Citations

Abstract Background: Microsatellite instability-high (MSI-H) tumors respond well to immune checkpoint blockade and oftentimes not to chemotherapeutics. Despite value of determining MSI status to guide therapy, many patients’ samples are not untested. Deep learning models may be able to predict MSI status by analyzing hematoxylin and eosin (H&E) stained whole-slide images (WSIs). Validation of this tool will provide another tool to increase MSI testing. However, to be deployed into clinical routine care, prediction models need be externally validated in large and diverse patient cohorts. In addition, these models should provide uncertainty of prediction to help clinicians make informed decisions. Results: In this study, we introduce a novel Bayesian prediction model using whole-slide images (WSIs) and deep Gaussian processes (DGPs) in a weakly supervised learning context. Extensively tested on large datasets (n=3,146) from multiple centers, our model not only demonstrated superior performance but also showed that incorporating uncertainty into predictions significantly improves MSI prediction accuracy, achieving AUROC of >0.91 in colon cancer and >0.94 in gastric cancer. Additionally, an in-depth analysis within the gastric cancer cohort indicated a significant correlation between predicted MSI-H regions and immunotherapy response. Patients who responded to immune checkpoint inhibitors had a higher proportion of MSI-H regions (P-value < 0.05). This correlation was also observed in patients categorized as MSS but responsive to ICIs, highlighting the potential of our model to identify MSI-H patterns not detected through standard laboratory tests. This advancement could lead to more precise patient selection for ICI therapy, enhancing personalized treatment strategies in gastrointestinal cancer. Citation Format: Sunho Park, Minj Kim, Ji-Youn Sung, Jeong Hwan Park, Sung Hak Lee, Sam C. Wang, Jaeho Cheong, Tae Hyun Hwang. Explainable AI model incorporating uncertainty estimation for enhanced MSI-H prediction and immunotherapy response in gastrointestinal cancer [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 7385.

Abstract Traditional cancer research methodologies predominantly focus on 2D tumor modeling, including spatial profiling and AI-driven analysis at the 2D level. To advance beyond these limitations, we implemented Holotomography (HT), a 3D, label-free optical imaging method. This technique, leveraging refractive index contrasts, allows for enhanced visualization of tumor tissues, organoids, and cells in three dimensions. Using serial H&E sections and unstained slides, we created detailed 3D tumor models in gastric cancer, providing insights into tumor, immune, and stromal composition, as well as cell-cell interactions and extracellular matrix characteristics. AI algorithms further enhanced our 3D tumor modeling, offering novel perspectives on the initiation and progression of tumor, immune, and stromal components at the subcellular level. Analyzing gastric tumors treated with immune checkpoint inhibitors before, during, and after treatment revealed dynamic changes in spatial composition over time, offering unique insights into the evolution of the 3D tumor ecosystem. Additionally, by integrating spatial transcriptomic and in situ molecular imaging data, we developed a novel Multimodal 3D Tumor Model. This model not only uncovers subcellular-level molecular characteristics but also elucidates cellular interactions during treatment, suggesting potential biomarkers and therapeutic approaches. Lastly, by constructing 3D cellular interaction networks incorporating true 3D interactions, we provided an in-depth view of cellular communication within the tumor microenvironment. This pioneering approach, representing the first Multimodal 3D Tumor Model at the subcellular level, offers novel insights into gastric cancer's spatial evolution, potentially revolutionizing our understanding and treatment of gastric cancer. Citation Format: Yoon Ho Choi, Minji Kim, Katya Redekop, Inyeop Jang, Jean R. Clemenceau, Isabel Barnfather, Sumanth Reddy Nakkireddy, Changjin Hong, Sunho Park, Ji-Youn Sung, Jeong Hwan Park, Shitara Kohei, Aoki Yu, Sung Hak Lee, Sam Wang, Jaeho Cheong, Tae Hyun Hwang. AI-driven multimodal 3D tumor modeling with spatial molecular insights for predicting ICI response in gastric cancer [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 7400.

Background: Hip arthroscopy is rapidly advancing, with positive published outcomes at short- and midterm follow-up; however, available long-term data remain limited. Purpose: To evaluate outcomes of primary hip arthroscopy at a minimum 10-year follow-up at 2 academic centers by describing patient-reported outcomes and determining reoperation and total hip arthroplasty (THA) rates. Study Design: Case series; Level of evidence, 4. Methods: Patients with primary hip arthroscopy performed between January 1988 and April 2013 at 2 academic centers were evaluated for postoperative patient-reported outcomes—including the visual analog scale, Tegner Activity Scale score, Hip Outcome Score Activities of Daily Living and Sport Specific subscales, modified Harris Hip Score, Nonarthritic Hip Score, 12-item International Hip Outcome Tool, surgery satisfaction, and reoperations. Results: A total of 294 patients undergoing primary hip arthroscopy (age, 40 ± 14 years; 66% women; body mass index, 27 ± 6) were followed for 12 ± 3 years (range, 10-24 years) postoperatively. Labral debridement and repair were performed in 41% and 59% of patients, respectively. Of all patients who underwent interportal capsulotomy, 2% were extended to a T-capsulotomy, and 11% underwent capsular repair. At final follow-up, patients reported a mean visual analog scale at rest of 2 ± 2 and with use of 3 ± 3, a 12-item International Hip Outcome Tool of 68 ± 27, a Nonarthritic Hip Score of 81 ± 18, a modified Harris Hip Score of 79 ± 17, and a Hip Outcome Score Activities of Daily Living of 82 ± 19 and Sport Specific subscale of 74 ± 25. The mean surgical satisfaction was 8.4 ± 2.4 on a 10-point scale, with 10 representing the highest level of satisfaction. In total, 96 hips (33%) underwent reoperation—including 65 hips (22%) converting to THA. THA risk factors included older age, higher body mass index, lower lateral center-edge angle, larger alpha angle, higher preoperative Tönnis grade, as well as labral debridement and capsular nonrepair ( P≤ .039). Patients undergoing combined labral and capsular repair demonstrated a THA conversion rate of 3% compared with 31% for patients undergoing combined labral debridement and capsular nonrepair ( P = .006). Labral repair trended toward increased 10-year THA-free survival (84% vs 77%; P = .085), while capsular repair demonstrated significantly increased 10-year THA-free survival (97% vs 79%; P = .033). Conclusion: At a minimum 10-year follow-up, patients undergoing primary hip arthroscopy demonstrated high satisfaction and acceptable outcome scores. In total, 33% of patients underwent reoperation—including 22% who underwent THA. Conversion to THA was associated with patient factors including older age, higher Tönnis grade, and potentially modifiable surgical factors such as labral debridement and capsular nonrepair.

Abstract Background We aimed to determine the factors associated with sequential blood culture time to positivity (STTP) and validate the previously defined time to positivity (TTP) ratio threshold of 1.5 in predicting adverse disease outcomes and mortality of Staphylococcus aureus bacteremia (SAB). Methods We conducted an observational study of adult patients with SAB. The TTP ratio was calculated by dividing the TTP of the second blood culture by that of the first. Results Of 186 patients, 69 (37%) were female, with a mean age of 63.6 years. Median TTP was 12 hours (interquartile range [IQR], 10–15 hours) from the initial and 21 hours (17–29) from sequential blood cultures. Methicillin-resistant S aureus (MRSA)–infected patients had significantly shorter STTPs (P < .001) and lower TTP ratios (P < .001) compared to patients with methicillin-susceptible S aureus (MSSA). A significant correlation between initial and STTP was observed in patients with MRSA (r = 0.42, P = .002) but not in those with MSSA. A higher rate of native valve endocarditis (NVE) significantly correlated with a TTP ratio of ≤1.5 (odds ratio, 2.65 [95% confidence interval, 1.3–5.6]; P = .01). The subgroup having an initial TTP <12 hours combined with a TTP ratio ≤1.5 showed the highest prevalence of NVE. Conclusions The STTP varies based on methicillin susceptibility of S aureus isolate. This study suggests a potential clinical utility of the STTP to identify patients at a higher risk of NVE. However, prospective studies are required to validate these findings.

Abstract Two variants of semantic dementia are recognized based on the laterality of temporal lobe involvement: a left-predominant variant associated with verbal knowledge impairment and a right-predominant variant associated with behavioural changes and non-verbal knowledge loss. This cross-sectional clinicoradiologic study aimed to assess whole hippocampal, subregion, and/or subfield volume loss in semantic dementia versus controls and across its variants. Thirty-five semantic dementia participants and 15 controls from the Neurodegenerative Research Group at Mayo Clinic who had completed 3.0-T volumetric magnetic resonance imaging and 18F-fluorodeoxyglucose-positron emission tomography were included. Classification as left-predominant (n = 25) or right-predominant (n = 10) variant was based on temporal lobe hypometabolism. Volumes of hippocampal subregions (head, body, and tail) and subfields (parasubiculum, presubiculum, subiculum, cornu ammonis 1, cornu ammonis 3, cornu ammonis 4, dentate gyrus, molecular layer, hippocampal–amygdaloid transition area, and fimbria) were obtained using FreeSurfer 7. Subfield volumes were measured separately from head and body subregions. We fit linear mixed-effects models using log-transformed whole hippocampal/subregion/subfield volumes as dependent variables; age, sex, total intracranial volume, hemisphere and a group-by-hemisphere interaction as fixed effects; and subregion/subfield nested within hemisphere as a random effect. Significant results (P < 0.05) are hereby reported. At the whole hippocampal level, the dominant (predominantly involved) hemisphere of both variants showed 23–27% smaller volumes than controls. The non-dominant (less involved) hemisphere of the right-predominant variant also showed volume loss versus controls and the left-predominant variant. At the subregional level, both variants showed 17–28% smaller dominant hemisphere head, body, and tail than controls, with the right-predominant variant also showing 8–12% smaller non-dominant hemisphere head than controls and left-predominant variant. At the subfield level, the left-predominant variant showed 12–36% smaller volumes across all dominant hemisphere subfields and 14–15% smaller non-dominant hemisphere parasubiculum, presubiculum (head and body), subiculum (head) and hippocampal–amygdaloid transition area than controls. The right-predominant variant showed 16–49% smaller volumes across all dominant hemisphere subfields and 14–22% smaller parasubiculum, presubiculum, subiculum, cornu ammonis 3, hippocampal–amygdaloid transition area (all from the head) and fimbria of non-dominant hemisphere versus controls. Comparison of dominant hemispheres showed 16–29% smaller volumes of the parasubiculum, presubiculum (head) and fimbria in the right-predominant than left-predominant variant; comparison of non-dominant hemispheres showed 12–15% smaller cornu ammonis 3, cornu ammonis 4, dentate gyrus, hippocampal–amygdaloid transition area (all from the head) and cornu ammonis 1, cornu ammonis 3 and cornu ammonis 4 (all from the body) in the right-predominant variant. All hippocampal subregion/subfield volumes are affected in semantic dementia, although some are more affected in both dominant and non-dominant hemispheres of the right-predominant than the left-predominant variant by the time of presentation. Involvement of hippocampal structures is apparently more subregion dependent than subfield dependent, indicating possible superiority of subregion volumes as disease biomarkers.

PURPOSE Current guidelines for the management of metastatic non–small cell lung cancer (NSCLC) without driver mutations recommend checkpoint immunotherapy with PD-1/PD-L1 inhibitors, either alone or in combination with chemotherapy. This approach fails to account for individual patient variability and host immune factors and often results in less-than-ideal outcomes. To address the limitations of the current guidelines, we developed and subsequently blindly validated a machine learning algorithm using pretreatment plasma proteomic profiles for personalized treatment decisions. PATIENTS AND METHODS We conducted a multicenter observational trial (ClinicalTrials.gov identifier: NCT04056247 ) of patients undergoing PD-1/PD-L1 inhibitor–based therapy (n = 540) and an additional patient cohort receiving chemotherapy (n = 85) who consented to pretreatment plasma and clinical data collection. Plasma proteome profiling was performed using SomaScan Assay v4.1. RESULTS Our test demonstrates a strong association between model output and clinical benefit (CB) from PD-1/PD-L1 inhibitor–based treatments, evidenced by high concordance between predicted and observed CB ( R 2 = 0.98, P < .001). The test categorizes patients as either PROphet-positive or PROphet-negative and further stratifies patient outcomes beyond PD-L1 expression levels. The test successfully differentiates between PROphet-negative patients exhibiting high tumor PD-L1 levels (≥50%) who have enhanced overall survival when treated with a combination of immunotherapy and chemotherapy compared with immunotherapy alone (hazard ratio [HR], 0.23 [95% CI, 0.1 to 0.51], P = .0003). By contrast, PROphet-positive patients show comparable outcomes when treated with immunotherapy alone or in combination with chemotherapy (HR, 0.78 [95% CI, 0.42 to 1.44], P = .424). CONCLUSION Plasma proteome–based testing of individual patients, in combination with standard PD-L1 testing, distinguishes patient subsets with distinct differences in outcomes from PD-1/PD-L1 inhibitor–based therapies. These data suggest that this approach can improve the precision of first-line treatment for metastatic NSCLC.