Need for evidence on long-term prognosis of PD+HD: a commentary

Effect of proactive combination therapy with peritoneal dialysis and hemodialysis on technique survival and mortality

PURPOSE

Clinically relevant evidence for the timing of starting combination therapy with peritoneal dialysis and hemodialysis remains scarce. We retrospectively examined whether combination therapy during the induction phase of dialysis prolongs peritoneal dialysis duration.

METHODS

This retrospective study includes 160 patients who underwent combination therapy from 20 dialysis facilities. Four groups were categorized: combination at peritoneal dialysis induction (n = 12, Proactive combination group), and combination following peritoneal dialysis durations of < 2 years (n = 65), 2-5 years (n = 70), or > 5 years (n = 13). Differences in technique survival of dialysis, mortality, and hospitalization due to cardiovascular events in the groups were observed.

RESULTS

The Proactive combination group had the longer mean duration of combination therapy (3.18 years) comparing to that of combination therapy following peritoneal dialysis (1.45 years), but total peritoneal dialysis duration was shorter than in control groups (4.02 years). Of the 160 cases in the entire cohort, there were 8 deaths, 18 ischemic heart disease hospitalizations, and 18 stroke hospitalizations. The Proactive group had lower crude mortality rate (0/12 cases, 0.0%) and crude hospitalization rate for ischemic heart disease (1/11, 8.3%) than the other groups. However, this cohort study did not have enough statistical power to adjust for patients' background, and we were unable to fully examine the differences in such clinical outcomes by the timing of initiation of combination therapy.

CONCLUSION

Use of combination therapy in the induction phase might prolong the duration of combination therapy, but is not necessarily effective for prolonging peritoneal dialysis technique survival.

Peritoneal Dialysis for Potential Kidney Transplant Recipients: Pride or Prejudice?

Kidney transplantation (KT) is recognized as the gold-standard of treatment for patients with end-stage renal disease. Additionally, it has been demonstrated that receiving a pre-emptive KT ensures the best recipient and graft survivals. However, due to an overwhelming discrepancy between the organs available and the patients on the transplant waiting list, the vast majority of transplant candidates require prolonged periods of dialysis before being transplanted. For many years, peritoneal dialysis (PD) and hemodialysis (HD) have been considered competitive renal replacement therapies (RRT). This dualistic vision has recently been questioned by evidence suggesting that an individualized and flexible approach may be more appropriate. In fact, tailored and cleverly planned changes between different RRT modalities, according to the patient’s needs and characteristics, are often needed in order to achieve the best results. While home HD is still under scrutiny in this particular setting, current data seems to favor the use of PD over in-center HD in patients awaiting a KT. In this specific population, the demonstrated advantages of PD are superior quality of life, longer preservation of residual renal function, lower incidence of delayed graft function, better recipient survival, and reduced cost.

MIDCAN: A multiple input deep convolutional attention network for Covid-19 diagnosis based on chest CT and chest X-ray

Background

COVID-19 has caused 3.34m deaths till 13/May/2021. It is now still causing confirmed cases and ongoing deaths every day.

Method

This study investigated whether fusing chest CT with chest X-ray can help improve the AI's diagnosis performance. Data harmonization is employed to make a homogeneous dataset. We create an end-to-end multiple-input deep convolutional attention network (MIDCAN) by using the convolutional block attention module (CBAM). One input of our model receives 3D chest CT image, and other input receives 2D X-ray image. Besides, multiple-way data augmentation is used to generate fake data on training set. Grad-CAM is used to give explainable heatmap.

Results

The proposed MIDCAN achieves a sensitivity of 98.10±1.88%, a specificity of 97.95±2.26%, and an accuracy of 98.02±1.35%.

Conclusion

Our MIDCAN method provides better results than 8 state-of-the-art approaches. We demonstrate the using multiple modalities can achieve better results than individual modality. Also, we demonstrate that CBAM can help improve the diagnosis performance.