Ahn JS, et al. J Breast Cancer. 2023 Oct;26:e45. https://doi.org/10.4048/jbc.2023.26.e45

Lee JH, et al. Korean J Radiol. 2022 May;23(5):505-516. https://doi.org/10.3348/kjr.2021.0476

The relationship between tumor microenvironments (TMEs) of regional lymph node metastases (LNMs) and primary tumors in head and neck squamous cell carcinoma (HNSCC) remains unclear. This study compared tumor-infiltrating lymphocytes (TILs) and the immune phenotype (IP), characterized by spatial TIL distribution, between primary tumors and LNMs. Twenty-one HNSCC patients with regional LNM who received immune checkpoint inhibitors (ICIs) were included. A paired comparative analysis of TIL densities and IP between primary tumors and LNMs revealed no significant difference or correlation between TIL densities in primary tumors and LNMs. Their IPs were discordant in 12 patients (57.1%). Patients with high intratumoral TIL exhibited longer progression-free survival (PFS) than those with low intratumoral TIL in both primary tumors (median, 5.2 vs. 1.3 months, p = 0.003) and LNMs (median, 30.2 vs. 1.3 months, p = 0.012). Patients with inflamed IP exhibited longer PFS than those with non-inflamed IP in both primary tumors (median, 4.5 vs. 1.3 months, p = 0.043) and LNMs (median, 4.1 vs. 1.3 months, p = 0.037). Given the lack of correlation in TIL densities, the discrepancies in IP, and the predictive value of both TMEs, evaluating the TMEs of both primary tumors and LNMs may be beneficial for the precise use of ICIs in HNSCC. There was a significant discordance between the TME of primary tumors and LNMs, with implications in survival outcomes. Therefore, evaluating the TME of both the primary tumor and LNM could be beneficial for the precise use of ICIs in HNSCC.

The ability to accurately predict the prognosis and intervention requirements for treating highly infectious diseases, such as COVID-19, can greatly support the effective management of patients, especially in resource-limited settings. The aim of the study is to develop and validate a multimodal artificial intelligence (AI) system using clinical findings, laboratory data and AI-interpreted features of chest X-rays (CXRs), and to predict the prognosis and the required interventions for patients diagnosed with COVID-19, using multi-center data. In total, 2282 real-time reverse transcriptase polymerase chain reaction-confirmed COVID-19 patients’ initial clinical findings, laboratory data and CXRs were retrospectively collected from 13 medical centers in South Korea, between January 2020 and June 2021. The prognostic outcomes collected included intensive care unit (ICU) admission and in-hospital mortality. Intervention outcomes included the use of oxygen (O₂) supplementation, mechanical ventilation and extracorporeal membrane oxygenation (ECMO). A deep learning algorithm detecting 10 common CXR abnormalities (DLAD-10) was used to infer the initial CXR taken. A random forest model with a quantile classifier was used to predict the prognostic and intervention outcomes, using multimodal data. The area under the receiver operating curve (AUROC) values for the single-modal model, using clinical findings, laboratory data and the outputs from DLAD-10, were 0.742 (95% confidence interval [CI], 0.696–0.788), 0.794 (0.745–0.843) and 0.770 (0.724–0.815), respectively. The AUROC of the combined model, using clinical findings, laboratory data and DLAD-10 outputs, was significantly higher at 0.854 (0.820–0.889) than that of all other models (p < 0.001, using DeLong’s test). In the order of importance, age, dyspnea, consolidation and fever were significant clinical variables for prediction. The most predictive DLAD-10 output was consolidation. We have shown that a multimodal AI model can improve the performance of predicting both the prognosis and intervention in COVID-19 patients, and this could assist in effective treatment and subsequent resource management. Further, image feature extraction using an established AI engine with well-defined clinical outputs, and combining them with different modes of clinical data, could be a useful way of creating an understandable multimodal prediction model.

PURPOSE: Immune checkpoint inhibitors (ICIs) are now first-line therapy for most patients with recurrent/metastatic head and neck squamous cell carcinoma (R/M HNSCC), and cetuximab is most often used as subsequent therapy. However, data describing cetuximab efficacy in the post-ICI setting are limited. METHODS: We performed a single-institution retrospective analysis of patients with R/M HNSCC treated with cetuximab, either as monotherapy or in combination with chemotherapy, after receiving an ICI. We extracted objective response rate (ORR), duration of treatment (DOT), and overall survival (OS) and compared them on the basis of patient characteristics. Multivariable models assessed associations between patient and tumor characteristics and outcomes. RESULTS: We identified 70 patients treated with cetuximab after an ICI. The mean age was 67.6 years, with 60% having virus-associated HNSCC. Overall, the ORR was 21.4%, the median DOT was 1.9 months, and the median OS was 6.3 months. Patients receiving cetuximab with chemotherapy had a higher ORR (27.7% v 8.7%) and longer median DOT but similar OS compared with monotherapy. Virus-independent HNSCC had higher ORR (28.6% v 10.7%), longer DOT (3.3 v 1.2 months; hazard ratio [HR], 0.47 [95% CI, 0.25 to 0.90]), and longer OS (8.1 v 4.6 months; HR, 0.40 [95% CI, 0.19 to 0.83]). In multivariable models, virus-independent disease and negative smoking history were associated with improved OS. Concurrent chemotherapy, age, and sex were not associated with differences in OS. When assessing genomic data, TP53 mutations were associated with improved DOT (HR, 0.33 [95% CI, 0.15 to 0.70]) and OS (HR, 0.38 [95% CI, 0.17 to 0.86]). CONCLUSION: Cetuximab-based therapy shows limited efficacy in R/M HNSCC post-ICI, although outcomes were better in virus-independent HNSCC and nonsmokers. The findings may improve prognostication and patient selection for cetuximab after ICI in R/M HNSCC.

Introduction A chest X-ray (CXR) is the most common imaging investigation performed worldwide. Advances in machine learning and computer vision technologies have led to the development of several artificial intelligence (AI) tools to detect abnormalities on CXRs, which may expand diagnostic support to a wider field of health professionals. There is a paucity of evidence on the impact of AI algorithms in assisting healthcare professionals (other than radiologists) who regularly review CXR images in their daily practice. Aims To assess the utility of an AI-based CXR interpretation tool in assisting the diagnostic accuracy, speed and confidence of a varied group of healthcare professionals. Methods and analysis The study will be conducted using 500 retrospectively collected inpatient and emergency department CXRs from two UK hospital trusts. Two fellowship-trained thoracic radiologists with at least 5 years of experience will independently review all studies to establish the ground truth reference standard with arbitration from a third senior radiologist in case of disagreement. The Lunit INSIGHT CXR tool (Seoul, Republic of Korea) will be applied and compared against the reference standard. Area under the receiver operating characteristic curve (AUROC) will be calculated for 10 abnormal findings: pulmonary nodules/mass, consolidation, pneumothorax, atelectasis, calcification, cardiomegaly, fibrosis, mediastinal widening, pleural effusion and pneumoperitoneum. Performance testing will be carried out with readers from various clinical professional groups with and without the assistance of Lunit INSIGHT CXR to evaluate the utility of the algorithm in improving reader accuracy (sensitivity, specificity, AUROC), confidence and speed (paired sample t-test). The study is currently ongoing with a planned end date of 31 December 2024. Ethics and dissemination The study has been approved by the UK Healthcare Research Authority. The use of anonymised retrospective CXRs has been authorised by Oxford University Hospital’s information governance teams. The results will be presented at relevant conferences and published in a peer-reviewed journal. Trial registration number Protocol ID 310995-B (awaiting approval), ClinicalTrials.gov