Lung cancer still ranks first among malignant tumors in the world and China. Although surgery， radiotherapy， chemotherapy， and other treatments can delay patients' lives， thorny problems remain to be solved， such as adverse reactions after intervention， patient resistance to treatment， and the economic burden of treatment. Traditional Chinese medicine （TCM） featuring a holistic view advocates macro interventions throughout the entire disease cycle， which has the advantages of reducing toxicity， improving efficiency， and enhancing patients' quality of life. The theory of ''sensation and response'' was first recorded in the book of I-Ching. This is the natural law of mutual induction， influence， and interaction among all things in nature. According to the theory of ''Qi monism'' and the proposal of regulating Qi movement and removing toxin by Professor Hua Baojin， we re-examine lung cancer from the primitive thinking in TCM and explain the relevance of Qi movement changes to the occurrence， progression， and treatment of lung cancer. The core pathogeneses of lung cancer are the deficiency of healthy Qi and invasion of deficiency pathogen resulting in the formation of cancer and the internal generation of cancer toxin leading to intermediate dysfunction. Six excesses and Yin pathogen invade and gradually accumulate in the lung and spleen， leading to the generation of cancer toxin， which eventually evolve into lung cancer. The treatment can be based on the theories of five elements and visceral manifestation from three aspects. First， on the basis of syndrome differentiation， medicinal materials of different flavors can be used. Specifically， pungent medicinal materials can be used for dredging and sweet medicinal materials can be used for tonifying. Second， medicinal materials with similar morphology or origin to that in the human body can be used for treating the diseases in corresponding sites. Finally， corrigent medicinal materials can be combined for two-way regulation. These measures can be applied in lung cancer treatment to optimize the prevention and treatment strategies and provide new research directions for TCM diagnosis and treatment of tumors.

ObjectiveThis study aims to develop and validate a novel multimodal predictive model， termed criss-cross network（CCNet）-directed graph neural network（DGNN）（CGN）， for accurate assessment of pulmonary nodule progression in high-risk individuals for lung cancer， by integrating longitudinal chest computed tomography（CT） imaging with both traditional Chinese and western clinical evaluation data. MethodsA cohort of 4 432 patients with pulmonary nodules was retrospectively analyzed. A twin CCNet was employed to extract spatiotemporal representations from paired sequential CT scans. Structured clinical assessment and imaging-derived features were encoded via a multilayer perceptron， and a similarity-based alignment strategy was adopted to harmonize multimodal imaging features across temporal dimensions. Subsequently， a DGNN was constructed to integrate heterogeneous features， where nodes represented modality-specific embeddings and edges denoted inter-modal information flow. Finally， model optimization was performed using a joint loss function combining cross-entropy and cosine similarity loss， facilitating robust classification of nodule progression status. ResultsThe proposed CGN model demonstrated superior predictive performance on the held-out test set， achieving an area under the receiver operating characteristic curve（AUC） of 0.830， accuracy of 0.843， sensitivity of 0.657， specificity of 0.712， Cohen's Kappa of 0.417， and F₁ score of 0.544. Compared with unimodal baselines， the CGN model yielded a 36%-48% relative improvement in AUC. Ablation studies revealed a 2%-22% increase in AUC when compared to simplified architectures lacking key components， substantiating the efficacy of the proposed multimodal fusion strategy and modular design. Incorporation of traditional Chinese medicine （TCM）-specific symptomatology led to an additional 5% improvement in AUC， underscoring the complementary value of integrating TCM and western clinical data. Through gradient-weighted activation mapping visualization analysis， it was found that the model's attention predominantly focused on nodule regions and effectively captured dynamic associations between clinical data and imaging-derived features. ConclusionThe CGN model， by synergistically combining cross-attention encoding with directed graph-based feature integration， enables effective alignment and fusion of heterogeneous multimodal data. The incorporation of both TCM and western clinical information facilitates complementary feature enrichment， thereby enhancing predictive accuracy for pulmonary nodule progression. This approach holds significant potential for supporting intelligent risk stratification and personalized surveillance strategies in lung cancer prevention.