 clinical pathways, providing treatment recommendations for almost all solid tumor and hematologic malignancies.

Cancer treatment has side effects. Regardless of their diagnosis, all cancer patients have the potential to experience a wide range of symptoms related to therapy or the progression of their disease. Given that the current approach to symptom management is often fragmented and reactive, Dana-Farber Cancer Institute has launched an innovative initiative to preemptively manage the side effects of cancer therapy by leveraging digital technologies. This includes the development of a portfolio of symptom management pathways by Dana-Farber Pathways. By implementing decision support at point of care, Dana-Farber hopes to:

HL7 Field Guide to Sharable Clinical Pathways

Clinical Guide Lines are the knowledge sources of modern evidence-based medicine and Clinical Decision Support (CDS) systems. But what if the clinical guideline document could not only be consumable by practitioners but by computers systems as well? The same document, offering clear interpretation and course of actions to both care providers and the computer systems supporting them.

This version is being published by the HL7 BPM Community of Practice (previously BPM+ Health at OMG). This is the latest version of the “Field Guide” aimed at organizations producing, consuming and deploying such “Sharable Clinical Guidelines.”

Unleashing Innovation: HL7 AI Challenge Winners Transforming Healthcare with Standards-Based AI

Presented By

Denis Gagne

Description

This on-demand session highlights the inaugural HL7 AI Challenge winners, organizations proving that healthcare AI can be powerful and trustworthy when built on open standards. Moderated by HL7 Chief AI Officer Dan Vreeman, DPT, the webinar features three teams delivering practical, standards-aligned solutions that move beyond prototypes and into real-world impact.

The program includes:

Overall Winner: Quantek Systems, Inc. – dynaMap AI. A clinical workflow engine using active inference to guide patient-specific decisions.
Overall Winner: Verto Health – VERTO Connect. A standards-based approach to structuring and integrating healthcare’s vast unstructured data assets.
Excellence in AI Transparency & Trust: Trisotech – Standardizing Clinical Autonomy: BPM+ Determinism and HL7 Integration for AI Agents. Trisotech demonstrates how deterministic BPM+ models, HL7 integration patterns, and explicit decision logic create AI agents that remain explainable, governable and clinically trustworthy. This submission showcases how decision-centric orchestration and transparent reasoning can extend clinical autonomy safely while meeting governance expectations.

You will see how HL7 standards are enabling scalable, interoperable and verifiable AI solutions that improve clinical workflows, enhance data usability and support responsible adoption across the health ecosystem. This session is relevant for developers, clinicians, policymakers and health IT leaders who want a clear view of where healthcare AI is heading and what “good” looks like in practice.

case study

HL7 International Excellence in AI Transparency and Trust Award

Trisotech capabilities deliver a trusted foundation for AI-powered clinical orchestration, combining the creativity of AI with the governance of BPM+ and HL7 standards.

Blog

Why Bring Your Own AI (BYOAI)?

By Dr. John Svirbely, MD

Read Time: 3 Minutes

Recently Trisotech posted a position paper entitled “Bring Your Own AI (BYOAI)“. Its observations are relevant to modeling and automation in healthcare. Personally, I think this is the way to make use of AI – at least for now.

Chasing the Next Shiny Thing

AI models are evolving right before your eyes, with many companies appearing then disappearing on a monthly basis. The environment is chaotic, and it is hard to know what to do, and it is tempting to try the newest platforms. This can paralyze project development as you struggle with deciding what tool to use, afraid that it will be obsolete next week. Often you look to see what others are doing rather than forging your own strategy.

Constantly changing environments are plagued by problems with version control and testing. Users become confused and may push back, especially after they hear about bias in algorithms or incorrect responses. They may feel forced to use something that they have no confidence in.

Overreaching

The natural tendency when using a powerful tool is to apply to a large problem all at once. For many projects this can result in subpar performance. Anyone using the current AI platforms can see a deterioration in performance once a certain task size is reached. Often you have no idea exactly what changed or why. Has a seemingly minor change in a prompt caused a vast change in output? Could you have run out of tokens? Are you competing against other users for access? When faced with something outside of your control you can hold a rabbit’s foot and pray for the best.

Who Is Going to Be Liable?

At some point something is going to go wrong – it always does. So just who is going to be left holding the bag? The lawyers are already lining up.

Do you think the AI companies are going to step up? The fine print of their user agreement tries as hard as possible to deflect responsibility. Traditionally clinicians have been liable and so carry liability insurance. What person is going to accept responsibility for a black box that they have no control over, do not understand, and offers no evidence for its actions. How can using a novel AI platform be considered standard of care? Will malpractice insurance cover this? You can be sure that your already expensive cyber insurance is going to cost a whole lot more.

So Why Does BYOAI Work in Healthcare Modeling?

Here are some reasons why I like the idea of BYOAI for modeling in healthcare.

You are not tied to a single AI platform.

Some platforms perform better in some tasks than others. A specific task can call whatever service works better. If a better one comes along then you can swap it in without changing the rest of your model.

You can control when and how the platform gets called.

You can limit its scope so that it returns focused responses. This makes the system easier to test.

You can make use of attended tasks.

These allow physicians to review and modify the model as it progresses in light of the patient’s clinical context. They can accept, reject or modify any suggestion based on the current situation and so can act responsibly in caring for a specific individual. Here AI functions as a useful ally with the clinician in control.

BPM+ Modeling with BYOAI gives you the best of both worlds. No one knows where AI will be going in the future, but modeling should be able to evolve along with the technology. You can confidently get started solving your problems now, rather than waiting for a future that is unpredictable.

Can You Trust an LLM with Clinical Decisions? A Deterministic Approach Using DMN

Blog

By John Svirbely

(Read Time: 5 Minutes)

Are You Standing on Thin Ice When Using AI for Healthcare

Blog

By John Svirbely

(Read Time: 2 Minutes)

A New Year’s Checklist for Building Better Clinical Models

Blog

By John Svirbely

(Read Time: 2 Minutes)

Why Bring Your Own AI (BYOAI)?

Blog

By John Svirbely

(Read Time: 3 Minutes)

From Pain to Gain: Turning CMS-0057-F Mandates into Workflow Wins with BPM+

Blog

By John Svirbely

(Read Time: 3 Minutes)

Suicide Prevention with Modeling Tools

Blog

By John Svirbely

(Read Time: 3 Minutes)

Getting FHIRed Up with SDMN

Blog

By John Svirbely

(Read Time: 2 Minutes)

Modelling Preauthorization Part II: Modelling a Solution

Blog

By John Svirbely

(Read Time: 3 Minutes)

Modelling Preauthorization Part I: The Problem

Blog

By John Svirbely

(Read Time: 3 Minutes)

Healthcare Orchestration versus Healthcare: Handling Interactions Between Processes

Blog

By John Svirbely

(Read Time: 3 Minutes)

In Healthcare: To Automate or Not to Automate, that is the Question

Blog

By John Svirbely

(Read Time: 3 Minutes)

Are you looking for Diagrams or Models of your Clinical Guidelines?

Blog

By John Svirbely

(Read Time: 3 Minutes)

Clinical Models at Scale

Blog

By John Svirbely

(Read Time: 3 Minutes)

Do Healthcare Process Models Need Attended Tasks?

Blog

By John Svirbely

(Read Time: 2 Minutes)

Orchestrating Generative AI in Business Process Models

Blog

By John Svirbely

(Read Time: 2 Minutes)

Going from Zero to Success using BPM+ for Healthcare. Part III: Going from Paper to Practice

Blog

By John Svirbely

(Read Time: 3 Minutes)

Going from Zero to Success using BPM+ for Healthcare. Part II: Getting Started

Blog

By John Svirbely

(Read Time: 3 Minutes)

Going from Zero to Success using BPM+ for Healthcare. Part I: Learning Modeling and Notation Tools

Blog

By John Svirbely

(Read Time: 3 Minutes)

In Healthcare, Interoperability is Just the Start

Blog

By John Svirbely

(Read Time: 3 Minutes)

Transforming Healthcare with Trisotech

Blog

By John Svirbely

(Read Time: 5 Minutes)

At its core, BPM+ combines the strengths of the following open standards from the Object Management Group, Inc. (OMG®):

BPMN™ (Business Process Model and Notation™) for structured workflows
CMMN™ (Case Management Model and Notation™) for unstructured, event-driven cases
DMN™ (Decision Model and Notation™) for business rules and decision logic
SDMN™ (Shared Data Model and Notation™) for unified data definitions

Together, these standards form a cohesive modeling ecosystem that supports end-to-end business transformation, governance, and automation.

Why BPM+?

Most organizations rely on written documents to define processes and rules, but natural language often introduces ambiguity and inconsistency. BPM+ replaces this with precise, visual models that are easier to understand, validate, and automate.

Whether you’re managing a hospital, onboarding a customer, processing a loan, or running DevOps pipelines, BPM+ gives you:

A blueprint for how your business operates
A standardized input for workflow and decision orchestration
A shared language for collaboration across teams

Key Benefits

Eliminate ambiguity with readable, standardized diagrams
Align stakeholders on scope, logic, and decision paths
Enable automation directly from the models with no code translation needed
Build reusable libraries of processes and decisions
Improve agility by adapting quickly to regulatory or business changes

With BPM+, your models are more than just documentation, they are living assets that drive execution and transformation.

Who Uses BPM+?

BPM+ is widely adopted by organizations that operate in complex, regulated environments and require clarity, consistency, and automation across their decisions, processes, and data. It’s especially valuable for teams looking to align business operations with digital transformation goals while ensuring regulatory compliance.

Used Across Industries

BPM+ appeals to a diverse range of medium to large enterprises, particularly in sectors where auditability, standardization, and agility are critical:

Healthcare: Hospitals and clinical organizations use BPM+ to model care pathways, enforce clinical best practices, and automate workflows at the point of care.
Financial Services: Banks and lenders apply BPM+ to streamline loan origination, servicing, risk evaluation, and compliance with evolving regulations.
Government: Public sector organizations modernize citizen-facing services and internal operations using BPM+ for greater transparency and efficiency.
Telecommunications & Utilities: Use BPM+ to manage dynamic service delivery, customer care processes, and operational resilience.
Technology & DevOps: Integrate BPM+ models with automation pipelines to orchestrate development, testing, deployment, and monitoring workflows.

Typical users include product owners, solution architects, business process teams, compliance departments, and low-code developers who need to orchestrate business decisions and workflows, manage cases, and standardize data.

BPM+ in Financial Services

The financial services sector is a leading adopter of BPM+, driven by the need to navigate complex regulations and maintain standardized, auditable business processes.

More info on Finance

Banks, insurers, investment firms, credit unions, and GSEs use BPM+ to manage critical functions like loan origination, customer onboarding, complaint resolution, and regulatory reporting. Financial institutions rely on BPM+ to model complex decision logic for credit scoring, fraud detection, and compliance, while maintaining the transparency required for audits and regulatory reviews. With BPMN and DMN, organizations codify risk and compliance rules; with CMMN, they manage investigative and exception-driven cases; and with SDMN, they standardize data definitions across processes. BPM+ helps ensure consistency, traceability, and agility, key to staying competitive and compliant in a fast-evolving financial landscape.

As the MISMO-approved standard for expressing business rules and decisions, DMN supports end-to-end lifecycle management, from authoring and validation, to execution and exchange, across systems and platforms.

MISMO®,
(Mortgage Industry Standards Maintenance Organization) a non-profit subsidiary of the Mortgage Bankers Association (MBA)

BPM+ is being used to document and automate hundreds of types of financial processes including:

Risk assessment and mitigation processes
Credit scoring processes
Regulatory compliance processes
Credit card processing
EOD/EOM/EOQ/EOY closing processes
Underwriting processes
Anti-money laundering processes
Loan origination processes
Consumer protection processes
Loan distribution processes
Know your customer (KYC) processes
Fraud detection processes
Claims handling processes
Loan servicing processes
Complaint handling & mitigation processes
Cross selling and up-selling processes
Investment trade processes
Trade review processes
Marketing processes
Sales forecasting processes

With BPM+, financial institutions can model and orchestrate business decisions, ensure auditability, and demonstrate governance across systems and geographies.

BPM+ in Healthcare

BPM+ is transforming healthcare by enabling organizations to model, standardize, and automate complex clinical and administrative workflows.

More info on Healthcare

By integrating BPMN, CMMN, DMN, and SDMN standards, BPM+ supports both structured care protocols and dynamic case management, making it ideal for environments where patient care must be individualized yet evidence-based. Healthcare providers use BPM+ to improve care coordination, reduce administrative burdens, and enhance regulatory compliance. The result is greater operational efficiency, better patient outcomes, and a data-driven foundation for continuous improvement across the care continuum.

BPM+ is being used to create healthcare process flows, manage cases and orchestrate DMN decision services in hundreds of ways. Here are some representative examples:

Create/improve clinical guidelines
Maintain EHR Systems
Procurement
Patient Admission and Discharge
Care management
Benefit Enrollment
FHIR support
Billings and payments
Prior authorization
Clinical decision support (CDS)
Adding AI/Machine Learning into processes
Insurance/claims processing
Onboard and Offboard Employees & Patients
Actuarial and risk management
Manage the Staff Roster
Automate FTP/SFTP/FTPS
Call center scripting
DevOps
Accelerate Help Desk Response Time
Fraud management
HIPAA compliance
Joint Commission standards reporting
Risk Management
CMS compliance

Trisotech: A Leader in BPM+

Trisotech is a global leader in business automation and a key contributor to all four BPM+ standards: DMN, BPMN, CMMN, and SDMN. Its tools, DMN Decision Modeler, BPMN Workflow Modeler, CMMN Case Modeler, and SDMN Shared Data Modeler are recognized as the reference implementations for these standards. Together, they form the foundation of the Trisotech Digital Enterprise Suite (DES), a definitive platform for standards-based business modeling and automation.

The suite offers a visual, browser-based environment for creating and deploying BPM+ models across public or private cloud infrastructures. It includes advanced capabilities such as AI and machine learning integration via Predictive Model Markup Language (PMML) and Clinical Quality Language (CQL), as well as Attended Tasks that support human-in-the-loop validation during automation. Additionally, Trisotech’s Knowledge Entity Modeler (KEM) allows organizations to manage business vocabularies and concept models based on the Semantics of Business Vocabulary and Business Rules™ (SVBR™) standard, supporting rich, domain-specific applications in industries like healthcare and finance.

Trisotech
in Financial Services:

Provides Mortgage Feature Set (MFS) for Regulation Z, Fannie Mae, Freddie Mac, and MISMO standards
Drag-and-drop support for MISMO data structures and business concepts
Over 30 financial FEEL functions for BPM+ models

Trisotech
in Healthcare:

Founding member of BPM + Health
Healthcare Feature Set (HFS) with support for FHIR , SMART on FHIR, and CDS Hooks
Over 1,000 pre-built clinical pathways and decision models
Human-in-the-loop validation via Attended Tasks with the and the.

Why Choose Trisotech for BPM+?

Trisotech delivers a scalable, cloud-ready, standards-based automation platform trusted by enterprises and governments worldwide. With full support for BPM+, Trisotech enables:

Rapid time-to-value through low-code modeling
Seamless integration into any IT environment
Reusable knowledge assets and accelerators
Full compliance with industry-specific regulations
Future-ready architecture for AI, APIs, and event-driven workflows

OMG®, BPMN™, (Business Process Model and Notation™), Decision Model and Notation™, (DMN™), CMMN™, (Case Management Model and Notation™), SDMN™, (Shared Data Model and Notation™), Semantics of Business Vocabulary and Business Rules™, (SVBR™), and BPM+ Health™ are either registered trademarks or trademarks of Object Management Group, Inc. in the United States and/or other countries. MISMO is a registered trademark of Mortgage Industry Standards Maintenance Organization, Inc. HomeReady® and Uniform Mortgage Data Program® (UMDP®) are registered trademarks of Federal National Mortgage Association (Fannie Mae).

What is Decision Intelligence?

Decision Intelligence (DI) is defined by Gartner as:

A practical discipline that advances decision making by explicitly understanding and engineering how decisions are made and how outcomes are evaluated, managed and improved via feedback.

It blends data science, AI, decision modeling, and domain expertise to support, augment, or automate business decisions. It treats decisions as strategic enterprise assets, ensuring that human expertise, business rules, AI insights, and organizational context are orchestrated into high-quality, auditable outcomes. Unlike traditional analytics, which stop at insight, DI connects the dots between data, rules, processes, and people, creating a closed-loop system where decisions are explicitly modeled, executed, monitored, and improved over time.

This decision-centric approach is rapidly gaining adoption across sectors, from finance and healthcare to government and public services.

How Trisotech Addresses
Decision Intelligence (DI)

Trisotech Digital Enterprise Suite (DES) is a cloud-native platform that treats decisions as first-class assets, combining decision models based on open-standards with AI and knowledge graphs to orchestrate processes, data, and human judgment. Business value is delivered by orchestrating decisions rather than just tasks or workflows. Every decision, process (workflow), case, or API is managed as a governed semantic asset, meaning it’s explainable and auditable. The platform is built on BPM+ standards (DMN for decisions, BPMN for processes, CMMN for cases, SDMN for data) to ensure model-driven interoperability and avoid vendor lock-in. A Digital Enterprise Graph (DEG) links these models with data and business vocabulary, providing rich context and reuse across the enterprise. Trisotech Decision Centric Orchestration (DCO) technology also emphasizes AI augmentation with governance: it can embed AI services (e.g. GenAI prompts, machine learning classifiers) directly into workflows while applying “TRUST” principles (Traceability, Reflectiveness, Understanding/Oversight, Separation of duty, Transparency) for safe, explainable AI use. In short, Trisotech DES is an integrated decision-centric platform combining decision automation, process orchestration, case management, and knowledge management with AI, all under strong governance. This comprehensive capability set aligns closely with Gartner’s vision of decision-centric solutions and Decision Intelligence Platforms (DIP).

What are Decision Intelligence Platforms (DIPs)?

A Decision Intelligence Platform (DIP) is a software environment that empowers organizations to model, automate, monitor, and optimize complex decisions. According to Gartner a DIP must support capabilities such as decision modeling, orchestration, composability, collaboration, execution, governance, and learning from outcomes.

Unlike standalone AI or analytics tools, a DIP delivers an end-to-end lifecycle:

Model decisions using standard notations.
Execute them via orchestration engines.
Monitor outcomes and compliance.
Analyze the quality and outcomes of those decisions.

This unified approach accelerates agility and ensures trust, transparency, and accountability in automated decisions.

How Trisotech Addresses
Decision Intelligence Platform (DIP)

Trisotech Decision-Centric Orchestration (DCO) technology aligns strongly with Gartner’s criteria for Decision Intelligence Platforms (DIPs) by offering explicit decision modeling and orchestration through BPM+ standards (DMN, BPMN, CMMN, SDMN). In fact, Trisotech is recognized by Gartner as a representative vendor in the DIP category. Trisotech modular, API-driven architecture supports composability and microservice deployment, while its cloud-native execution environment enables governed, traceable decision services at scale. The platform fosters collaboration among business and technical stakeholders and integrates human oversight into AI-augmented decisions via its TRUST (Traceability, Reflectiveness, Understanding, Separation, Transparency) framework. Trisotech also emphasizes governance, policy enforcement, and real-time observability to meet strict monitoring and compliance demands. Through modeling and continuous monitoring, it supports decision refinement and learning over time. Conceptually, Trisotech neuro-symbolic approach, combining business rules, knowledge graphs, and AI, embodies the principles of decision intelligence, positioning it as a fully realized and future-ready DIP.

In short, the Trisotech Digital Enterprise (DES) Suite offers:

Full decision modeling and orchestration via DMN, BPMN, CMMN and SDMN.
Composability through a low-code environment and open APIs.
Governed execution with explainability and observability at every step.
Collaboration across business and technical roles via shared semantic assets.
Analysis of decision performance for improvement insights.

Decision Intelligence in Financial Services

In financial services, DI is transforming how firms manage risk, ensure compliance, personalize customer experiences, and detect fraud.

More info on Finance

By treating decisions as governed, repeatable assets, financial institutions can:

Standardize regulatory and credit decisions.
Automate case-based operations (e.g., KYC, loan approvals).
Embed explainable AI in decision workflows.
Ensure full traceability for audits and regulatory reviews.

Decision Intelligence in financial services improves “decision quality and explainability while reducing time-to-insight and operational costs”.

How Trisotech Addresses
Decision Intelligence in Financial Services

Trisotech for Financial Services enables institutions to:

Model compliance, risk, and eligibility decisions using DMN with a business vocabulary.
Orchestrate workflows involving human approvals and AI components.
Embed auditability and compliance at the core of decision execution.
Deploy modular decision services that are scalable and policy-controlled.

Through semantic modeling and governed orchestration, Trisotech helps financial organizations operationalize DI to accelerate innovation while maintaining compliance and trust.

Decision Intelligence in Healthcare

In healthcare, DI supports more consistent, explainable, and patient-centered decisions, from clinical pathways to administrative approvals.

More info on Healthcare

DI enables:

Standardization of clinical decision support (CDS).
Real-time orchestration of care pathways and prior authorization.
Transparent, auditable AI augmentation in clinical workflows.
Interoperability via standards like FHIR and BPM+ Health.

Decision intelligence in healthcare is entering the early mainstream and is key for next-generation care orchestration and utilization management.

How Trisotech Addresses
Decision Intelligence in Healthcare

Trisotech for Healthcare provides:

End-to-end support for BPM+ Health modeling (DMN, BPMN, CMMN, SDMN).
Seamless integration with FHIR APIs.
Orchestration of AI-assisted decisions with human oversight (e.g., infection control, remote monitoring).
Compliance with data privacy, consent, and auditability standards through its governance-first architecture.

By embedding decision intelligence into clinical and operational pathways, Trisotech empowers health systems to improve outcomes and reduce variability, all while maintaining transparency and trust.

Conclusion

Decision Intelligence is more than a buzzword; it’s the future of responsible automation. Whether in finance, healthcare, or any data-driven industry, the ability to model, govern, and optimize decisions is the key to agility and trust.

Trisotech leads this transformation with its Decision-Centric Orchestration (DCO) technology: a complete decision intelligence platform rooted in open standards, AI augmentation, and human-AI collaboration. It’s not just automation; it’s orchestration of intelligence. A statement that could serve as a manifesto for decision intelligence.

Fast-Track CMS-57 Compliance: Wrap, Comply, and Iteratively Modernize with BPM+

Presented By

Melanie Gauthier, Solution Architect, Trisotech
Denis Gagne, CEO and CTO, Trisotech

Description

Achieving CMS-57 compliance doesn’t have to mean a costly system overhaul. Learn how Trisotech’s BPM+ approach enables organizations to quickly wrap existing legacy systems for immediate FHIR compliance—while progressively modernizing capabilities at their own pace. Reduce disruption, streamline prior authorization, and future-proof your IT investments with a flexible, standards-based strategy.

Join us to see how compliance can be a catalyst for transformation.

Watch the video

Fast-Track CMS-57 Compliance: Wrap, Comply, and Iteratively Modernize with BPM+

Presented By

Melanie Gauthier, Solution Architect, Trisotech
Denis Gagne, CEO and CTO, Trisotech

Description

Join us to see how compliance can be a catalyst for transformation.

View the slides

AI, FHIR, and BPM+ in Suicide Prevention: From Early Detection to Coordinated Care

Presented By

Dr. John Svirbely, CMIO, Trisotech
Denis Gagne, CEO and CTO, Trisotech

Description

Suicide prevention requires more than early detection—it demands seamless, patient-centered care. This session explores how AI-powered monitoring, BPM+ visual standards, and FHIR interoperability work together to detect suicidal ideation early and coordinate interventions across emergency departments, mental health specialists, and primary care.

Learn how technology-driven, standards-based orchestration enhances care continuity, reduces gaps, and ensures timely, effective support for at-risk patients.

Watch the video

Blog

Suicide Prevention with Modeling Tools

By Dr. John Svirbely, MD

Read Time: 3 Minutes

Suicide is an important problem around the world, causing significant morbidity and mortality. It impacts family and friends, causing long-lasting wounds. Many people are interested in finding effective solutions to the problem, often looking to technology for answers.

Facts about Suicide

Before we can find effective solutions, we need to understand the problem. Figure 1 from the Centers for Disease Control and Prevention (CDC) Suicide Prevention website shows some of the relevant numbers related to suicide. The number of people committing suicide may be undercounted since there is a tendency to avoid calling a death at suicide. In addition, some forms of suicide such as death by cop can be missed.

Can You Trust an LLM with Clinical Decisions? A Deterministic Approach Using DMN

Blog

By John Svirbely

(Read Time: 5 Minutes)

Are You Standing on Thin Ice When Using AI for Healthcare

Blog

By John Svirbely

(Read Time: 2 Minutes)

A New Year’s Checklist for Building Better Clinical Models

Blog

By John Svirbely

(Read Time: 2 Minutes)

Why Bring Your Own AI (BYOAI)?

Blog

By John Svirbely

(Read Time: 3 Minutes)

From Pain to Gain: Turning CMS-0057-F Mandates into Workflow Wins with BPM+

Blog

By John Svirbely

(Read Time: 3 Minutes)

Suicide Prevention with Modeling Tools

Blog

By John Svirbely

(Read Time: 3 Minutes)

Getting FHIRed Up with SDMN

Blog

By John Svirbely

(Read Time: 2 Minutes)

Modelling Preauthorization Part II: Modelling a Solution

Blog

By John Svirbely

(Read Time: 3 Minutes)

Modelling Preauthorization Part I: The Problem

Blog

By John Svirbely

(Read Time: 3 Minutes)

Healthcare Orchestration versus Healthcare: Handling Interactions Between Processes

Blog

By John Svirbely

(Read Time: 3 Minutes)

In Healthcare: To Automate or Not to Automate, that is the Question

Blog

By John Svirbely

(Read Time: 3 Minutes)

Are you looking for Diagrams or Models of your Clinical Guidelines?

Blog

By John Svirbely

(Read Time: 3 Minutes)

Clinical Models at Scale

Blog

By John Svirbely

(Read Time: 3 Minutes)

Do Healthcare Process Models Need Attended Tasks?

Blog

By John Svirbely

(Read Time: 2 Minutes)

Orchestrating Generative AI in Business Process Models

Blog

By John Svirbely

(Read Time: 2 Minutes)

Going from Zero to Success using BPM+ for Healthcare. Part III: Going from Paper to Practice

Blog

By John Svirbely

(Read Time: 3 Minutes)

Going from Zero to Success using BPM+ for Healthcare. Part II: Getting Started

Blog

By John Svirbely

(Read Time: 3 Minutes)

Going from Zero to Success using BPM+ for Healthcare. Part I: Learning Modeling and Notation Tools

Blog

By John Svirbely

(Read Time: 3 Minutes)

In Healthcare, Interoperability is Just the Start

Blog

By John Svirbely

(Read Time: 3 Minutes)

Transforming Healthcare with Trisotech

Blog

By John Svirbely

(Read Time: 5 Minutes)

If your Business runs on Rules, it should run on Trisotech!

Blog

Can You Trust an LLM with Clinical Decisions?

The Problem

Clinical Caveat

Our Position

Solution Overview

Decision Modeling Approach

Decomposition and Traceability

Reuse and Iteration

Orchestration and Control

Governing the LLM

Example Interaction

What This Demonstrates

What Comes Next

Conclusion

Blog Articles

All Blog Articles

AI Agents You Can Actually Trust in Healthcare: From Opaque to Governed Automation

Presented By

Description

Videos

Recorded webinars

How Dana-Farber Enables Earlier Cancer Symptom Intervention at Scale

Presented By

Description

Videos

Recorded webinars

case study

Intermountain® Health’s

New Interoperability Platform Saves Lives and Reduces Costs

Content

Articles

case study

Mayo Clinic

Mayo Expert Decision Advisor: Revolutionizing Health IT with a Model-Driven Strategy, Enabling Rapid EHR Workflow Updates in Days, Not Months

Content

Articles

case study

Dana-Farber Cancer Institute

Preemptively managing the side effects of cancer treatment through model-driven clinical decision support

Content

Articles

HL7 Field Guide to Sharable Clinical Pathways

Content

Articles

Unleashing Innovation: HL7 AI Challenge Winners Transforming Healthcare with Standards-Based AI

Presented By

Description

Videos

Recorded webinars

case study

HL7 International Excellence in AI Transparency and Trust Award

Trisotech capabilities deliver a trusted foundation for AI-powered clinical orchestration, combining the creativity of AI with the governance of BPM+ and HL7 standards.

Content

Articles

Blog

Why Bring Your Own AI (BYOAI)?

Chasing the Next Shiny Thing

Overreaching

Who Is Going to Be Liable?

So Why Does BYOAI Work in Healthcare Modeling?

Blog Articles

John Svirbely

All Blog Articles

Read our experts’ blog

What is BPM+?

Why BPM+?

Key Benefits

Who Uses BPM+?

Used Across Industries

BPM+ in Financial Services

BPM+ in Healthcare

Trisotech: A Leader in BPM+

Trisotech in Financial Services:

Trisotech in Healthcare:

Why Choose Trisotech for BPM+?

Start Your BPM+ Journey

Trisotech

the Innovator

Model, Automate, and Govern every Decision

Intermountain^® Health’s

Mayo Expert Decision Advisor:
Revolutionizing Health IT with a Model-Driven Strategy, Enabling Rapid EHR Workflow Updates in Days, Not Months

Trisotech
in Financial Services:

Trisotech
in Healthcare:

the
Innovator

How Trisotech Addresses
Decision Intelligence (DI)

How Trisotech Addresses
Decision Intelligence Platform (DIP)

How Trisotech Addresses
Decision Intelligence in Financial Services

How Trisotech Addresses
Decision Intelligence in Healthcare

the
Innovator