By Joseph Gucciardi, MS, CCE

At the 2025 AAMI eXchange in New Orleans, I co-presented a session titled “From Reactive to Proactive: Enhancing Medical Device Safety in the CMMS,” a topic that strikes a nerve with HTM professionals facing increased expectations—from faster repairs and tighter compliance to a stronger role in patient safety. 

Our goal was to show how the CMMS can become more than a logbook for work orders. With the right workflow design, it can be a proactive tool for managing clinical risk.

Why Now?

Healthcare organizations are under mounting pressure: aging medical devices, staffing shortages, cybersecurity threats, and increased regulatory oversight. HTM teams are expected to do more with less—and ensure that medical equipment is not only functional but also safe, documented, and ready to support care.

Yet most CMMS tools still rely on basic intake fields and reactive workflows. Tickets often lack context. Safety issues go unnoticed until audits—or worse, until patient care is delayed. HTM teams know the data is there, but they haven’t had the tools to act on it.

A New Approach to CMMS Design

The session introduced a patient safety–oriented redesign of CMMS workflows. While the examples are based on recent implementation experiences, the strategies discussed aren’t vendor-specific; they’re grounded in concepts any HTM team can begin applying.

We focus on five key areas:

1. Structured Intake: Forms and digital tools can be designed to capture clinical impact upfront. Questions like “Was patient care delayed?” or “Is the device currently in use?” help flag potential safety risks at the point of intake.
2. Risk-Based Triage and Assignment: Instead of triaging by ticket order, workflows can use device attributes, service history, and clinical location to assign and escalate based on risk. Predictive models and rules-based logic can enhance this approach.
3. Dashboards that Surface Safety Issues: Dashboards can highlight unresolved work on high-risk devices, show Service Level Agreement breaches, and spot recurring safety-related patterns. These aren’t just metrics—they’re conversation starters for compliance reviews, department meetings, and capital planning.
4. Integrations with Other Systems: Tying the CMMS to cybersecurity tools, incident reporting platforms, and recall management systems closes the loop. When device-related risks are flagged in multiple systems, HTM can respond faster and document the full picture.
5. Patient Safety as a Workflow Outcome: Medical device safety isn’t just about preventing downtime. It’s about embedding safety logic into how work orders are created, prioritized, routed, and resolved.

Practical Takeaways for Any HTM Team

Any HTM department can begin shifting its CMMS toward safety outcomes by: 

• Adding structured intake questions related to patient care impact 
• Using existing asset fields (location, criticality) to guide routing 
• Creating dashboards that highlight unresolved issues tied to high-risk devices 
• Collaborating with risk management, cybersecurity, and informatics teams to share data

These small changes lay the groundwork for a more proactive CMMS—one that not only tracks what’s broken but also helps prevent the next issue from happening at all.

The Road Ahead

As HTM takes on a larger role in clinical safety, our systems must evolve with us. Whether you’re customizing an existing CMMS or exploring new platforms, think beyond the next PM schedule. Ask how your data, workflows, and reporting can help your team surface and act on safety risks—before they reach the bedside.

Author Bio: Joseph Gucciardi, MS, CCE, is a business process consultant with Optimum Healthcare IT and a certified clinical engineer. He previously served as a senior regional clinical engineer with the US Department of Veterans Affairs.

Disclosures: The author consults on healthcare workflow design and implementation. This article reflects general principles and does not promote any specific product or platform.

ID 113077722 © Dreammasterphotographer | Dreamstime.com

Related Read:

Corti has launched FactsR, a real-time agentic reasoning system designed to enhance ambient documentation during clinical consultations by reducing extraneous content and minimizing the need for post-visit edits.

The system integrates with ambient AI tools and uses a recursive, fact-first architecture to identify, validate, and structure clinical information—such as symptoms, vitals, and medications—as conversations unfold. According to Corti, early tests show that FactsR reduces AI-generated note bloat by over 65%, helping clinicians produce more concise and relevant documentation.

Unlike traditional large language models retrofitted for healthcare, FactsR is powered by Corti’s recursive fact-first reasoning loop, a purpose-built engine designed to surface, validate, and structure clinical knowledge in real time as conversations unfold. The tool is delivered as a modular API, allowing developers to embed it directly into healthcare applications.

Why a Recursive Approach Matters

Many traditional ambient documentation tools process raw transcripts through general-purpose language models after a consultation ends, often producing lengthy summaries that clinicians spend up to three hours a week correcting.

FactsR takes a different approach, from passive summarization to active reasoning. Its workflow consists of four key stages:

1. Listen and Extract in Real Time: As the consultation unfolds, FactsR continuously identifies and surfaces structured clinical “facts”—such as symptoms, vitals, medications, and social history.
2. Vet and Refine with Specialized AI: Each fact is automatically reviewed and improved through an AI-driven feedback loop. If something is unclear, the system refines it until it is accurate, consistent, and ready to use.
3. Clinician-in-the-Loop: Clinicians can review, accept, or adjust facts as they go. Early adopters report far fewer post-visit edits and rarely need to add missing information after the consultation, according to Corti. 
4. Generate EHR-Ready Notes: Once the facts are finalized, the system assembles a concise summary that’s free from long, verbose summaries or irrelevant content.

Reported benefits include:

1. Less Screen Time: Early trials show that users spend minutes, not hours, on corrections
2. Better Patient Focus: Real‑time reasoning means decisions stay in the consultation, not in hindsight.
3. Audit‑Ready Transparency: Every fact carries a timestamp, confidence score, and link back to the conversation.
4. Healthcare AI that Delivers: Reduces general-purpose AI-driven “note bloat” by 65%.

The innovation behind FactsR has been published together with evaluation results on the public benchmark Primock57 dataset. The evaluation shows that FactsR increases clinical completeness by 13%, capturing significantly more of the relevant medical information compared to traditional ambient scribes, while reducing note bloat by over 65% with a clinician in the loop.

FactsR is offered today through a consumption‑based API with enterprise‑grade HIPAA and GDPR compliance. 

ID 80884410 | Doctor Patient © Imtmphoto | Dreamstime.com

Related Read:

GE HealthCare has announced the integration of its proprietary algorithms and features with MIM Encore, a platform developed by MIM Software, aimed at improving digital imaging and streamlining clinical workflows.

The implementation offers new capabilities for healthcare providers using GE HealthCare systems and MIM software. Built using clinician feedback, MIM Encore is designed as a unified platform to support diagnostic accuracy, operational efficiency, and personalized care planning.

“In today’s rapidly evolving healthcare landscape, operational efficiency and seamless collaboration are not just goals—they’re the cornerstone to success. That’s why we aim to provide tools that can help enhance providers’ confidence in decision making and support patients in receiving personalized care,” says Jean-Luc Procaccini, president and CEO of molecular imaging and computed tomography at GE HealthCare, in a release.

Expanded Capabilities for MIM and GE HealthCare Users

MIM Encore now includes post-processing tools developed for GE HealthCare systems, aiming to support consistent image quality and reduce manual steps in nuclear medicine and cardiology workflows. The platform combines features such as automated read preparation, structured reporting, and flexible interpretation tools for PET/CT, SPECT/CT, and multi-modality fusion in one system.

According to the company, the integration is intended to support accurate diagnoses and more consistent communication across clinical teams.

“Customers are telling us that this pairing is exactly what users have been looking for. The combined solution enables streamlined, accurate reading of images, supports quantitative analysis out of the box, and helps eliminate manual entries,” says Andrew Nelson, CEO of MIM Software, a GE HealthCare company, in a release.

MIM Encore includes resolution recovery and image-enhancement features tailored to GE HealthCare scanners, with the goal of improving workflow and diagnostic consistency across specialties:

• Oncology: The platform supports configurable enhancements for SPECT imaging, including resolution recovery, attenuation and scatter correction, advanced filtering, and motion correction. It also allows for dynamic and static scan viewing, image sharing, and quantitation tools.
• Cardiology: Cardiac imaging is supported by PET and SPECT tools offering motion correction, automated quality checks, and displays intended to streamline cardiac assessments. The platform also supports key radiotracers and incorporates algorithms such as Evolution for Cardiac, developed at Johns Hopkins and the University of North Carolina.
• Neurology: MIM Encore includes tools for 3D rendering and reconstruction in neurodegenerative imaging, designed to produce consistent, high-quality images and assist in diagnosis and treatment planning.

GE HealthCare’s Effortless Workflow also integrates with MIM Encore, with features intended to simplify interface navigation, reduce manual input, and help manage increasing patient volumes.

GE HealthCare acquired MIM Software in 2024 to combine strengths in multi-modality imaging, quantitation, automation, and molecular imaging.

Photo caption: MIM Encore

Photo credit: GE HealthCare

AU10TIX, a company specializing in identity verification and fraud prevention, has expanded its product suite with the release of AnyDoc Authentication, a tool designed to detect forged, tampered, or synthetic non-ID documents that may evade traditional verification systems.

The solution uses AI, forensic forgery detection, and metadata analysis to help organizations detect document fraud, maintain regulatory compliance, and scale secure onboarding. This layer of protection supports a range of document types, including utility bills, bank statements, tax filings, business licenses, and more.

According to AU10TIX, the system runs more than 150 AI-driven forgery tests, validates embedded metadata for consistency, and processes documents within five to 20 seconds. It is format-agnostic, working with both PDFs and image files, and can classify documents in under three seconds.

Key capabilities include:

• Detection of manipulated text, synthetic content, and structural anomalies
• Cross-checking of metadata such as timestamps and issuing authority
• Support for a range of document types
• Real-time decision-making and document classification

“Effective fraud prevention demands more than identity verification; it is built on ensuring the authenticity of every supporting document,” said Yair Tal, CEO of AU10TIX, in a statement.

AnyDoc Authentication is designed to align with KYC, KYB, and AML regulatory frameworks. It incorporates third-party data verification to reduce false positives and detect synthetic or deepfake document attempts. Optimized for high-risk, high-volume sectors, AnyDoc Authentication is suited for multiple industries, including healthcare where it can assist in authenticating insurance documents, prescriptions, and provider credentials. 

AnyDoc Authentication is now available to businesses seeking to enhance fraud detection and regulatory compliance.

ID 212388480 © Nicoelnino | Dreamstime.com

A new 2025 Future Ready Healthcare Survey Report from Wolters Kluwer Health, conducted in partnership with the independent marketing research firm Ipsos, reveals that while healthcare professionals widely recognize the transformative potential of generative AI (GenAI), most organizations are not yet ready to harness its full value.

The survey identifies strong enthusiasm for using GenAI to address the current challenges of workforce shortages, burnout, high healthcare costs, and rising administrative burdens, as well as keen interest in leveraging GenAI to achieve the next level of innovation and efficiency across the enterprise.

However, the data also show a clear disconnect between what organizations say they want to achieve with GenAI and how prepared they are to deliver on that promise. For example, while 80% of respondents cited “optimizing workflows” as a top organizational goal, only 63% feel prepared to use GenAI to do so.

[RELATED READ: Why Health Systems Should Ensure BMETs Are Comfortable and Confident with AI]

“GenAI has the potential to be a powerful tool for supporting sustainability in healthcare organizations right now, as well as preparing them for a more efficient future,” says Greg Samios, CEO of Wolters Kluwer Health, in a release. “The challenge is developing a strategy that can both optimize the current state in a highly volatile environment and simultaneously equip organizations with the digital capabilities they need to remain competitive over the next several years. Right now, organizations are at risk of falling behind unless they take a more cohesive approach to making GenAI standardized, scalable, and impactful.”

Healthcare’s GenAI Aspirations Collide with Operational Gaps

Key Findings:

• Nurse staffing and workforce concerns are at the top of the priority list for health GenAI applications: 85% of respondents cited “recruiting/retaining nursing staff” as a top priority, while 76% identified “reducing clinician burnout” as a main concern.
• Leaders are focusing on the basics to keep the enterprise running: GenAI-driven technologies are likely to be part of the solution for longstanding challenges, such as addressing the burdens of prior authorizations (67%), electronic health record management (62%), cybersecurity preparedness (68%), and supporting telehealth/virtual care programs (65%).
• But clinical staff expect more from the GenAI revolution: In qualitative responses, participants said they understand and acknowledge the need for workflow optimization but also want to see innovative capabilities such as ambient listening, clinical decision support leveraging GenAI, and assistance with communication and documentation utilizing GenAI.
• Formal GenAI policies and guidance are scarce: Only 18% of respondents were aware of formal organizational policies governing GenAI use, and only 1 in 5 reported being required to take structured training.
• As a result, concerns about appropriate implementation persist: More than half (57%) believe that overreliance on GenAI may erode clinical decision-making skills, while 55% are concerned that lack of transparency around GenAI’s potential role in making diagnoses could contribute to unclear reasoning behind patient-facing decisions.

“To successfully integrate GenAI, organizations must recognize its current limitations, as well as anticipate its realistic evolution and the regulatory landscape,” says Peter Bonis, MD, chief medical officer at Wolters Kluwer Health, in a release. “It is also vital to select GenAI applications that align with both clinical and financial goals while fitting into existing workflows. Establishing robust and ongoing governance will be essential to succeed.”

ID 322452409 | Ai Healthcare © Paradee Paradee | Dreamstime.com

Related Read:

As artificial intelligence rapidly transforms the cyber threat landscape in healthcare, new data from Black Book Research reveals a critical and overlooked vulnerability: the physical security of hospitals, clinics, and payer organizations. 

While 93% of surveyed cybersecurity leaders say their digital defenses are strong, fewer than one in five have any strategic plan to address the rise of AI-enabled physical security threats.

Based on Q2 2025 polling of 1,128 provider and payer cybersecurity decision-makers worldwide, Black Book’s findings point to a dangerous disconnect. Healthcare organizations are investing heavily in digital firewalls, endpoint protection, and ransomware defense, yet they remain largely blind to a new class of threats powered by generative AI—threats that can mimic clinician voices, manipulate surveillance footage, bypass building access systems, and compromise smart infrastructure.

“AI is no longer just a digital threat; it is a physical one,” says Doug Brown, founder of Black Book Research, in a release. “We are now seeing threat actors use generative AI to impersonate clinicians, defeat voice authentication, bypass smart locks, and manipulate surveillance systems. These are no longer hypothetical scenarios. Attackers are walking through the front doors of hospitals using tools that outpace the slow churn of healthcare policy, procurement, and security oversight. Any health system that still separates physical and cyber risk is operating on outdated assumptions.”

Respondents described a widening gap between cyber risk awareness and operational readiness. Despite growing headlines about AI-generated phishing, deepfake impersonations, and drone surveillance, the healthcare sector has not meaningfully upgraded its physical security posture in parallel with its digital investments.

Key findings from the Black Book Q2 2025 poll:

• 93% of cybersecurity leaders say their digital protections are adequate, but only 18% report having any strategy to mitigate AI-driven physical threats.
• 71% of hospital executives acknowledge their facility’s physical security systems are unprepared for manipulations such as deepfake badge credentials or sensor spoofing.
• 67% of payer organizations with physical office sites or hybrid call centers were unaware that AI voice cloning could defeat IVR authentication or front-desk verification processes.
• 82% of all respondents reported they had not conducted a cyber-physical risk audit in the past 12 months.

Vendors Recognized for Addressing AI-Driven Cyber-Physical Threats

Survey respondents identified several vendors as having strong capabilities in detecting and mitigating emerging AI-driven threats that cross digital and physical domains. These platforms are used across hospitals, health systems, and payer networks and include tools based on machine learning, behavioral analytics, and autonomous threat detection.

• Armis offers agentless visibility and AI-based monitoring for connected medical devices and operational technologies.
• Bishop Fox provides red teaming services used to expose vulnerabilities in surveillance, badge access systems, and connected care infrastructure.
• Claroty (Medigate) protects IoMT and clinical systems through machine learning that detects manipulation of connected devices and smart facility components.
• Cisco Secure supports Zero Trust architectures and includes AI-powered analytics to monitor digital and physical access behaviors in hybrid clinical environments.
• CrowdStrike offers agent-based AI for detecting behavioral anomalies and sophisticated threat campaigns across clinical endpoints.
• Cynerio secures medical IoT systems by baselining device behavior and flagging manipulation or ransomware infections.
• Darktrace uses self-learning AI to detect impersonation, badge cloning, and network manipulation across thousands of healthcare organizations.
• IBM Security offers platforms that correlate digital and physical access data while automating threat response.
• Okta provides identity and access management with adaptive AI to prevent credential theft and synthetic access.
• Ordr enforces security policies for medical and building systems, isolating unauthorized device activity.
• Palo Alto Networks uses AI-powered platforms to enforce segmentation and detect polymorphic malware.
• SentinelOne delivers autonomous endpoint protection against AI-crafted exploits and real-time threat behaviors.
• Vectra AI flags privilege escalation and behavioral deviations common in AI-generated attacks.

These solutions reflect a growing shift toward integrated cyber-physical risk management, as AI-generated threats increasingly evade traditional rules-based defenses.

What Makes a Tool ‘AI Threat-Ready’ in Healthcare?

According to Black Book, effective tools must detect synthetic behaviors rather than just known malware signatures, identify identity misuse such as voice or video impersonation, monitor IoMT and operational environments, and support red teaming or simulation of AI threats to proactively assess system vulnerabilities.

ID 309840907 © Tero Vesalainen | Dreamstime.com

This guide compares several CMMS currently available to HTM teams, highlighting key aspects such as implementation time, training formats, security features, and pricing structures. HTM teams can use this guide to assess which systems align with their operational needs.

EQ2 HEMS by TMA Systems – HEMS (Hospital Equipment Management System)

TruAsset – TruAsset

FSI – FSI

MediMizer Software – MediMizer Software

MediMizer Software – iRequestManager

Renovo Solutions – RENOVOLive

Phoenix Data Systems, Inc – AIMS 3

Brightly Software – TheWorxHub

Last updated June 2025.

Information for this guide is based on data submitted by CMMS marketers. 24×7 strives for accuracy in all data but cannot be held responsible for claims made by marketers. All CMMS marketers get one listing at no charge. Advertisers are offered multiple listings. All CMMS platforms may not be included. Email editor@24x7mag.com to be considered for the next update.

Clairity Inc, a digital health company advancing artificial intelligence (AI)-driven healthcare solutions, has received US Food and Drug Administration (FDA) De Novo authorization for Clairity Breast, a novel, image-based prognostic platform designed to predict five-year breast cancer risk from a routine screening mammogram. 

With this authorization, Clairity is planning to launch among leading health systems through 2025.

Clairity Breast analyzes subtle imaging features on screening mammograms that correlate with future breast cancer risk, making early risk prediction feasible based on a screening mammogram alone. The result is a validated five-year risk score delivered to healthcare providers through existing clinical infrastructures, supporting more personalized follow-up care.

“For more than 60 years, mammograms have saved lives by detecting early-stage cancers. Now, advancements in AI and computer vision can uncover hidden clues in the mammograms—invisible to the human eye—to help predict future risk,” says Connie Lehman, MD, PhD, founder of Clairity, who is also a breast imaging specialist at Mass General Brigham, in a release. “By delivering validated, equitable risk assessments, we can help expand access to life-saving early detection and prevention for women everywhere.”

Limitations of Traditional Risk Models

Each year, more than 2.3 million new cases of breast cancer are diagnosed worldwide, including over 370,000 cases in women in the United States. Early detection and risk reduction are powerful tools to save lives, but their most effective deployment depends on accurate risk assessment. Most risk assessment models rely heavily on age and family history to predict risk. 

However, 85% of women diagnosed with breast cancer have no family history, and nearly half have no identifiable risk factors. In addition, traditional risk models, built on data from predominantly European Caucasian women, have not generalized well to women of diverse racial and ethnic backgrounds.

“Personalized, risk-based screening is critical to improving breast cancer outcomes, and AI tools offer us the best opportunity to fulfill that potential,” says Robert A. Smith, PhD, senior vice president of early cancer detection science at the American Cancer Society, in a release. “By integrating AI models that assess individual risk, we can better identify women at higher risk, and those who may benefit from supplemental screening methods, such as MRI, improving early detection and more effective prevention strategies.”

Photo caption: Clinical workflow within Clairity Breast

Photo credit: Clairity

Related Read:

MSKai, an image identification and post-processing software platform for spine imaging, has received 510(k) clearance from the US Food and Drug Administration (FDA), authorizing its use by physicians and radiologists for lumbar spine MRI analysis. 

The FDA determined that MSKai is substantially equivalent to legally marketed devices, allowing it to be marketed under the general controls of the Federal Food, Drug, and Cosmetic Act.

“The FDA’s decision confirms that MSKai meets rigorous safety and performance standards as a spine imaging tool,” says Chip Wade, PhD, chief operating officer at MSKai, in a release. “We’re proud to deliver a product that gives healthcare professionals enhanced capabilities in lumbar spine analysis while reinforcing the central role of expert clinical judgement.”

MSKai is designed to assist medical professionals in the evaluation of previously acquired T2-weighted lumbar spine MRIs. The software enables users to perform anatomy segmentation, labeling, measurement, and export of quantitative and qualitative results into customizable reports. 

MSKai is not a diagnostic device and does not provide or recommend any medical diagnosis or treatment. Instead, it serves as a decision-support tool that offers repeatable insights for users trained in medical imaging. Users are responsible for confirming preferences, verifying automated measurements, and finalizing reports in accordance with clinical best practices.

ID 28422282 © Andreblais | Dreamstime.com

Related Read:

Rad AI has secured an additional $8 million in Series C funding from four US health systems, advancing its push to scale generative AI tools across hospitals and clinics.

The investment—led by Advocate Health, Memorial Hermann Health System, Corewell Health, and Atlantic Health System—brings Rad AI’s total Series C funding to $68 million. These health systems are partnering with Rad AI to expand the use of generative AI across complex clinical environments, aiming to improve workflow efficiency, care quality, and patient outcomes at scale. 

Collectively, the organizations operate over 100 hospitals and serve millions of patients nationwide, providing real-world insights to help accelerate the development and deployment of AI-driven solutions in radiology and follow-up care.

“The impact of AI in healthcare is no longer theoretical—it’s happening right now at scale,” says Doktor Gurson, co-founder and CEO of Rad AI, in a release. “It’s an honor to collaborate with these leading health systems to expand that impact even further, building solutions that improve care for millions of patients.”

Rad AI’s Radiology Solutions

Rad AI’s solutions support providers responsible for nearly half of all imaging volume in the US, according to a release from the company, helping radiologists work faster, reduce dictation load, and improve care quality.

“Memorial Hermann invests in AI not just to adapt to technology, but to transform patient care and improve workflows,” says Feby Abraham, PhD, executive vice president and chief strategy officer for Memorial Hermann, in a release. “We are always seeking partners who can deliver measurable impact on outcomes, efficiency, and improving the patient experience, and Rad AI checks all those boxes.”

Rad AI delivers an integrated solution to multifaceted clinical challenges:

• Rad AI Impressions — a generative AI application in radiology that automates the impression section of reports, saving radiologists more than an hour per shift on average.
• Rad AI Reporting — designed to enhance the radiology workflow with features like Omni Unchanged, which pulls stable findings from prior reports with one phrase and cuts follow-up dictation time by 50% and spoken words by 90%. Omni Report enables radiologists to dictate naturally and auto-fills structured templates, up to doubling reporting speed and easing cognitive load.
• Rad AI Continuity — closes the loop on incidental findings by automatically tracking and coordinating follow-up care. Health systems using Continuity have improved follow-up exam completion rates from approximately 30% to over 75%, helping ensure critical findings don’t fall through the cracks.

“We are pleased to invest in a company that is at the forefront of developing technology to make the jobs of physicians more convenient and efficient,” says Christian Rische, vice president and managing director, Corewell Health Ventures, in a release. “The products of Rad AI will help lead to a reduced workload for providers and, most importantly, potential improvements in patient care.”

Photo caption: Rad AI reporting illustration

Photo credit: Rad AI

Further Reading for You: