In light of the burgeoning successes of cancer immunotherapy, glioblastoma (GBM) remains refractory due to an immunosuppressive microenvironment originating from its molecular heterogeneity. Thus, identifying promising therapeutic targets for treating GBM and discovering methodologies to effectively regulate them is still a tremendous challenge. Here we describe photodynamic protein tyrosine phosphatase 1B (PTP1B) proteolysis mediated by a proteolysis-targeting chimera (PROTAC) nanoassembly. The PTP1B-targeting PROTAC is conjugated with a photosensitizer via a cathepsin B (Cat B)-cleavable peptide, which spontaneously forms nanoassemblies due to intermolecular π-π stacking interactions. In GBM models, PROTAC nanoassemblies significantly accumulate in the tumor region across the disrupted blood-brain barrier (BBB), triggering a burst release of the photosensitizer and active PROTAC by Cat B-mediated enzymatic cleavage. Upon laser irradiation, photodynamic therapy (PDT) synergizes with PROTAC-mediated PTP1B proteolysis to induce potent immunogenic cell death (ICD) in tumor cells. Subsequently, persistent PTP1B degradation by nanoassemblies in Cat B-overexpressed intratumoral T cells downregulates exhaustion markers, reinvigorating their functionality. These sequential processes of photodynamic PTP1B proteolysis ultimately augment T cell-mediated antitumor immunity as well as protective immunity, completely eradicating the primary GBM and preventing its recurrence. Overall, our findings underscore the therapeutic potential of combining PDT with PROTAC activity for GBM immunotherapy.

Purpose: This study evaluated the educational impact of an artificial intelligence (AI)–based decision support system for breast ultrasonography (US) on medical professionals not specialized in breast imaging. Methods: In this multi-case, multi-reader study, educational materials, including American College of Radiology Breast Imaging Reporting and Data System (BI-RADS) descriptors, were provided alongside corresponding AI results during training. The AI system presented results in the form of AIheatmaps, AI scores, and AI-provided BI-RADS assessment categories. Forty-two readers evaluated the test set in three sessions: the first session (S1) occurred before the educational intervention, the second session (S2) followed education without AI assistance, and the third session (S3) took place after education with AI assistance. The area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and overall performance, were compared between the sessions. Results: The mean sensitivity increased from 66.5% (95% confidence interval [CI], 59.2% to 73.7%) to 88.7% (95% CI, 84.1% to 93.3%), with a statistically significant difference (P<0.001), and the AUC non-significantly increased from 0.664 (95% CI, 0.606 to 0.723) to 0.684 (95% CI, 0.620 to 0.748) (P=0.300). Both measures were higher in S2 than in S1. The AI-achieved AUC was comparable to that of the expert reader (0.747 [95% CI, 0.640 to 0.855] vs. 0.803 [95% CI, 0.706 to 0.900], P=0.217). Additionally, with AI assistance, the mean AUC for inexperienced readers was not significantly different from that of the expert reader (0.745 [95% CI, 0.660 to 0.830] vs. 0.803 [95% CI, 0.706 to 0.900], P=0.120). Conclusion The mean AUC and sensitivity improved after incorporating AI into breast US education and interpretation. AI systems with high-level performance for breast US can potentially be used as educational tools in the interpretation of breast US images.

Purpose: This study evaluated the educational impact of an artificial intelligence (AI)–based decision support system for breast ultrasonography (US) on medical professionals not specialized in breast imaging. Methods: In this multi-case, multi-reader study, educational materials, including American College of Radiology Breast Imaging Reporting and Data System (BI-RADS) descriptors, were provided alongside corresponding AI results during training. The AI system presented results in the form of AIheatmaps, AI scores, and AI-provided BI-RADS assessment categories. Forty-two readers evaluated the test set in three sessions: the first session (S1) occurred before the educational intervention, the second session (S2) followed education without AI assistance, and the third session (S3) took place after education with AI assistance. The area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and overall performance, were compared between the sessions. Results: The mean sensitivity increased from 66.5% (95% confidence interval [CI], 59.2% to 73.7%) to 88.7% (95% CI, 84.1% to 93.3%), with a statistically significant difference (P<0.001), and the AUC non-significantly increased from 0.664 (95% CI, 0.606 to 0.723) to 0.684 (95% CI, 0.620 to 0.748) (P=0.300). Both measures were higher in S2 than in S1. The AI-achieved AUC was comparable to that of the expert reader (0.747 [95% CI, 0.640 to 0.855] vs. 0.803 [95% CI, 0.706 to 0.900], P=0.217). Additionally, with AI assistance, the mean AUC for inexperienced readers was not significantly different from that of the expert reader (0.745 [95% CI, 0.660 to 0.830] vs. 0.803 [95% CI, 0.706 to 0.900], P=0.120). Conclusion The mean AUC and sensitivity improved after incorporating AI into breast US education and interpretation. AI systems with high-level performance for breast US can potentially be used as educational tools in the interpretation of breast US images.

Background: This study analyzed the status of community-based practice in public healthcare institutions in Korean medical schools and identified related needs. Methods: We conducted an online cross-sectional survey in which 32 of 40 medical schools (80.0%) participated between March and April 2023. We developed questionnaire items aimed at ascertaining the status and perceptions of community-based practice and analyzed the response data using frequency analysis, the Mann-Whitney U test, and content analysis with word clouds. Results: Of the 32 medical schools analyzed, 23 (71.9%) offered practical courses, and of those, 12 (52.2%) implemented practice lessons within courses. Among 20 schools, 18 (90.0%) required students to complete practical courses and over 50% offered these courses in the third and fourth years of the clerkship phase. Perceptions of community practice showed no significant differences based on whether courses were offered. Many schools have proposed that practice should be a continuous curricular element from the premedical to medical years. The primary challenges facing community-based practice were identified as faculty development, collaboration, and compensation of practice institutions. The following words were extracted from the respondents’ comments: practice, community, institution, student, education, faculty, university, and public. Conclusion This study identified the limitations of community-based education provided by Korean medical schools and we report findings that highlight areas of improvement. Notable among these is the need to continuously incorporate community-based practice into medical education while engaging in discussions and conducting research toward developing a comprehensive and systematic curriculum.

Purpose: This study evaluated the educational impact of an artificial intelligence (AI)–based decision support system for breast ultrasonography (US) on medical professionals not specialized in breast imaging. Methods: In this multi-case, multi-reader study, educational materials, including American College of Radiology Breast Imaging Reporting and Data System (BI-RADS) descriptors, were provided alongside corresponding AI results during training. The AI system presented results in the form of AIheatmaps, AI scores, and AI-provided BI-RADS assessment categories. Forty-two readers evaluated the test set in three sessions: the first session (S1) occurred before the educational intervention, the second session (S2) followed education without AI assistance, and the third session (S3) took place after education with AI assistance. The area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and overall performance, were compared between the sessions. Results: The mean sensitivity increased from 66.5% (95% confidence interval [CI], 59.2% to 73.7%) to 88.7% (95% CI, 84.1% to 93.3%), with a statistically significant difference (P<0.001), and the AUC non-significantly increased from 0.664 (95% CI, 0.606 to 0.723) to 0.684 (95% CI, 0.620 to 0.748) (P=0.300). Both measures were higher in S2 than in S1. The AI-achieved AUC was comparable to that of the expert reader (0.747 [95% CI, 0.640 to 0.855] vs. 0.803 [95% CI, 0.706 to 0.900], P=0.217). Additionally, with AI assistance, the mean AUC for inexperienced readers was not significantly different from that of the expert reader (0.745 [95% CI, 0.660 to 0.830] vs. 0.803 [95% CI, 0.706 to 0.900], P=0.120). Conclusion The mean AUC and sensitivity improved after incorporating AI into breast US education and interpretation. AI systems with high-level performance for breast US can potentially be used as educational tools in the interpretation of breast US images.