Development and validation of a deep learning model to screen hypokalemia from electrocardiogram in emergency patients.

BACKGROUND: A deep learning model (DLM) that enables non-invasive hypokalemia screening from an electrocardiogram (ECG) may improve the detection of this life-threatening condition. This study aimed to develop and evaluate the performance of a DLM for the detection of hypokalemia from the ECGs of emergency patients. METHODS: We used a total of 9908 ECG data from emergency patients who were admitted at the Second Affiliated Hospital of Nanchang University, Jiangxi, China, from September 2017 to October 2020. The DLM was trained using 12 ECG leads (lead I, II, III, aVR, aVL, aVF, and V1-6) to detect patients with serum potassium concentrations <3.5 mmol/L and was validated using retrospective data from the Jiangling branch of the Second Affiliated Hospital of Nanchang University. The blood draw was completed within 10 min before and after the ECG examination, and there was no new or ongoing infusion during this period. RESULTS: We used 6904 ECGs and 1726 ECGs as development and internal validation data sets, respectively. In addition, 1278 ECGs from the Jiangling branch of the Second Affiliated Hospital of Nanchang University were used as external validation data sets. Using 12 ECG leads (leads I, II, III, aVR, aVL, aVF, and V1-6), the area under the receiver operating characteristic curve (AUC) of the DLM was 0.80 (95% confidence interval [CI]: 0.77-0.82) for the internal validation data set. Using an optimal operating point yielded a sensitivity of 71.4% and a specificity of 77.1%. Using the same 12 ECG leads, the external validation data set resulted in an AUC for the DLM of 0.77 (95% CI: 0.75-0.79). Using an optimal operating point yielded a sensitivity of 70.0% and a specificity of 69.1%. CONCLUSIONS: In this study, using 12 ECG leads, a DLM detected hypokalemia in emergency patients with an AUC of 0.77 to 0.80. Artificial intelligence could be used to analyze an ECG to quickly screen for hypokalemia.

[The effect of breast cancer specific gene 1 in the prognosis of breast cancer].

OBJECTIVE: To detect breast cancer specific gene 1 (BCSG1) expression in different breast tissue, analysis its correlation with clinical parameters and evaluate the prognosis of breast cancer. METHODS: The expression of BCSG1 was detected by reverse transcription-polymerase chain reaction (RT-PCR) in surgical specimens from 84 cases of breast disease patients selected randomly at XinHua Hospital affiliated with Shanghai Second Medical University from September 1999 to December 2002. Of 84 cases, 72 case were breast cancer. Statistic analysis BCSG1 gene expression correlation with clinical parameters of breast cancer. 72 breast cancers were followed up (4 - 43 months) to set up independent prognosis factor by survival analysis. RESULTS: BCSG1 was undetectable in all benign breast lesions, while was detectable in 36.1% of all breast cancer samples (26/72), in which 79.2% of stage III/IV cases were positive (19/24). The expression of BCSG1 was tightly correlated with the stage (P = 0.000) and the size of tumor (P = 0.007). Both ER (P = 0.027) and BCSG1 (P = 0.001) were the independent prognosis factor of breast cancer. CONCLUSION: BCSG1 is one of independent tumor marker of breast cancer, the expression of BCSG1 is closely correlated to the stage of breast cancer and the tumor size. Maybe, BCSG1 is a new prognosis factor of breast cancer.

Role of enteral immunonutrition in patients with gastric carcinoma undergoing major surgery.

OBJECTIVE: To evaluate the influence of postoperative immunonutrition on immune and nutritional parameters in patients with gastric carcinoma. METHODS: From September 2002 to August 2003, 40 patients with gastric carcinoma who had undergone major surgery were randomly divided into an immunonutrition group and standard nutrition group, each of 20 patients. On postoperative Day 2, patients in the standard nutrition group received a standard enteral formula, while those in the immunonutrition group received an enteral formula enriched with glutamine, arginine and omega-3 fatty acids. Nutritional support was continued for 7 days. Blood samples were obtained to determine plasma albumin, prealbumin and transferrin on Days 0, 5 and 9. On Days 0, 1 and 9, blood samples were collected to detect immunoglobulin (Ig) A, IgG, IgM, CD4 and CD8 cell counts, the ratio of CD4/CD8, interleukin (IL)-2, IL-6 and tumour necrosis factor (TNF)-alpha, respectively. RESULTS: There were no significant differences between the two groups in protein and immune parameters preoperatively and no significant differences in management perioperatively. No serious adverse effects were recorded with the two formulas. Postoperative procedures were smooth in both groups. On Day 9, serum levels of prealbumin and transferrin were higher in the immunonutrition group than in the standard nutrition group (p<0.01). After 7 days' nutritional support, patients in the immunonutrition group had higher levels of immunoglobulin, CD4 cell counts, CD4/CD8 ratio and IL-2 than those in the control group, whereas IL-6 and TNF-alpha levels were significantly lower in the immunonutrition group. CONCLUSION: Compared with standard enteral nutrition, enteral immunonutrition can improve defence mechanisms and modulate inflammatory action after major elective surgery for gastric carcinoma.

Survivin antisense oligodeoxynucleotide inhibits growth of gastric cancer cells.

AIM: To investigate the effect of transfected survivin antisense oligonucleotide (ASODN) on proliferation and apoptosis of gastric cancer cells. METHODS: The authors designed ASODNs targeting different regions of survivin mRNA, including surviving ASODN1, ASODN2 and ASODN3. ASODNs were transfected into gastric cancer cell line SGC 7901, cell growth was detected by MTT assay. Cells exposed to the potent oligonucleotide were also examined for apoptosis induction by FCM and fluorescence microscopy. Semiquantitive RT-PCR and Western blot examinations were carried for expression of survivin mRNA and protein. RESULTS: ASODN3 caused a statistically significant reduction of cell viability to 60.6% (+/-2.9%) (P<0.01), while ASODN1 and ASODN2 had no such changes (P>0.05). The cell growth was also significantly inhibited by ASODN3, compared with reversal and scrambled sequence. A significant loss of survivin mRNA was presented in ASODN3 treated cells and this was not seen in treatment with sense ODN or scramble ODN. Protein level was significantly decreased 48 h after survivin ASODN trasfected by approximately 2-fold decrease compared with untreated controls. However, ASODN3 did not induce significant apoptosis response until 48 h after transfection (P>0.05). CONCLUSION: ASODN3, which targets translation initiation part, can be identified as a most potent antisense compound. Srvivin ASODN3 may provide a novel approach to therapy of gastric cancer.

Ets1 as a marker of malignant potential in gastric carcinoma.

AIM: Ets1 proto-oncogene is a transcription factor involved in the activation of several genes of tumor invasion and metastasis. We aimed to determine the relationship between the extent and intensity of Ets1 expression and patients' clinicopathological factors in gastric carcinoma. METHODS: Immunohistochemical analysis was performed for gastric tumor paraffin-embedded sections, followed by image analysis. RESULTS: Ets1 was not expressed in the normal gastric epithelium and its surrounding cells. The percentage of Ets1 expressing cells detected increased significantly in both epithelial tumor and stromal cells from high T classification, lymph node metastasis positive, clinical advanced-stage groups (P<0.001). The level of Ets1 staining in epithelial tumor cells also reflected the degree of cell differentiation. The percentage of epithelial and stromal cells expressing Ets1 was significantly correlated with the presence of lymph node metastasis (P=0.014 and P<0.001 respectively). Ets1 expression was not observed in tissue samples from patients with benign gastric ulcers. CONCLUSION: Ets1 protein expression in epithelial tumor cells reflects the degree of differentiation, and the percentage of Ets1 positive tumor and stromal cells correlates with lymph node metastasis. Thus Ets1 is a valuable marker of malignant potential in terms of invasiveness and metastasis of gastric carcinoma. It is also possible that inhibition of Ets1 is a potential avenue for therapy in gastric cancer.