ObjectiveThe essence of syndrome manifestation recognition in traditional Chinese medicine (TCM) is to infer the body’s latent pathogenesis state from clinical observational information, rather than to perform simple label matching. However, previous studies have largely modeled this task as syndrome pattern classification within a fixed label space, which does not adequately reflect the cognition process of TCM syndrome differentiation centered on pathogenesis reasoning, and is also insufficient to capture the openness, semantic variability, and cross-disease reusability of syndrome manifestation expression. This study aimed to investigate whether introducing pathogenesis reasoning chain-of-thought (PR-CoT) supervision into large language models (LLMs) could improve the quality and cognitive consistency of syndrome manifestation recognition and support cross-disease transfer. MethodsSyndrome manifestation recognition was formulated as a conditional generation task under the framework of clinical observational information (X)→pathogenesis structure (Z)→syndrome pattern output (Y), where Z serves as an explicit intermediate structural variable linking the clinical evidence and syndrome judgment. Within this framework, a PR-CoT-supervised dataset for syndrome manifestation recognition was constructed based on medical case records of spleen-stomach disorders. After preprocessing, information extraction, manual proofreading, and data cleaning, the dataset comprised 4 800 training cases, 400 development cases, and 400 test cases. Each sample was annotated with a structured PR-CoT consisting of three progressive levels: clinical information summarization, comprehensive pathogenesis analysis, and syndrome pattern output. Supervised fine-tuning was conducted on open-source LLMs, with an end-to-end model serving as the baseline. Qwen3-32B was used as the primary experimental model, and Qwen3-14B as the scale comparison model. A progressive multidimensional evaluation framework was further established, comprising a structural parsing level, a semantic similarity level, and an expert blind review level. At the structural parsing level, syndrome pattern expressions were decomposed into structural elements and evaluated using Precision, Recall, F1 score, and Jaccard similarity. At the semantic similarity level, independent LLMs scored the theoretical proximity between predicted and reference syndrome patterns. At the expert blind review level, three TCM experts independently evaluated model outputs on two dimensions: syndrome differentiation consistency and terminology standardization of syndrome patterns. In addition, zero-shot cross-disease transfer evaluation was conducted on gynecological and heart-system disorder test sets. ResultsAt the structural parsing level, PR-CoT supervision did not lead to a stable improvement in the element-wise overlap of syndrome pattern structural components. Compared with the corresponding baselines, neither Qwen3-32B nor Qwen3-14B showed consistent advantages in structural matching metrics after the introduction of PR-CoT supervision. In contrast, at the semantic similarity level, PR-CoT supervision produced stable positive gains across different model scales and evaluation systems. The average semantic score of Qwen3-32B increased from 6.425 8 in the baseline model to 6.585 0 after PR-CoT supervision, and that of Qwen3-14B increased from 5.870 0 to 5.964 2. At the expert blind review level, the overall score of Qwen3-32B (PR-CoT) was 7.026 0±0.107 7, higher than 6.416 3±0.288 9 for its baseline. In zero-shot cross-disease testing, the PR-CoT model still showed advantages in semantic evaluation and expert evaluation on both gynecological and heart-system disorder test sets, indicating a certain degree of transferability. ConclusionThe benefits of PR-CoT supervision are mainly reflected in TCM semantic consistency and clinical plausibility, rather than in improved hard matching of structural elements. These findings support understanding syndrome manifestation recognition as a process of generating and expressing latent pathogenesis structures, rather than as a classification task within a traditional fixed label space. By introducing pathogenesis reasoning as an explicit intermediate structure into the modeling process and combining it with a progressive multidimensional evaluation framework, this study provides a methodological pathway for intelligent TCM syndrome differentiation that integrates theoretical alignment, interpretability, and multi-level evaluation.

ObjectiveThe essence of syndrome manifestation recognition in traditional Chinese medicine (TCM) is to infer the body’s latent pathogenesis state from clinical observational information, rather than to perform simple label matching. However, previous studies have largely modeled this task as syndrome pattern classification within a fixed label space, which does not adequately reflect the cognition process of TCM syndrome differentiation centered on pathogenesis reasoning, and is also insufficient to capture the openness, semantic variability, and cross-disease reusability of syndrome manifestation expression. This study aimed to investigate whether introducing pathogenesis reasoning chain-of-thought (PR-CoT) supervision into large language models (LLMs) could improve the quality and cognitive consistency of syndrome manifestation recognition and support cross-disease transfer. MethodsSyndrome manifestation recognition was formulated as a conditional generation task under the framework of clinical observational information (X)→pathogenesis structure (Z)→syndrome pattern output (Y), where Z serves as an explicit intermediate structural variable linking the clinical evidence and syndrome judgment. Within this framework, a PR-CoT-supervised dataset for syndrome manifestation recognition was constructed based on medical case records of spleen-stomach disorders. After preprocessing, information extraction, manual proofreading, and data cleaning, the dataset comprised 4 800 training cases, 400 development cases, and 400 test cases. Each sample was annotated with a structured PR-CoT consisting of three progressive levels: clinical information summarization, comprehensive pathogenesis analysis, and syndrome pattern output. Supervised fine-tuning was conducted on open-source LLMs, with an end-to-end model serving as the baseline. Qwen3-32B was used as the primary experimental model, and Qwen3-14B as the scale comparison model. A progressive multidimensional evaluation framework was further established, comprising a structural parsing level, a semantic similarity level, and an expert blind review level. At the structural parsing level, syndrome pattern expressions were decomposed into structural elements and evaluated using Precision, Recall, F1 score, and Jaccard similarity. At the semantic similarity level, independent LLMs scored the theoretical proximity between predicted and reference syndrome patterns. At the expert blind review level, three TCM experts independently evaluated model outputs on two dimensions: syndrome differentiation consistency and terminology standardization of syndrome patterns. In addition, zero-shot cross-disease transfer evaluation was conducted on gynecological and heart-system disorder test sets. ResultsAt the structural parsing level, PR-CoT supervision did not lead to a stable improvement in the element-wise overlap of syndrome pattern structural components. Compared with the corresponding baselines, neither Qwen3-32B nor Qwen3-14B showed consistent advantages in structural matching metrics after the introduction of PR-CoT supervision. In contrast, at the semantic similarity level, PR-CoT supervision produced stable positive gains across different model scales and evaluation systems. The average semantic score of Qwen3-32B increased from 6.425 8 in the baseline model to 6.585 0 after PR-CoT supervision, and that of Qwen3-14B increased from 5.870 0 to 5.964 2. At the expert blind review level, the overall score of Qwen3-32B (PR-CoT) was 7.026 0±0.107 7, higher than 6.416 3±0.288 9 for its baseline. In zero-shot cross-disease testing, the PR-CoT model still showed advantages in semantic evaluation and expert evaluation on both gynecological and heart-system disorder test sets, indicating a certain degree of transferability. ConclusionThe benefits of PR-CoT supervision are mainly reflected in TCM semantic consistency and clinical plausibility, rather than in improved hard matching of structural elements. These findings support understanding syndrome manifestation recognition as a process of generating and expressing latent pathogenesis structures, rather than as a classification task within a traditional fixed label space. By introducing pathogenesis reasoning as an explicit intermediate structure into the modeling process and combining it with a progressive multidimensional evaluation framework, this study provides a methodological pathway for intelligent TCM syndrome differentiation that integrates theoretical alignment, interpretability, and multi-level evaluation.

Objective: This study aims to overcome challenges in lumbar spine imaging, particularly lumbar spinal stenosis, by developing an automated segmentation model using advanced techniques. Traditional manual measurement and lesion detection methods are limited by subjectivity and inefficiency. The objective is to create an accurate and automated segmentation model that identifies anatomical structures in lumbar spine magnetic resonance imaging scans. Methods: Leveraging a dataset of 539 lumbar spinal stenosis patients, the study utilizes the residual U-Net for semantic segmentation in sagittal and axial lumbar spine magnetic resonance images. The model, trained to recognize specific tissue categories, employs a geometry algorithm for anatomical structure quantification. Validation metrics, like Intersection over Union (IOU) and Dice coefficients, validate the residual U-Net’s segmentation accuracy. A novel rotation matrix approach is introduced for detecting bulging discs, assessing dural sac compression, and measuring yellow ligament thickness. Results: The residual U-Net achieves high precision in segmenting lumbar spine structures, with mean IOU values ranging from 0.82 to 0.93 across various tissue categories and views. The automated quantification system provides measurements for intervertebral disc dimensions, dural sac diameter, yellow ligament thickness, and disc hydration. Consistency between training and testing datasets assures the robustness of automated measurements. Conclusion Automated lumbar spine segmentation with residual U-Net and deep learning exhibits high precision in identifying anatomical structures, facilitating efficient quantification in lumbar spinal stenosis cases. The introduction of a rotation matrix enhances lesion detection, promising improved diagnostic accuracy, and supporting treatment decisions for lumbar spinal stenosis patients.

Objective: This study aims to overcome challenges in lumbar spine imaging, particularly lumbar spinal stenosis, by developing an automated segmentation model using advanced techniques. Traditional manual measurement and lesion detection methods are limited by subjectivity and inefficiency. The objective is to create an accurate and automated segmentation model that identifies anatomical structures in lumbar spine magnetic resonance imaging scans. Methods: Leveraging a dataset of 539 lumbar spinal stenosis patients, the study utilizes the residual U-Net for semantic segmentation in sagittal and axial lumbar spine magnetic resonance images. The model, trained to recognize specific tissue categories, employs a geometry algorithm for anatomical structure quantification. Validation metrics, like Intersection over Union (IOU) and Dice coefficients, validate the residual U-Net’s segmentation accuracy. A novel rotation matrix approach is introduced for detecting bulging discs, assessing dural sac compression, and measuring yellow ligament thickness. Results: The residual U-Net achieves high precision in segmenting lumbar spine structures, with mean IOU values ranging from 0.82 to 0.93 across various tissue categories and views. The automated quantification system provides measurements for intervertebral disc dimensions, dural sac diameter, yellow ligament thickness, and disc hydration. Consistency between training and testing datasets assures the robustness of automated measurements. Conclusion Automated lumbar spine segmentation with residual U-Net and deep learning exhibits high precision in identifying anatomical structures, facilitating efficient quantification in lumbar spinal stenosis cases. The introduction of a rotation matrix enhances lesion detection, promising improved diagnostic accuracy, and supporting treatment decisions for lumbar spinal stenosis patients.

Objectives: This study aimed to present the Asia-Pacific consensus on long-term and sequential therapy for osteoporosis, offering evidence-based recommendations for the effective management of this chronic condition.The primary focus is on achieving optimal fracture prevention through a comprehensive, individualized approach. Methods: A panel of experts convened to develop consensus statements by synthesizing the current literature and leveraging clinical expertise. The review encompassed long-term anti-osteoporosis medication goals, first-line treatments for individuals at very high fracture risk, and the strategic integration of anabolic and anti resorptive agents in sequential therapy approaches. Results: The panelists reached a consensus on 12 statements. Key recommendations included advocating for anabolic agents as the first-line treatment for individuals at very high fracture risk and transitioning to anti resorptive agents following the completion of anabolic therapy. Anabolic therapy remains an option for in dividuals experiencing new fractures or persistent high fracture risk despite antiresorptive treatment. In cases of inadequate response, the consensus recommended considering a switch to more potent medications. The consensus also addressed the management of medication-related complications, proposing alternatives instead of discontinuation of treatment. Conclusions This consensus provides a comprehensive, cost-effective strategy for fracture prevention with an emphasis on shared decision-making and the incorporation of country-specific case management systems, such as fracture liaison services. It serves as a valuable guide for healthcare professionals in the Asia-Pacific region, contributing to the ongoing evolution of osteoporosis management.

Objective: Lynch syndrome (LS) is a hereditary cancer predisposition syndrome with a significantly increased risk of colorectal and endometrial cancers. Current standard practice involves universal screening for LS in patients with newly diagnosed colorectal or endometrial cancer using a multi-step screening protocol (MSP). However, MSP may not always accurately identify LS cases. To address this limitation, we compared the diagnostic performance of immediate germline sequencing (IGS) with MSP in a high-risk group. Methods: A total of 31 Taiwanese women with synchronous or metachronous endometrial and colorectal malignancies underwent MSP which included immunohistochemical staining of DNA mismatch repair (MMR) proteins, MLH1 promoter hypermethylation analysis, and germline sequencing to identify pathogenic variants. All patients who were excluded during MSP received germline sequencing for MMR genes to simulate IGS for the detection of LS. Results: Our findings indicate that IGS surpassed MSP in terms of diagnostic yield (29.0% vs.19.4%, respectively) and sensitivity (90% vs. 60%, respectively). Specifically, IGS successfully identified nine LS cases, which is 50% more than the number detected through MSP.Additionally, germline methylation analysis revealed one more LS case with constitutional MLH1 promoter hypermethylation, bringing the total LS cases to ten (32.3%). Intriguingly, we observed no significant differences in clinical characteristics or overall survival between patients with and without LS in our cohort. Conclusion Our study suggests that IGS may potentially offer a more effective approach compared to MSP in identifying LS among high-risk patients. This advantage is evident when patients have been pre-selected utilizing specific clinical criteria.

Objective: Lynch syndrome (LS) is a hereditary cancer predisposition syndrome with a significantly increased risk of colorectal and endometrial cancers. Current standard practice involves universal screening for LS in patients with newly diagnosed colorectal or endometrial cancer using a multi-step screening protocol (MSP). However, MSP may not always accurately identify LS cases. To address this limitation, we compared the diagnostic performance of immediate germline sequencing (IGS) with MSP in a high-risk group. Methods: A total of 31 Taiwanese women with synchronous or metachronous endometrial and colorectal malignancies underwent MSP which included immunohistochemical staining of DNA mismatch repair (MMR) proteins, MLH1 promoter hypermethylation analysis, and germline sequencing to identify pathogenic variants. All patients who were excluded during MSP received germline sequencing for MMR genes to simulate IGS for the detection of LS. Results: Our findings indicate that IGS surpassed MSP in terms of diagnostic yield (29.0% vs.19.4%, respectively) and sensitivity (90% vs. 60%, respectively). Specifically, IGS successfully identified nine LS cases, which is 50% more than the number detected through MSP.Additionally, germline methylation analysis revealed one more LS case with constitutional MLH1 promoter hypermethylation, bringing the total LS cases to ten (32.3%). Intriguingly, we observed no significant differences in clinical characteristics or overall survival between patients with and without LS in our cohort. Conclusion Our study suggests that IGS may potentially offer a more effective approach compared to MSP in identifying LS among high-risk patients. This advantage is evident when patients have been pre-selected utilizing specific clinical criteria.

Objective: Lynch syndrome (LS) is a hereditary cancer predisposition syndrome with a significantly increased risk of colorectal and endometrial cancers. Current standard practice involves universal screening for LS in patients with newly diagnosed colorectal or endometrial cancer using a multi-step screening protocol (MSP). However, MSP may not always accurately identify LS cases. To address this limitation, we compared the diagnostic performance of immediate germline sequencing (IGS) with MSP in a high-risk group. Methods: A total of 31 Taiwanese women with synchronous or metachronous endometrial and colorectal malignancies underwent MSP which included immunohistochemical staining of DNA mismatch repair (MMR) proteins, MLH1 promoter hypermethylation analysis, and germline sequencing to identify pathogenic variants. All patients who were excluded during MSP received germline sequencing for MMR genes to simulate IGS for the detection of LS. Results: Our findings indicate that IGS surpassed MSP in terms of diagnostic yield (29.0% vs.19.4%, respectively) and sensitivity (90% vs. 60%, respectively). Specifically, IGS successfully identified nine LS cases, which is 50% more than the number detected through MSP.Additionally, germline methylation analysis revealed one more LS case with constitutional MLH1 promoter hypermethylation, bringing the total LS cases to ten (32.3%). Intriguingly, we observed no significant differences in clinical characteristics or overall survival between patients with and without LS in our cohort. Conclusion Our study suggests that IGS may potentially offer a more effective approach compared to MSP in identifying LS among high-risk patients. This advantage is evident when patients have been pre-selected utilizing specific clinical criteria.

Objective: This study aims to overcome challenges in lumbar spine imaging, particularly lumbar spinal stenosis, by developing an automated segmentation model using advanced techniques. Traditional manual measurement and lesion detection methods are limited by subjectivity and inefficiency. The objective is to create an accurate and automated segmentation model that identifies anatomical structures in lumbar spine magnetic resonance imaging scans. Methods: Leveraging a dataset of 539 lumbar spinal stenosis patients, the study utilizes the residual U-Net for semantic segmentation in sagittal and axial lumbar spine magnetic resonance images. The model, trained to recognize specific tissue categories, employs a geometry algorithm for anatomical structure quantification. Validation metrics, like Intersection over Union (IOU) and Dice coefficients, validate the residual U-Net’s segmentation accuracy. A novel rotation matrix approach is introduced for detecting bulging discs, assessing dural sac compression, and measuring yellow ligament thickness. Results: The residual U-Net achieves high precision in segmenting lumbar spine structures, with mean IOU values ranging from 0.82 to 0.93 across various tissue categories and views. The automated quantification system provides measurements for intervertebral disc dimensions, dural sac diameter, yellow ligament thickness, and disc hydration. Consistency between training and testing datasets assures the robustness of automated measurements. Conclusion Automated lumbar spine segmentation with residual U-Net and deep learning exhibits high precision in identifying anatomical structures, facilitating efficient quantification in lumbar spinal stenosis cases. The introduction of a rotation matrix enhances lesion detection, promising improved diagnostic accuracy, and supporting treatment decisions for lumbar spinal stenosis patients.

Objective: This study aims to overcome challenges in lumbar spine imaging, particularly lumbar spinal stenosis, by developing an automated segmentation model using advanced techniques. Traditional manual measurement and lesion detection methods are limited by subjectivity and inefficiency. The objective is to create an accurate and automated segmentation model that identifies anatomical structures in lumbar spine magnetic resonance imaging scans. Methods: Leveraging a dataset of 539 lumbar spinal stenosis patients, the study utilizes the residual U-Net for semantic segmentation in sagittal and axial lumbar spine magnetic resonance images. The model, trained to recognize specific tissue categories, employs a geometry algorithm for anatomical structure quantification. Validation metrics, like Intersection over Union (IOU) and Dice coefficients, validate the residual U-Net’s segmentation accuracy. A novel rotation matrix approach is introduced for detecting bulging discs, assessing dural sac compression, and measuring yellow ligament thickness. Results: The residual U-Net achieves high precision in segmenting lumbar spine structures, with mean IOU values ranging from 0.82 to 0.93 across various tissue categories and views. The automated quantification system provides measurements for intervertebral disc dimensions, dural sac diameter, yellow ligament thickness, and disc hydration. Consistency between training and testing datasets assures the robustness of automated measurements. Conclusion Automated lumbar spine segmentation with residual U-Net and deep learning exhibits high precision in identifying anatomical structures, facilitating efficient quantification in lumbar spinal stenosis cases. The introduction of a rotation matrix enhances lesion detection, promising improved diagnostic accuracy, and supporting treatment decisions for lumbar spinal stenosis patients.