MedKPL: A heterogeneous knowledge enhanced prompt learning framework for transferable diagnosis.

Artificial Intelligence (AI) based diagnosis systems have emerged as powerful tools to reform traditional medical care. Each clinician now wants to have his own intelligent diagnostic partner to expand the range of services he can provide. However, the implementation of intelligent decision support systems based on clinical note has been hindered by the lack of extensibility of end-to-end AI diagnosis algorithms. When reading a clinical note, expert clinicians make inferences with relevant medical knowledge, which serve as prompts for making accurate diagnoses. Therefore, external medical knowledge is commonly employed as an augmentation for medical text classification tasks. Existing methods, however, cannot integrate knowledge from various knowledge sources as prompts nor can fully utilize explicit and implicit knowledge. To address these issues, we propose a Medical Knowledge-enhanced Prompt Learning (MedKPL) diagnostic framework for transferable clinical note classification. Firstly, to overcome the heterogeneity of knowledge sources, such as knowledge graphs or medical QA databases, MedKPL uniform the knowledge relevant to the disease into text sequences of fixed format. Then, MedKPL integrates medical knowledge into the prompt designed for context representation. Therefore, MedKPL can integrate knowledge into the models to enhance diagnostic performance and effectively transfer to new diseases by using relevant disease knowledge. The results of our experiments on two medical datasets demonstrate that our method yields superior medical text classification results and performs better in cross-departmental transfer tasks under few-shot or even zero-shot settings. These findings demonstrate that our MedKPL framework has the potential to improve the interpretability and transferability of current diagnostic systems.

MALAT1 promotes gastric adenocarcinoma through the MALAT1/miR-181a-5p/AKT3 axis.

Gastric adenocarcinoma, which originates from the gastric mucosal epithelium, has the highest incidence among various malignant tumours in China. As a crucial long non-coding RNA, metastasis-associated lung adenocarcinoma transcript 1 (MALAT1) has been suggested to play an important role in many tumours. Here, we aimed to investigate the role and underlying mechanism of MALAT1 in gastric adenocarcinoma. Quantitative reverse transcription polymerase chain reaction was applied to determine the expression levels of MALAT1 in serum and cell lines. A CCK-8 assay and a clonogenic survival assay were used to examine cell proliferation and apoptosis. The protein level of RAC-γ serine/threonine-specific protein kinase (AKT3) was determined by western blot. Our results showed that MALAT1 was highly expressed in the serum of patients with gastric adenocarcinoma and in cell lines. Downregulating MALAT1 inhibited proliferation and promoted apoptosis of MGC-803 cells. In addition, MALAT1 directly targeted and decreased the expression of miR-181a-5p, which in turn upregulated the expression of AKT3. Further, overexpressing miR-181a-5p or directly inhibiting the AKT pathway with the inhibitor ipatasertib exhibited similar effects to MALAT1 knockdown. Our research proposes a novel mechanism where the role of MALAT1 is dependent on the MALAT1/miR-181a-5p/AKT3 axis. MALAT1 competes with AKT3 for miR-181a-5p binding, thereby upregulating the AKT3 protein level and ultimately promoting the growth of gastric adenocarcinoma.