Search

Objective To analyze the risk factors and clinical prognosis of acute kidney injury (AKI) early after lung transplantation. Methods Clinical data of 155 recipients undergoing lung transplantation or combined heart-lung transplantation were retrospectively analyzed, and they were divided into the AKI group (n=104) and non-AKI group (n=51) according to the 2012 Kidney Disease: Improving Global Outcomes Clinical Practice Guideline. The incidence of AKI early after lung transplantation was summarized. The main indexes of recipients were collected. The risk factors of the occurrence of AKI early after lung transplantation were subjected to univariate and multivariate analysis. The clinical prognosis of lung transplant recipients was evaluated and the survival curve was delineated. Results The incidence of AKI early after lung transplantation was 67.1%(104/155), including 47 recipients with stage 1 AKI, 34 recipients with stage2 AKI and 23 recipients with stage 3 AKI, respectively. Sixteen recipients required continuous renal replacement therapy (CRRT) early after lung transplantation. Preoperative complication with diabetes mellitus, preoperative complication with pulmonary hypertension, intraoperative mean arterial pressure (MAP) < 60 mmHg, intraoperative massive blood transfusion, and treatment with excessive therapeutic concentration of tacrolimus (Tac) within postoperative 1 week were the independent risk factors for the occurrence of AKI early after lung transplantation. Up to the end of follow-up, 66 recipients (42.6%) died, including 50 recipients in the AKI group and 16 recipients in the non-AKI group. The cumulative survival rate in the AKI group was significantly lower than that in the non-AKI group (40% vs. 66%, P < 0.05). With the increase of AKI severity, the cumulative survival rate of lung transplant recipients was decreased. Conclusions AKI develops early after lung transplantation with high incidence and poor clinical prognosis. Preoperative complication with diabetes mellitus and pulmonary hypertension, intraoperative MAP < 60 mmHg and massive blood transfusion, and treatment with excessive therapeutic concentration of Tac within postoperative 1 week are the independent risk factors for the occurrence of AKI early after lung transplantation.

Objective To analyze the dynamic changes and the influencing factors of T lymphocyte subsets in recipients with stable graft status within 1 year after lung transplantation. Methods Clinical data of 41 recipients with stable graft status after allogeneic lung transplantation were analyzed. The absolute value and ratio of T lymphocyte subsets in peripheral blood from recipients were measured by flow cytometry before operation, 2 weeks and each month (within 1 year) after operation, respectively. The effects of age, gender, body mass index (BMI), surgical method, incidence of primary graft dysfunction (PGD) after operation, and primary disease upon the absolute values of T lymphocytes were evaluated. Results Within 1 year after lung transplantation, the absolute values of CD3+, CD3+CD4+, CD3+CD8+T lymphocytes and CD4+/CD8+ ratio were changed over time (all P < 0.001). Compared with preoperative values, there was no statistical significance in the absolute values of CD3+ and CD3+CD4+T lymphocytes at 12 months after operation (P=0.659, 0.109), whereas the absolute value of CD3+CD8+T lymphocytes was increased (P=0.02) and the CD4+/CD8+ ratio was decreased (P < 0.001). Age, gender, BMI, surgical method and incidence of PGD after operation exerted no significant effect on the dynamic changes of absolute values of CD3+CD4+ and CD3+CD8+T lymphocytes (all P > 0.05). Primary disease before lung transplantation exerted no effect on the changes of CD3+CD4+T lymphocytes, whereas the postoperative absolute value of CD3+CD8+T lymphocytes was higher in recipients with infectious lung diseases (P < 0.05). Conclusions The absolute values of CD3+, CD3+CD4+, CD3+CD8+T lymphocytes in recipients with stable graft status after lung transplantation are relatively low in the early stage after lung transplantation, then gradually restore, and stabilize at 6 months after operation. Dynamic changes are not associated with age, gender, BMI, surgical method and incidence of PGD after operation of recipients.

Background Main challenges for COVID-19 include the lack of a rapid diagnostic test, a suitable tool to monitor and predict a patient’s clinical course and an efficient way for data sharing among multicenters. We thus developed a novel artificial intelligence system based on deep learning (DL) and federated learning (FL) for the diagnosis, monitoring, and prediction of a patient’s clinical course. Methods CT imaging derived from 6 different multicenter cohorts were used for stepwise diagnostic algorithm to diagnose COVID-19, with or without clinical data. Patients with more than 3 consecutive CT images were trained for the monitoring algorithm. FL has been applied for decentralized refinement of independently built DL models. Results A total of 1,552,988 CT slices from 4804 patients were used. The model can diagnose COVID-19 based on CT alone with the AUC being 0.98 (95% CI 0.97–0.99), and outperforms the radiologist’s assessment. We have also successfully tested the incorporation of the DL diagnostic model with the FL framework. Its auto-segmentation analyses co-related well with those by radiologists and achieved a high Dice’s coefficient of 0.77. It can produce a predictive curve of a patient’s clinical course if serial CT assessments are available. Interpretation The system has high consistency in diagnosing COVID-19 based on CT, with or without clinical data. Alternatively, it can be implemented on a FL platform, which would potentially encourage the data sharing in the future. It also can produce an objective predictive curve of a patient’s clinical course for visualization. Key Points • CoviDet could diagnose COVID-19 based on chest CT with high consistency; this outperformed the radiologist’s assessment. Its auto-segmentation analyses co-related well with those by radiologists and could potentially monitor and predict a patient’s clinical course if serial CT assessments are available. It can be integrated into the federated learning framework. • CoviDet can be used as an adjunct to aid clinicians with the CT diagnosis of COVID-19 and can potentially be used for disease monitoring; federated learning can potentially open opportunities for global collaboration. Supplementary Information The online version contains supplementary material available at 10.1007/s00330-021-08334-6.