Deep learning analysis of clinical course of primary nephrotic syndrome: Japan Nephrotic Syndrome Cohort Study (JNSCS).

BACKGROUND: Prognosis of nephrotic syndrome has been evaluated based on pathological diagnosis, whereas its clinical course is monitored using objective items and the treatment strategy is largely the same. We examined whether the entire natural history of nephrotic syndrome could be evaluated using objective common clinical items. METHODS: Machine learning clustering was performed on 205 cases from the Japan Nephrotic Syndrome Cohort Study, whose clinical parameters, serum creatinine, serum albumin, dipstick hematuria, and proteinuria were traceable after kidney biopsy at 5 measured points up to 2 years. The clinical patterns of time-series data were learned using long short-term memory (LSTM)-encoder-decoder architecture, an unsupervised machine learning classifier. Clinical clusters were defined as Gaussian mixture distributions in a two-dimensional scatter plot based on the highest log-likelihood. RESULTS: Time-series data of nephrotic syndrome were classified into four clusters. Patients in the fourth cluster showed the increase in serum creatinine in the later part of the follow-up period. Patients in both the third and fourth clusters were initially high in both hematuria and proteinuria, whereas a lack of decline in the urinary protein level preceded the worsening of kidney function in fourth cluster. The original diseases of fourth cluster included all the disease studied in this cohort. CONCLUSIONS: Four kinds of clinical courses were identified in nephrotic syndrome. This classified clinical course may help objectively grasp the actual condition or treatment resistance of individual patients with nephrotic syndrome.

Incidence of remission and relapse of proteinuria, end-stage kidney disease, mortality, and major outcomes in primary nephrotic syndrome: the Japan Nephrotic Syndrome Cohort Study (JNSCS).

BACKGROUND: Despite recent advances in immunosuppressive therapy for patients with primary nephrotic syndrome, its effectiveness and safety have not been fully studied in recent nationwide real-world clinical data in Japan. METHODS: A 5-year cohort study, the Japan Nephrotic Syndrome Cohort Study, enrolled 374 patients with primary nephrotic syndrome in 55 hospitals in Japan, including 155, 148, 38, and 33 patients with minimal change disease (MCD), membranous nephropathy (MN), focal segmental glomerulosclerosis (FSGS), and other glomerulonephritides, respectively. The incidence rates of remission and relapse of proteinuria, 50% and 100% increases in serum creatinine, end-stage kidney disease (ESKD), all-cause mortality, and other major adverse outcomes were compared among glomerulonephritides using the Log-rank test. Incidence of hospitalization for infection, the most common cause of mortality, was compared using a multivariable-adjusted Cox proportional hazard model. RESULTS: Immunosuppressive therapy was administered in 339 (90.6%) patients. The cumulative probabilities of complete remission within 3 years of the baseline visit was ≥ 0.75 in patients with MCD, MN, and FSGS (0.95, 0.77, and 0.79, respectively). Diabetes was the most common adverse events associated with immunosuppressive therapy (incidence rate, 71.0 per 1000 person-years). All-cause mortality (15.6 per 1000 person-years), mainly infection-related mortality (47.8%), was more common than ESKD (8.9 per 1000 person-years), especially in patients with MCD and MN. MCD was significantly associated with hospitalization for infection than MN. CONCLUSIONS: Patients with MCD and MN had a higher mortality, especially infection-related mortality, than ESKD. Nephrologists should pay more attention to infections in patients with primary nephrotic syndrome.

Better remission rates in elderly Japanese patients with primary membranous nephropathy in nationwide real-world practice: The Japan Nephrotic Syndrome Cohort Study (JNSCS).

BACKGROUND: The aim of the present study was to clarify the prevalence of immunosuppressive drug use and outcomes in elderly and non-elderly patients with primary membranous nephropathy (MN) in nationwide real-world practice in Japan. PATIENTS AND METHODS: Between 2009 and 2010, 374 patients with primary nephrotic syndrome were enrolled in the cohort study (The Japan Nephrotic Syndrome Cohort Study, JNSCS), including 126 adult patients with MN. Their clinical characteristics were compared with those of nephrotic patients with primary MN registered in a large nationwide registry (The Japan Renal Biopsy Registry, J-RBR). Outcomes and predictors in the elderly (≥ 65 years) and non-elderly groups were identified. RESULTS: Similar clinical characteristics were observed in JNSCS patients and J-RBR patients (n = 1808). At the early stage of 1 month, 84.1% of patients were treated with immunosuppressive therapies. No significant differences were observed in therapies between age groups. However, elderly patients achieved complete remission (CR) more frequently than non-elderly patients, particularly those treated with therapies that included corticosteroids. No significant differences were noted in serum creatinine (sCr) elevations at 50 or 100%, end-stage kidney disease, or all-cause mortality between age groups. Corticosteroids were identified as an independent predictor of CR (HR 2.749, 95%CI 1.593-4.745, p = 0.000) in the multivariate Cox's model. sCr levels, hemoglobin levels, immunosuppressants, clinical remission, and relapse after CR were independent predictors of sCr × 1.5 or × 2.0. CONCLUSION: Early immunosuppressive therapy including corticosteroids for primary MN showed better remission rates in elderly patients in a nationwide cohort study.

Regional variations in immunosuppressive therapy in patients with primary nephrotic syndrome: the Japan nephrotic syndrome cohort study.

BACKGROUND: The lack of high-quality clinical evidences hindered broad consensus on optimal therapies for primary nephrotic syndromes. The aim of the present study was to compare prevalence of immunosuppressive drug use in patients with primary nephrotic syndrome across 6 regions in Japan. METHODS: Between 2009 and 2010, 380 patients with primary nephrotic syndrome in 56 hospitals were enrolled in a prospective cohort study [Japan Nephrotic Syndrome Cohort Study (JNSCS)], including 141, 151, and 38 adult patients with minimal change disease (MCD), membranous nephropathy (MN), and focal segmental glomerulosclerosis (FSGS), respectively. Their clinical characteristics were compared with those of patients registered in a large nationwide registry of kidney biopsies [Japan Renal Biopsy Registry (J-RBR)]. The regional prevalence of use of each immunosuppressive drug was assessed among adult MCD, MN, and FSGS patients who underwent immunosuppressive therapy in the JNSCS (n = 139, 127, and 34, respectively). Predictors of its use were identified using multivariable-adjusted logistic regression models. RESULTS: The clinical characteristics of JNSCS patients were comparable to those of J-RBR patients, suggesting that the JNSCS included the representatives in the J-RBR. The secondary major immunosuppressive drugs were intravenous methylprednisolone [n = 33 (24.6%), 24 (19.7%), and 9 (28.1%) in MCD, MN, and FSGS, respectively] and cyclosporine [n = 25 (18.7%), 62 (50.8%), and 16 (50.0%), respectively]. The region was identified as a significant predictor of use of intravenous methylprednisolone in MCD and MN patients. CONCLUSION: Use of intravenous methylprednisolone for MCD and MN differed geographically in Japan. Its efficacy should be further evaluated in a well-designed trial.

A case of perirenal extramedullary hematopoiesis in a patient with primary myelofibrosis.

Extramedullary hematopoiesis (EMH) is hematopoiesis in organs outside the bone marrow and most frequently occurs in the liver, spleen, and lymph nodes. We report a case of perirenal EMH revealed by kidney biopsy in a patient with primary myelofibrosis. We observed only bilateral kidney enlargement with plain computed tomography (CT) and ultrasonography before obtaining a renal biopsy. We obtained a percutaneous biopsy from the lower pole of the left kidney using ultrasonographic guidance. Ultrasonography just after the renal biopsy revealed no bleeding around the kidney. However, early the next morning, the patient developed severe hemorrhagic shock. Contrast-enhanced CT at that time revealed a massive hematoma in the left posterior perirenal space and bilateral abnormalities of the perirenal soft tissues. In patients with primary myelofibrosis, if plain CT shows an abnormal renal enlargement, EMH should be considered. In addition, a contrast-enhanced CT should be obtained before performing a percutaneous renal biopsy to assess for the possibility of perirenal EMH in these patients.

Bone marrow transplant nephropathy successfully treated with angiotensin-converting enzyme inhibitor.

We report a patient who developed chronic renal failure 11 months after an allogeneic hematopoietic stem-cell transplantation (HSCT) for Ph1(+) acute lymphocytic leukemia. Renal biopsy showed typical pathological findings compatible with a bone marrow transplant nephropathy (BMT nephropathy). The general course of BMT nephropathy is slowly progressive, eventually reaching endstage renal failure. Intervention therapy with an angiotensin-converting enzyme inhibitor (ACE-I), temocapril, was started for this patient, based on several experimental reports showing the protective effects of ACE-Is on BMT nephropathy. After the induction of ACE-I in this patient, the rate of regression of renal function was significantly reduced and his serum creatinine was maintained at almost the same level for 18 months. Although the course of observation in this patient was short, we clearly showed the effects of an ACE-I on preventing BMT nephropathy from progressing to endstage renal failure in a human rather than in an experimental model.