Detection of visually occult metastatic lymph nodes using molecularly targeted fluorescent imaging during surgical resection of pancreatic cancer.

BACKGROUND: Although most patients with PDAC experience distant failure after resection, a significant portion still present with local recurrence. Intraoperative fluorescent imaging can potentially facilitate the visualization of involved peritumoral LNs and guide the locoregional extent of nodal dissection. Here, the efficacy of targeted intraoperative fluorescent imaging was examined in the detection of metastatic lymph nodes (LNs) during resection of pancreatic ductal adenocarcinoma (PDAC). METHODS: A dose-escalation prospective study was performed to assess feasibility of tumor detection within peripancreatic LNs using cetuximab-IRDye800 in PDAC patients. Fluorescent imaging of dissected LNs was analyzed ex vivo macroscopically and microscopically and fluorescence was correlated with histopathology. RESULTS: A total of 144 LNs (72 in the low-dose and 72 in the high-dose cohort) were evaluated. Detection of metastatic LNs by fluorescence was better in the low-dose (50 mg) cohort, where sensitivity and specificity was 100% and 78% macroscopically, and 91% and 66% microscopically. More importantly, this method was able to detect occult foci of tumor (measuring < 5 mm) with a sensitivity of 88% (15/17 LNs). CONCLUSION: This study provides proof of concept that intraoperative fluorescent imaging with cetuximab-IRDye800 can facilitate the detection of peripancreatic lymph nodes often containing subclinical foci of disease.

Intraoperative Pancreatic Cancer Detection using Tumor-Specific Multimodality Molecular Imaging.

BACKGROUND: Operative management of pancreatic ductal adenocarcinoma (PDAC) is complicated by several key decisions during the procedure. Identification of metastatic disease at the outset and, when none is found, complete (R0) resection of primary tumor are key to optimizing clinical outcomes. The use of tumor-targeted molecular imaging, based on photoacoustic and fluorescence optical imaging, can provide crucial information to the surgeon. The first-in-human use of multimodality molecular imaging for intraoperative detection of pancreatic cancer is reported using cetuximab-IRDye800, a near-infrared fluorescent agent that binds to epidermal growth factor receptor. METHODS: A dose-escalation study was performed to assess safety and feasibility of targeting and identifying PDAC in a tumor-specific manner using cetuximab-IRDye800 in patients undergoing surgical resection for pancreatic cancer. Patients received a loading dose of 100 mg of unlabeled cetuximab before infusion of cetuximab-IRDye800 (50 mg or 100 mg). Multi-instrument fluorescence imaging was performed throughout the surgery in addition to fluorescence and photoacoustic imaging ex vivo. RESULTS: Seven patients with resectable pancreatic masses suspected to be PDAC were enrolled in this study. Fluorescence imaging successfully identified tumor with a significantly higher mean fluorescence intensity in the tumor (0.09 ± 0.06) versus surrounding normal pancreatic tissue (0.02 ± 0.01), and pancreatitis (0.04 ± 0.01; p < 0.001), with a sensitivity of 96.1% and specificity of 67.0%. The mean photoacoustic signal in the tumor site was 3.7-fold higher than surrounding tissue. CONCLUSIONS: The safety and feasibilty of intraoperative, tumor-specific detection of PDAC using cetuximab-IRDye800 with multimodal molecular imaging of the primary tumor and metastases was demonstrated.

First-in-human intraoperative near-infrared fluorescence imaging of glioblastoma using cetuximab-IRDye800.

INTRODUCTION: Maximizing extent of surgical resection with the least morbidity remains critical for survival in glioblastoma patients, and we hypothesize that it can be improved by enhancements in intraoperative tumor detection. In a clinical study, we determined if therapeutic antibodies could be repurposed for intraoperative imaging during resection. METHODS: Fluorescently labeled cetuximab-IRDye800 was systemically administered to three patients 2 days prior to surgery. Near-infrared fluorescence imaging of tumor and histologically negative peri-tumoral tissue was performed intraoperatively and ex vivo. Fluorescence was measured as mean fluorescence intensity (MFI), and tumor-to-background ratios (TBRs) were calculated by comparing MFIs of tumor and histologically uninvolved tissue. RESULTS: The mean TBR was significantly higher in tumor tissue of contrast-enhancing (CE) tumors on preoperative imaging (4.0 ± 0.5) compared to non-CE tumors (1.2 ± 0.3; p = 0.02). The TBR was higher at a 100 mg dose than at 50 mg (4.3 vs. 3.6). The smallest detectable tumor volume in a closed-field setting was 70 mg with 50 mg of dye and 10 mg with 100 mg. On sections of paraffin embedded tissues, fluorescence positively correlated with histological evidence of tumor. Sensitivity and specificity of tumor fluorescence for viable tumor detection was calculated and fluorescence was found to be highly sensitive (73.0% for 50 mg dose, 98.2% for 100 mg dose) and specific (66.3% for 50 mg dose, 69.8% for 100 mg dose) for viable tumor tissue in CE tumors while normal peri-tumoral tissue showed minimal fluorescence. CONCLUSION: This first-in-human study demonstrates the feasibility and safety of antibody based imaging for CE glioblastomas.

The algorithm journey map: a tangible approach to implementing AI solutions in healthcare.

When integrating AI tools in healthcare settings, complex interactions between technologies and primary users are not always fully understood or visible. This deficient and ambiguous understanding hampers attempts by healthcare organizations to adopt AI/ML, and it also creates new challenges for researchers to identify opportunities for simplifying adoption and developing best practices for the use of AI-based solutions. Our study fills this gap by documenting the process of designing, building, and maintaining an AI solution called SepsisWatch at Duke University Health System. We conducted 20 interviews with the team of engineers and scientists that led the multi-year effort to build the tool, integrate it into practice, and maintain the solution. This "Algorithm Journey Map" enumerates all social and technical activities throughout the AI solution's procurement, development, integration, and full lifecycle management. In addition to mapping the "who?" and "what?" of the adoption of the AI tool, we also show several 'lessons learned' throughout the algorithm journey maps including modeling assumptions, stakeholder inclusion, and organizational structure. In doing so, we identify generalizable insights about how to recognize and navigate barriers to AI/ML adoption in healthcare settings. We expect that this effort will further the development of best practices for operationalizing and sustaining ethical principles-in algorithmic systems.

Empowering US healthcare delivery organizations: Cultivating a community of practice to harness AI and advance health equity.

Healthcare delivery organizations (HDOs) in the US must contend with the potential for AI to worsen health inequities. But there is no standard set of procedures for HDOs to adopt to navigate these challenges. There is an urgent need for HDOs to present a unified approach to proactively address the potential for AI to worsen health inequities. Amidst this background, Health AI Partnership (HAIP) launched a community of practice to convene stakeholders from across HDOs to tackle challenges related to the use of AI. On February 15, 2023, HAIP hosted an inaugural workshop focused on the question, "Our health care delivery setting is considering adopting a new solution that uses AI. How do we assess the potential future impact on health inequities?" This topic emerged as a common challenge faced by all HDOs participating in HAIP. The workshop had 2 main goals. First, we wanted to ensure participants could talk openly without reservations about challenging topics such as health equity. The second goal was to develop an actionable, generalizable framework that could be immediately put into practice. The workshop engaged 77 participants with 100% representation from all 10 HDOs and invited ecosystem partners. In an accompanying Research Article, we share the Health Equity Across the AI Lifecycle (HEAAL) framework. We invite and encourage HDOs to test the HEAAL framework internally and share feedback so that we can continue to refine and maintain the set of procedures. The HEAAL framework reveals the challenges associated with rigorously assessing the potential for AI to worsen health inequities. Significant investment in personnel, capabilities, and data infrastructure is required, and the level of investment needed could be beyond reach for most HDOs. We look forward to expanding our community of practice to assist HDOs around the world.

Development and preliminary testing of Health Equity Across the AI Lifecycle (HEAAL): A framework for healthcare delivery organizations to mitigate the risk of AI solutions worsening health inequities.

The use of data-driven technologies such as Artificial Intelligence (AI) and Machine Learning (ML) is growing in healthcare. However, the proliferation of healthcare AI tools has outpaced regulatory frameworks, accountability measures, and governance standards to ensure safe, effective, and equitable use. To address these gaps and tackle a common challenge faced by healthcare delivery organizations, a case-based workshop was organized, and a framework was developed to evaluate the potential impact of implementing an AI solution on health equity. The Health Equity Across the AI Lifecycle (HEAAL) is co-designed with extensive engagement of clinical, operational, technical, and regulatory leaders across healthcare delivery organizations and ecosystem partners in the US. It assesses 5 equity assessment domains-accountability, fairness, fitness for purpose, reliability and validity, and transparency-across the span of eight key decision points in the AI adoption lifecycle. It is a process-oriented framework containing 37 step-by-step procedures for evaluating an existing AI solution and 34 procedures for evaluating a new AI solution in total. Within each procedure, it identifies relevant key stakeholders and data sources used to conduct the procedure. HEAAL guides how healthcare delivery organizations may mitigate the potential risk of AI solutions worsening health inequities. It also informs how much resources and support are required to assess the potential impact of AI solutions on health inequities.

Frameworks for procurement, integration, monitoring, and evaluation of artificial intelligence tools in clinical settings: A systematic review.

Research on the applications of artificial intelligence (AI) tools in medicine has increased exponentially over the last few years but its implementation in clinical practice has not seen a commensurate increase with a lack of consensus on implementing and maintaining such tools. This systematic review aims to summarize frameworks focusing on procuring, implementing, monitoring, and evaluating AI tools in clinical practice. A comprehensive literature search, following PRSIMA guidelines was performed on MEDLINE, Wiley Cochrane, Scopus, and EBSCO databases, to identify and include articles recommending practices, frameworks or guidelines for AI procurement, integration, monitoring, and evaluation. From the included articles, data regarding study aim, use of a framework, rationale of the framework, details regarding AI implementation involving procurement, integration, monitoring, and evaluation were extracted. The extracted details were then mapped on to the Donabedian Plan, Do, Study, Act cycle domains. The search yielded 17,537 unique articles, out of which 47 were evaluated for inclusion based on their full texts and 25 articles were included in the review. Common themes extracted included transparency, feasibility of operation within existing workflows, integrating into existing workflows, validation of the tool using predefined performance indicators and improving the algorithm and/or adjusting the tool to improve performance. Among the four domains (Plan, Do, Study, Act) the most common domain was Plan (84%, n = 21), followed by Study (60%, n = 15), Do (52%, n = 13), & Act (24%, n = 6). Among 172 authors, only 1 (0.6%) was from a low-income country (LIC) and 2 (1.2%) were from lower-middle-income countries (LMICs). Healthcare professionals cite the implementation of AI tools within clinical settings as challenging owing to low levels of evidence focusing on integration in the Do and Act domains. The current healthcare AI landscape calls for increased data sharing and knowledge translation to facilitate common goals and reap maximum clinical benefit.