Nefropatia cukrzycowa
Rokowania, prognozy i postęp choroby

Nefropatia cukrzycowa (DN) jest główną przyczyną schyłkowej niewydolności nerek (ESRD) u pacjentów z cukrzycą typu 2 (T2D). Rokowanie zależy od wielu czynników klinicznych i patologicznych, przy czym pacjenci z czystą DN oraz mieszanymi postaciami DN i niecukrzycowej choroby nerek (NDRD) mają gorsze wyniki niż osoby z samą NDRD. Kluczowymi czynnikami prognostycznymi są m.in. wyjściowy eGFR, nasilenie białkomoczu, poziom hemoglobiny, wiek, płeć męska oraz parametry laboratoryjne takie jak albumina, wapń, wodorowęglany i fosforany. Retinopatia cukrzycowa (DR) jest silnym niezależnym predyktorem progresji do ESRD, z ryzykiem wzrastającym od łagodnej do proliferacyjnej postaci DR (HR 1,69; 95% CI: 1,16-2,45; p=0,006). Modele prognostyczne, takie jak Kidney Failure Risk Equation (KFRE), choć skuteczne, mają ograniczoną wartość predykcyjną w DN w porównaniu do mieszanych postaci CKD. Dodanie danych patologicznych do KFRE nie poprawia istotnie predykcji ESRD.

Rokowanie w nefropatii cukrzycowej (Diabetic nephropathy prognosis)

Nefropatia cukrzycowa (DN) jest jednym z najczęstszych powikłań cukrzycy typu 2 (T2D) i wiodącą przyczyną schyłkowej niewydolności nerek (ESRD) na całym świecie. Przebieg choroby, progresja do ESRD oraz rokowanie u pacjentów z nefropatią cukrzycową zależą od wielu czynników klinicznych, laboratoryjnych i patologicznych.123

Porównanie rokowania w różnych typach choroby nerek u pacjentów z cukrzycą

Badania wykazały istotne różnice w rokowaniu pomiędzy pacjentami z czystą nefropatią cukrzycową (DN), niecukrzycową chorobą nerek (NDRD) oraz mieszaną postacią obu chorób (MIX):12

  • Pacjenci z czystą nefropatią cukrzycową oraz z mieszaną postacią choroby (MIX) wykazują gorsze rokowanie nerkowe niż pacjenci z niecukrzycową chorobą nerek (NDRD)
  • Po uwzględnieniu parametrów wyjściowych (czas trwania cukrzycy, HbA1c, retinopatii cukrzycowej, eGFR i 24-godzinnego białkomoczu), pacjenci z czystą DN byli prawie czterokrotnie bardziej narażeni na niepomyślne rokowanie nerkowe w porównaniu do pacjentów z NDRD
  • Identyfikacja NDRD u pacjentów z cukrzycą ma istotne znaczenie kliniczne, ponieważ wykazano, że ci pacjenci mają lepsze przeżycie i rokowanie nerkowe w porównaniu z DN

145

Kliniczne czynniki prognostyczne w nefropatii cukrzycowej

Zidentyfikowano szereg klinicznych czynników prognostycznych, które są związane z niepomyślnym rokowaniem nerkowym u pacjentów z nefropatią cukrzycową:26

  • Wyjściowa funkcja nerek – niższy eGFR jest silnym predyktorem progresji do ESRD
  • Nasilenie białkomoczu – ciężki białkomocz jest związany z gorszym rokowaniem
  • Niższy poziom hemoglobiny – koreluje z szybszą progresją choroby
  • Wywiad rodzinny cukrzycy – zwiększa ryzyko niekorzystnych wyników nerkowych
  • Wiek – starszy wiek jest czynnikiem ryzyka rozwoju przewlekłej choroby nerek
  • Płeć męska – mężczyźni wykazują szybszą progresję do niewydolności nerek
  • Parametry laboratoryjne – niższy poziom albuminy, wapnia i wodorowęglanów w surowicy oraz wyższy poziom fosforanów wiążą się z podwyższonym ryzykiem niewydolności nerek

789

W badaniu oceniającym pacjentów z nefropatią cukrzycową z białkomoczem w zakresie nerczycowym, wieloczynnikowa analiza wykazała, że niższy poziom hemoglobiny i niższy eGFR były istotnie związane z gorszymi wynikami nerkowymi, podczas gdy czas trwania cukrzycy, poziom albuminy, białkomocz, stosowanie ACEI/ARB, stosowanie insuliny i uszkodzenie histopatologiczne nie były związane z niepomyślnymi wynikami nerkowymi.610

Retinopatia cukrzycowa jako czynnik prognostyczny

Retinopatia cukrzycowa (DR) jest istotnym czynnikiem prognostycznym rozwoju i progresji nefropatii cukrzycowej:1112

  • Obecność retinopatii cukrzycowej jest związana ze zwiększonym ryzykiem rozwoju ESRD
  • W analizie przeżycia Coxa, retinopatia cukrzycowa była związana ze zwiększonym ryzykiem rozwoju ESRD z skorygowanym współczynnikiem ryzyka 1,69 (95% CI: 1,16-2,45, P=0,006)
  • Ryzyko ESRD wzrasta stopniowo od łagodnej nieproliferacyjnej retinopatii cukrzycowej (NPDR) do umiarkowanej NPDR, ciężkiej NPDR i proliferacyjnej retinopatii cukrzycowej, nawet po uwzględnieniu znanych czynników ryzyka ESRD
  • Dodanie stopnia retinopatii do modelu klinicznego poprawia wartość prognostyczną, co jest porównywalne z dodaniem oceny zmian nerkowych do modelu klinicznego

1314

Badania wykazały, że progresja retinopatii dodatnio koreluje ze wszystkimi ocenami zmian nerkowych, szczególnie z klasyfikacją opartą na kłębuszkach (r=0,41), ocenami włóknienia śródmiąższowego (r=0,41) i zmian rozlanych (r=0,48). To sugeruje, że retinopatia cukrzycowa i choroba nerek mają podobny zakres progresji choroby, a zatem retinopatia cukrzycowa może być użyteczna w prognozowaniu przebiegu klinicznego nefropatii cukrzycowej.13

Modele predykcyjne w nefropatii cukrzycowej

Równanie ryzyka niewydolności nerek (KFRE)

Równanie ryzyka niewydolności nerek (Kidney Failure Risk Equation, KFRE) jest jednym z najlepiej zwalidowanych narzędzi prognostycznych w przewlekłej chorobie nerek:1516

  • KFRE zostało zewnętrznie zwalidowane i przewyższa inne modele predykcji ryzyka
  • Model ten może pomóc w ustaleniu czasu przygotowania do terapii zastępczej nerek oraz poprawić planowanie zasobów opieki zdrowotnej
  • KFRE jest dobrym narzędziem do identyfikacji wysokiego ryzyka progresji do ESRD wśród pacjentów z nefropatią cukrzycową i zaawansowaną CKD
  • Jednak wartość predykcyjna KFRE jest słabsza w nefropatii cukrzycowej niż w mieszanej kohorcie CKD pierwotnie opisanej przez Tangri i wsp.

1718

Warto zauważyć, że dodanie informacji patologicznych opartych na klasyfikacji nefropatii cukrzycowej przez Renal Pathology Society do KFRE nie poprawiło znacząco predykcji ESRD.17

Modele uczenia maszynowego w przewidywaniu progresji nefropatii cukrzycowej

Coraz więcej badań koncentruje się na zastosowaniu sztucznej inteligencji (AI) i uczenia maszynowego (ML) do przewidywania progresji nefropatii cukrzycowej:1920

  • AI może przewidywać nasilenie DKD z 71% dokładnością, przetwarzając język naturalny i dane longitudinalne z wykorzystaniem uczenia maszynowego na dużych zbiorach danych
  • Pacjenci z progresją DKD w ciągu 6 miesięcy mieli znacznie wyższą częstość występowania hemodializy z powodu przewlekłej niewydolności nerek w okresie 10 lat
  • Model LightGBM wykazał najwyższą wartość AUC (0,815, 95% CI 0,747-0,882) w prognozowaniu 3-letniego ryzyka rozwoju DKD u pacjentów z T2DM i normoalbuminurią
  • Starsi pacjenci z wysokim poziomem homocysteiny (Hcy), słabą kontrolą glikemii, niskim poziomem albuminy w surowicy (ALB), niskim eGFR i wysokim poziomem wodorowęglanów mieli zwiększone ryzyko rozwoju DKD w ciągu najbliższych 3 lat

2122

Pomimo potencjału wykorzystania technik ML do pełnego wykorzystania wymiaru czasowego danych z elektronicznej dokumentacji medycznej (EHR) w celu przewidywania ryzyka rozwoju lub progresji DN, nie zostało to jeszcze w pełni osiągnięte. Wiele stosowanych technik ma ograniczone wykorzystanie wymiaru czasowego i bogactwa danych pacjentów dostępnych w danych EHR.23

Modele kliniczno-patologiczne

Opracowano również modele predykcyjne łączące dane kliniczne i patologiczne do przewidywania ryzyka ESRD u pacjentów z nefropatią cukrzycową potwierdzoną biopsją:2425

  • Model kliniczno-patologiczny wykazał dobrą wydajność wśród kilku modeli
  • Badanie wykazało, że niższy eGFR, wyższy poziom cystatyny C, wyższy BNP, wyższy poziom Log ACR i wyższy stopień patologiczny znacząco zwiększają ryzyko ESRD u pacjentów z DN
  • Model uwzględniający te czynniki ryzyka może potencjalnie stać się prostym kalkulatorem medycznym do zastosowania w praktyce klinicznej

Japoński system punktacji patologicznej (J-score) oparty na klasyfikacji Japońskiego Towarzystwa Patologii Nerkowej (JRPS) również wykazał wartość predykcyjną w odniesieniu do rokowania nerkowego:2627

  • Mezangioliza, waskuloza biegunowa i podwojenie błony podstawnej kłębuszków – cechy systemu JRPS – były istotnie związane z rokowaniem nerkowym
  • Po uwzględnieniu czynników klinicznych, J-score był istotnym predyktorem rokowania nerkowego
  • Na podstawie systemu J-score można przewidzieć rokowanie nerkowe; jeśli J-score wynosi 5, przewidywane rokowanie nerkowe jest doskonałe, z oczekiwanym przeżyciem nerek 18 lat. Jednak jeśli J-score wynosi 16, przewidywane rokowanie nerkowe jest złe, z oczekiwanym przeżyciem nerek 2 lata

Progresja choroby i zapobieganie

Naturalna progresja nefropatii cukrzycowej

Nefropatia cukrzycowa jest uważana za chorobę postępującą, która zwykle pogarsza się z czasem, aż nerki nie będą mogły funkcjonować samodzielnie, co prowadzi do schyłkowej niewydolności nerek (ESRD).20 Badania wykazały, że:16

  • U 29% do 38% osób z T2DM rozwija się CKD po medianie obserwacji wynoszącej 15 lat
  • Szacowana zapadalność na ESRD wśród osób z CKD G3a wynosi 0,3 na 1000 osobolat, podczas gdy wzrasta ona do 4 i 43 na 1000 osobolat odpowiednio w CKD G3b i G4
  • W badaniu obejmującym 3-letni okres obserwacji było 225 zdarzeń końcowych (47,1%) wśród pacjentów z nefropatią cukrzycową potwierdzoną biopsją

24

Analiza trajektorii stężenia kreatyniny w surowicy, zarówno w czasie rzeczywistym, jak i retrospektywnie, rzeczywiście dostarcza dodatkowych, lepszych informacji diagnostycznych i prognostycznych w postępowaniu z pacjentem nefrologicznym. Należy jednak zauważyć, że z niejasnych przyczyn stopień albuminurii niekoniecznie jest powiązany z progresją choroby u pacjentów z nefropatią cukrzycową związaną z cukrzycą typu 1 lub typu 2, co podkreśla heterogeniczność nefropatii cukrzycowej.28

Strategie zapobiegania i leczenia

Terminowe wdrożenie oceny ryzyka DN może opóźnić lub nawet zapobiec jej progresji, co z pewnością zmniejszyłoby liczbę osób z ESRD.20 Kluczowe strategie zapobiegania i leczenia obejmują:299

  • Wczesne wykrywanie – uszkodzenie nerek jest bardziej prawdopodobne, jeśli masz niekontrolowany poziom cukru we krwi (glukozy)
  • Wczesne leczenie – gdy uszkodzenie nerek zostaje wykryte we wczesnych stadiach, można je spowolnić dzięki leczeniu. Gdy w moczu pojawią się większe ilości białka, uszkodzenie nerek będzie stopniowo się pogarszać
  • Identyfikacja czynników ryzyka – wczesna identyfikacja i stratyfikacja ryzyka osób, które mają zwiększone ryzyko szybkiej progresji CKD, ułatwi terminową interwencję w celu zapobiegania ESRD i przedwczesnej śmiertelności
  • Proste podejścia oparte na ryzyku – takie jak KFRE mogą poprawić wykrywanie, stratyfikację ryzyka, upodmiotowienie pacjenta i terminową interwencję w celu zmniejszenia inercji terapeutycznej i poprawy wyników zdrowotnych

30

W celu obniżenia zachorowalności i śmiertelności z powodu przewlekłej choroby nerek wśród pacjentów z cukrzycą typu 2, zaleca się opracowanie zarówno strategii profilaktycznych, jak i leczniczych, takich jak podnoszenie świadomości, tworzenie wspierającego środowiska i przepisywanie odpowiednich leków na wczesnym etapie.9

Wnioski

Nefropatia cukrzycowa pozostaje główną przyczyną schyłkowej niewydolności nerek na całym świecie, nakładając ciężkie brzemię nie tylko na poszczególnych pacjentów, ale także na społeczeństwo.3 Dokładne przewidywanie ryzyka ESRD jest podstawą optymalnego postępowania w CKD.16

Prognozy pacjentów z nefropatią cukrzycową zależą od wielu czynników, w tym wieku, podstawowego rozpoznania, wdrożenia i powodzenia wtórnych środków zapobiegawczych oraz indywidualnych cech pacjenta.7 Czysta nefropatia cukrzycowa i mieszane formy DN z NDRD mają gorsze rokowanie nerkowe niż NDRD.2

Nowoczesne modele predykcyjne wykorzystujące dane kliniczne, patologiczne i analizy oparte na uczeniu maszynowym mogą pomóc w identyfikacji pacjentów zagrożonych szybką progresją do ESRD, co umożliwia terminową interwencję i optymalne zarządzanie zasobami opieki zdrowotnej.230

Retinopatia cukrzycowa jest silnym predyktorem ESRD, niezależnie od ustalonych czynników ryzyka ESRD, u pacjentów z cukrzycą typu 2 i nefropatią cukrzycową potwierdzoną biopsją, co sugeruje, że intensywne badania przesiewowe w kierunku retinopatii cukrzycowej mogą być potężnym narzędziem w prognozowaniu przebiegu klinicznego nefropatii cukrzycowej.14

Kolejne rozdziały

Zapraszamy do dalszego czytania naszego leksykonu.

Wybierz kolejny rozdział z menu poniżej, aby otworzyć nową podstronę kompedium wiedzy i uzyskać szczegółowe informację o leku, substancji lub chorobie.

  1. 09.04.2026
  2. www.leksykon.com.pl

Materiały źródłowe

  • #1
    https://pmc.ncbi.nlm.nih.gov/articles/PMC8543721/
    To evaluate the renal outcomes and prognostic factors among patients with type-2 diabetes (T2D) and biopsy-confirmed diabetic nephropathy (DN), non-diabetic renal disease (NDRD) and DN mixed with NDRD (MIX). […] In patients with T2D and CKD, pure DN and MIX group displayed a worse renal prognosis than NDRD group. Worse renal function, severe proteinuria, lower hemoglobin, and a family history of diabetes may be associated with adverse renal outcomes in patients with DN. […] Diabetic nephropathy (DN) is one of the most common complications of type-2 diabetes (T2D) and the leading cause of end-stage renal disease (ESRD) worldwide. […] Our results showed that after adjustment of baseline parameters including duration of diabetes, HbA1c, DR, eGFR, and 24-h urinary protein, patients with pure DN were almost four times more likely to have adverse renal outcomes compared to NDRD.
  • #2 Artificial intelligence predicts the progression of diabetic kidney disease using big data machine learning | Scientific Reports
    https://www.nature.com/articles/s41598-019-48263-5
    DKD is one of the most common diabetic complications and its progression results in hemodialysis for end-stage renal disease (ESRD). […] We showed here that progression of DKD in 6 months could result in a higher incidence of hemodialysis due to chronic renal failure in our patients over 10 years. Furthermore, the unstable proteinuria group had a higher incidence of cardiovascular events than the stable non-proteinuria group. These results suggest that very early intervention to reduce proteinuria could contribute to a better prognosis for both renal and cardiac diseases. […] In conclusion, the new predictive model using AI could detect the progression of DKD, which may contribute to more effective and accurate intervention to reduce hemodialysis and cardiovascular events.
  • #2
    https://pmc.ncbi.nlm.nih.gov/articles/PMC8543721/
    Among patients with DN, individuals with a DM family history, lower Hb, lower eGFR, and severe proteinuria were prone to have adverse renal outcomes. […] The prognosis of pure DN might be similar to DN mixed with NDRD, and both of them were worse than that of pure NDRD. A family history of diabetes, lower hemoglobin, worse renal function, and severe proteinuria were independent predictors for endpoint events in patients with DN.
  • #3 Value of adding the renal pathological score to the kidney failure risk equation in advanced diabetic nephropathy | PLOS One
    https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0190930
    There have been a limited number of biopsy-based studies on diabetic nephropathy, and therefore the clinical importance of renal biopsy in patients with diabetes in late-stage chronic kidney disease (CKD) is still debated. […] We aimed to clarify the renal prognostic value of pathological information to clinical information in patients with diabetes and advanced CKD. […] The cox regression analysis showed that the KFRE, D-score and KFRE+D-score were significant predictors of ESRD both in the development cohort and in the validation cohort. […] We found that the predict values of the KFRE and the D-score were not as good as reported, and combining the D-score with the KFRE did not significantly improve prediction of the risk of ESRD in advanced diabetic nephropathy. […] Despite advances over the past 20 years in delaying the progression of diabetic nephropathy, it is still a leading cause of end-stage renal disease (ESRD) worldwide and imposes a heavy burden not only on individual patients but also on society.
  • #4 A predictive model of non-diabetic kidney disease in patients with diabetes mellitus and chronic kidney disease. A Spanish multi-center study | Nefrología
    https://revistanefrologia.com/es-a-predictive-model-of-non-diabetic-articulo-S0211699524001231
    A predictive model of non-diabetic kidney disease in patients with diabetes mellitus and chronic kidney disease. A Spanish multi-center study […] Identifying NDKD is crucial since these patients have a better renal prognosis and survival compared to patients with diabetic nephropathy (DN). […] In our study, we developed a risk-stratification score to calculate the probability of NDKD. This could be in a next future a useful tool for the clinical indication of renal biopsy in patients with diabetes and kidney disease. […] Identifying NDKD in patients with DM has an important clinical relevance since it has been shown that these patients have a better survival and renal prognosis as compared with DN. […] The independent risk factors for NDKD were the presence of microhaematuria, older age, the absence of DR and the absence of peripheral vascular disease.
  • #5 A predictive model of non-diabetic kidney disease in patients with diabetes mellitus and chronic kidney disease. A Spanish multi-center study | Nefrología
    https://revistanefrologia.com/es-a-predictive-model-of-non-diabetic-articulo-S0211699524001231
    In summary, our study provides a new predictive model with clinical utility for helping the clinician to decide when to perform renal biopsy in patients with diabetes. This nomogram is a useful tool since it helps to identify patients with diabetes at risk for NDKD. If NDKD is confirmed by kidney biopsy, as a consequence, may lead to a change on treatment, renal prognosis and patient survival.
  • #6 Whether Renal Pathology Is an Independent Predictor for End-Stage Renal Disease in Diabetic Kidney Disease Patients with Nephrotic Range Proteinuria: A Biopsy-Based Study
    https://www.mdpi.com/2077-0383/12/1/88
    Aims: To investigate whether renal pathology is an independent predictor for end-stage renal disease (ESRD) in diabetic kidney diseases (DKD) with nephrotic range proteinuria. […] The hemoglobin and e-GFR, but not the histopathological damage, were significantly associated with a higher risk of ESRD in both the univariate and multivariate Cox analyses. […] In patients with diabetic kidney disease characterized by nephrotic range proteinuria, histopathological damage (glomerular alterations, interstitial fibrosis and tubular atrophy (IFTA), interstitial inflammation, and arteriolar hyalinosis) is not associated with poor renal outcomes, but hemoglobin and e-GFR could predict poor renal outcomes. […] Multivariate analysis showed that lower hemoglobin and lower e-GFR were significantly associated with poorer renal outcomes, while the duration of diabetes, albumin level, proteinuria, use of ACEI/ARB, use of insulin, and histopathological damage were not associated with adverse renal outcomes.
  • #7 Chronic Kidney Disease (CKD): Practice Essentials, Pathophysiology, Etiology
    https://emedicine.medscape.com/article/238798-overview
    Patients with chronic kidney disease (CKD) generally experience progressive loss of kidney function and are at risk for end-stage kidney disease (ESKD). The rate of progression depends on age, the underlying diagnosis, the implementation and success of secondary preventive measures, and the individual patient. Timely initiation of long-term renal replacement therapy is imperative to prevent the uremic complications of CKD that can lead to significant morbidity and death. […] Tangri et al developed and validated a model in adult patients that uses routine laboratory results to predict progression from CKD (stages 3-5) to kidney failure. They reported that lower estimated glomerular filtration rate (GFR), higher albuminuria, younger age, and male sex pointed to a faster progression of kidney failure. Also, a lower serum albumin, calcium, and bicarbonate level and a higher serum phosphate level predicted an elevated risk of kidney failure.
  • #8 Prevalence and predictors of chronic kidney disease among type 2 diabetic patients worldwide, systematic review and meta-analysis | Diabetology & Metabolic Syndrome | Full Text
    https://dmsjournal.biomedcentral.com/articles/10.1186/s13098-023-01202-x
    Diabetes is the leading cause of CKD. […] The pooled magnitude of chronic kidney disease among type 2 DM patients was 27% (95% CI 21%, 33%). […] Patients with CKD have an elevated risk of severe renal and cardiovascular morbidity and mortality. […] In this systematic review and meta-analysis increased age, obesity, having a history of type 2 diabetes mellitus, smoking history, presence of hypertension, and cardiac heart disease were factors significantly associated with the presence of chronic kidney disease among type 2 diabetic patients. […] The prevalence of chronic kidney disease among type 2 diabetes mellitus patients was high based on the included 20 articles. […] The review reported that old age, hypertension, cardiac disease, smoking, obesity, and duration of diabetes mellitus was predictor variable for chronic kidney disease among type 2 diabetic patients.
  • #9 Prevalence and predictors of chronic kidney disease among type 2 diabetic patients worldwide, systematic review and meta-analysis | Diabetology & Metabolic Syndrome | Full Text
    https://dmsjournal.biomedcentral.com/articles/10.1186/s13098-023-01202-x
    Therefore, in order to lower the morbidity and mortality from chronic kidney disease among type 2 diabetic patients, it is advised to develop both preventive and curative intervention strategies, such as raising awareness, creating a supportive environment, and prescribing appropriate medication at an early stage. […] CKD is estimated to affect 50% patients with T2DM globally, and its presence and severity markedly influences disease prognosis. […] The study revealed that being old age, hypertension, cardiac disease, smoking, obesity, having type 2 diabetes mellitus was predictor variable for presence of chronic kidney disease among type 2 diabetic patients. […] This systematic review and meta-analysis revealed that the prevalence of chronic kidney disease among type 2 diabetes mellites patients was high based on the included 20 articles.
  • #10 Whether Renal Pathology Is an Independent Predictor for End-Stage Renal Disease in Diabetic Kidney Disease Patients with Nephrotic Range Proteinuria: A Biopsy-Based Study
    https://www.mdpi.com/2077-0383/12/1/88
    In conclusion, this study suggests that in patients with DKD complicated by nephrotic range proteinuria, lower hemoglobin and lower GFR are significantly associated with adverse renal outcomes. However, histopathological damage (glomerular alterations, interstitial fibrosis and tubular atrophy (IFTA), interstitial inflammation, and arteriolar hyalinosis) is not associated with poor renal outcomes.
  • #11 Diabetic Retinopathy and Clinical Parameters Favoring the Presence of Diabetic Nephropathy could Predict Renal Outcome in Patients with Diabetic Kidney Disease | Scientific Reports
    https://www.nature.com/articles/s41598-017-01204-6
    Diabetes duration, diabetic retinopathy (DR), and a diagnostic model have been proposed as clinical parameters favoring the presence of diabetic nephropathy (DN) in biopsied patients with diabetic kidney disease. […] DN, compared with non-diabetic renal disease, had poorer renal outcomes. […] In a Cox survival analysis, DR and the diagnostic model favoring DN were associated with an increased risk for end-stage renal disease with adjusted hazard ratios of 1.69 (95% CI: 1.162.45, P=0.006) and 1.66 (95% CI: 1.052.61, P=0.029), respectively. […] In conclusion, DR and the diagnostic model favoring DN were associated with poorer renal outcomes. […] After a median follow-up period of 2.9 years, 24 (8.0%) and 184 (17.9%) patients with DM8 years and DM8 years progressed to ESRD, respectively.
  • #12 Diabetic Retinopathy and Clinical Parameters Favoring the Presence of Diabetic Nephropathy could Predict Renal Outcome in Patients with Diabetic Kidney Disease | Scientific Reports
    https://www.nature.com/articles/s41598-017-01204-6
    Both DR and the positive diagnostic model were significantly associated with increased risks for ESRD with HRs of 1.69 (95% CI: 1.162.45, P=0.006) and 1.66 (95% CI: 1.052.61, P=0.029), respectively. […] Our study findings have several limitations. […] Our study investigated whether DM8 years, DR, and the diagnostic model favoring DN are associated with clinical outcomes in patients with diabetic kidney disease. […] We further revealed that DR and the diagnostic model favoring DN were significantly associated with an increased risk for ESRD.
  • #13 Retinopathy progression and the risk of end-stage kidney disease: results from a longitudinal Japanese cohort of 232 patients with type 2 diabetes and biopsy-proven diabetic kidney disease | BMJ Open Diabetes Research & Care
    https://drc.bmj.com/content/7/1/e000726
    The predictive value of diabetic retinopathy on end-stage kidney disease (ESKD) has not been fully addressed in patients with type 2 diabetes and diabetic kidney disease. […] The diabetic retinopathy progression positively correlated with all scores of renal lesions, especially with the glomerular-based classification (r=0.41), scores of interstitial fibrosis (r=0.41) and diffuse lesion (r=0.48). During a median follow-up of 5.7 years, 114 patients developed ESKD. […] Retinopathy progression appeared to be associated with renal lesions and the development of ESKD. Our findings suggest that diabetic retinopathy and kidney disease share the same magnitude of disease progression, and therefore diabetic retinopathy may be useful for prognosticating the clinical course for diabetic kidney disease.
  • #14 Retinopathy progression and the risk of end-stage kidney disease: results from a longitudinal Japanese cohort of 232 patients with type 2 diabetes and biopsy-proven diabetic kidney disease | BMJ Open Diabetes Research & Care
    https://drc.bmj.com/content/7/1/e000726
    The risk for end-stage kidney disease (ESKD) increased in a stepwise fashion, from mild non-proliferative diabetic retinopathy (NPDR) to moderate NPDR, to severe NPDR, to proliferative diabetic retinopathy, even after adjusting for known risk factors for ESKD. […] Addition of the retinopathy grading to the clinical model alone improved the prognostic value, which is an improvement equivalent to the addition of the renal lesion grading to the clinical model. […] This study demonstrated that diabetic retinopathy was correlated with changes in renal pathology, and a powerful predictor of ESKD, independent of established risk factors for ESKD, in patients with type 2 diabetes and biopsy-proven diabetic kidney disease. […] These findings imply that extensive screening for diabetic retinopathy may be a powerful tool in prognosticating the clinical course for diabetic kidney disease in patients with type 2 diabetes.
  • #15 Risk Prediction and Management of Chronic Kidney Disease in People Living with Type 2 Diabetes Mellitus
    https://e-dmj.org/journal/view.php?number=2801
    People with type 2 diabetes mellitus have increased risk of chronic kidney disease and atherosclerotic cardiovascular disease. […] Given limited resources, better risk stratification approaches to identify people at risk of rapid progression to end-stage kidney disease can reduce therapeutic inertia, facilitate timely interventions and identify the need for early nephrologist referral. […] The kidney failure risk equations (KFRE) have been externally validated and outperformed other risk prediction models. […] The KFRE can also guide the timing of preparation for kidney replacement therapy with improved healthcare resources planning and may prevent multiple complications and premature mortality among people with chronic kidney disease with and without type 2 diabetes mellitus. […] The present review summarizes the evidence of KFRE to date and call for future research to validate and evaluate its impact on cardiovascular and mortality outcomes, as well as healthcare resource utilization in multiethnic populations and different healthcare settings.
  • #16 Risk Prediction and Management of Chronic Kidney Disease in People Living with Type 2 Diabetes Mellitus
    https://e-dmj.org/journal/view.php?number=2801
    Studies have shown that 29% to 38% of people with T2DM develop CKD after a median follow-up of 15 years. […] The estimated incidence of ESKD among people with CKD G3a is 0.3 per 1,000 person-years, while it increases to 4 and 43 per 1,000 person-years in CKD G3b and G4, respectively. […] Accurate prediction of the risk of ESKD is the cornerstone of optimal CKD management. […] The KDIGO CKD classification informs about the risk of progression to ESKD but lacks absolute risk quantification which is essential to facilitate clinical decision-making. […] These challenges call for a better CKD risk prediction model as the rates of CKD progression vary considerably between people with CKD. […] Developing clinical risk scores and prediction models have become increasingly popular. […] Notwithstanding a few notable examples like the kidney failure risk equation (KFRE) developed by Tangri et al., most kidney failure prediction models were neither externally validated nor considered competing risk of death prior to ESKD.
  • #17 Value of adding the renal pathological score to the kidney failure risk equation in advanced diabetic nephropathy | PLOS One
    https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0190930
    However, it has been unclear whether the KFRE performs well in patients who have specific renal diseases associated with a very high risk of ESRD such as diabetic nephropathy. […] Our findings suggest that we may not perform renal biopsies just for anticipating additional prognostic information from renal pathology based on the RPS DN Classification and that alternatively, to improve prediction of renal prognosis for advanced diabetic nephropathy may require different approaches with combining unmeasured clinical and pathological features. […] In conclusion, the kidney failure risk equation was a good instrument for identifying a high risk of progression to ESRD among patients with diabetic nephropathy and advanced CKD. However, its predictive value was weaker than in the miscellaneous CKD cohort originally reported by Tangri et al and adding pathological information based on the Diabetic Nephropathy Classification by the Renal Pathology Society to the KFRE did not significantly improve prediction of ESRD.
  • #18
    https://link.springer.com/article/10.1007/s40620-021-01220-w
    Various prognostic models have been derived to predict chronic kidney disease (CKD) development in type 2 diabetes (T2D). […] This study aimed to externally validate several prognostic models of CKD in a T2D Thai cohort. […] All models showed moderate discrimination and fair calibration. Updating models to include routine clinical factors substantially enhanced their accuracy. […] These models can assist clinicians to improve the risk-stratification of diabetic patients for CKD and/or ESRD in the regions settings are similar to Thailand. […] In conclusion, we have provided an independent external validation of prognostic models for the prediction of incident CKD/ESRD in participants with T2D from Thailand. All evaluated prognostic models showed only moderate discriminative performance, but fair calibration at baseline validation. Updated prognostic scores improved predictive performance in most of the evaluation metrics (i.e., discrimination, calibration, and Brier score). An updated prognostic model for clinical use in Asian populations is provided. […] Although no model was excellent, prognostic equations not delimited by sex (i.e., Lows and Elleys) performed better in our data and may offer clinical utility as a CKD screening tool in primary care for patients with diabetes.
  • #19 Artificial intelligence predicts the progression of diabetic kidney disease using big data machine learning | Scientific Reports
    https://www.nature.com/articles/s41598-019-48263-5
    Artificial intelligence (AI) is expected to support clinical judgement in medicine. We constructed a new predictive model for diabetic kidney diseases (DKD) using AI, processing natural language and longitudinal data with big data machine learning, based on the electronic medical records (EMR) of 64,059 diabetes patients. AI could predict DKD aggravation with 71% accuracy. Furthermore, the group with DKD aggravation had a significantly higher incidence of hemodialysis than the non-aggravation group, over 10 years (N=2,900). The new predictive model by AI could detect progression of DKD and may contribute to more effective and accurate intervention to reduce hemodialysis. […] In this study, we showed that AI could predict the progression of DKD using big data machine learning, according to the EMR of T2DM patients.
  • #20
    https://link.springer.com/article/10.1007/s40200-023-01357-4
    Diabetes is a major public health challenge with widespread prevalence, often leading to complications such as Diabetic Nephropathy (DN)a chronic condition that progressively impairs kidney function. […] Diabetic Nephropathy (DN) is a chronic disease in which the function of the kidneys deteriorates, reducing their ability to eliminate wastes and toxins from the bloodstream and affecting the water balance in the body. DN is considered a progressive disease that usually gets worse over time until the kidneys can no longer function on their own, which is known as end-stage renal disease (ESRD). […] The timely implementation of a DN risk assessment may delay or even prevent its progression, which would certainly reduce the number of people with ESRD. […] The application of ML techniques to analyze EHR data can provide valuable insights and enable the development of ML models that can predict the risk of developing DN or progressing to higher stages, aiding physicians in the diagnosis and ultimately improving the quality of healthcare.
  • #21 Prediction of 3-year risk of diabetic kidney disease using machine learning based on electronic medical records | Journal of Translational Medicine | Full Text
    https://translational-medicine.biomedcentral.com/articles/10.1186/s12967-022-03339-1
    Established prediction models of Diabetic kidney disease (DKD) are limited to the analysis of clinical research data or general population data and do not consider hospital visits. […] The LightGBM model had the highest AUC (0.815, 95% CI 0.7470.882). […] Older patients with T2DM with high homocysteine (Hcy), poor glycemic control, low serum albumin (ALB), low estimated glomerular filtration rate (eGFR), and high bicarbonate had an increased risk of developing DKD over the next 3 years. […] This study constructed a 3-year DKD risk prediction model in patients with T2DM and normo-albuminuria using machine learning and EMR. […] The performance of predictive models generated by seven machine learning algorithms were compared. Findings showed the LightGBM model had the highest AUC, sensitivity, positive predictive, and negative predictive values.
  • #22 Prediction of 3-year risk of diabetic kidney disease using machine learning based on electronic medical records | Journal of Translational Medicine | Full Text
    https://translational-medicine.biomedcentral.com/articles/10.1186/s12967-022-03339-1
    Specifically, older patients with high Hcy, poor glycemic control, low Alb, low eGFR, and high bicarbonate had a high 3-year risk of developing DKD. […] In the study population, the risk of developing DKD over the next 3 years was 49.6%. […] This study identified predictive risk factors for DKD and constructed a 3-year DKD risk prediction model in patients with T2DM and normo-albuminuria using machine learning and clinical variables easily extracted from EMR. […] We established the LightGBM model as a tool with potential to facilitate population management strategies for T2DM care in the EMR era.
  • #23
    https://link.springer.com/article/10.1007/s40200-023-01357-4
    Our analysis showed that some studies ignored the temporal factor, while others partially exploited it. Greater use of the temporal aspect inherent in Electronic Health Records (EHR) data, together with the integration of omics data, could lead to the development of more reliable and powerful predictive models. […] The reviewed literature suggests that despite the potential of using ML techniques to fully exploit the temporal dimension of EHR data to predict the risk of developing or progressing to DN, this has not yet been fully achieved. Many of the techniques used have limited use of the temporal dimension and richness of patient records available in EHR data. […] In summary, all the papers included in this review were generally able to arrive at a workable risk model for the onset or development of DN using a variety of techniques. All of them have attempted, either statically or dynamically, to make partial use of the temporal factor.
  • #24 Development and validation of a predictive model for end-stage renal disease risk in patients with diabetic nephropathy confirmed by renal biopsy [PeerJ]
    https://peerj.com/articles/8499/
    This study was performed to develop and validate a predictive model for the risk of end-stage renal disease (ESRD) inpatients with diabetic nephropathy (DN) confirmed by renal biopsy. […] The outcome was defined as a fatal or nonfatal ESRD event (peritoneal dialysis or hemodialysis for ESRD, renal transplantation, or death due to chronic renal failure or ESRD). […] During the 3-year follow-up period, there were 225 outcome events (47.1%) during follow-up. […] The clinical-pathological model using routinely available clinical measurements was shown to be accurate and validated method for predicting disease progression in patients with DN. […] We therefore aimed to derive and validate a model to predict the 3-year risk of end-stage renal events, including dialysis, renal transplantation, or death from renal failure, among people with DN without advanced kidney disease within a secondary care context to prevent or slow the progression from DN to ESRD.
  • #25 Development and validation of a predictive model for end-stage renal disease risk in patients with diabetic nephropathy confirmed by renal biopsy [PeerJ]
    https://peerj.com/articles/8499/
    The clinical-pathological model showed good performance among the several models. […] Our study demonstrated that lower eGFR, higher cystatin C levels, higher BNP, higher Log ACR level and higher pathological grade significantly increased the risk of ESRD in patients with DN. […] The model incorporating these risk factors can potentially be a simple medical calculator for use in clinical practice. […] We have developed and validated a model to predict the risk of progression to ESRD in patients diagnosed with biopsy-confirmed DN. The clinical-pathological model demonstrated that pathological grade, cystatin C, eGFR, BNP and Log ACR influenced the disease progression from DN to ESRD.
  • #26 A new pathological scoring system by the Japanese classification to predict renal outcome in diabetic nephropathy | PLOS One
    https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0190923
    The impact of the newly proposed pathological classification by the Japan Renal Pathology Society (JRPS) on renal outcome is unclear. So we evaluated that impact and created a new pathological scoring to predict outcome using this classification. […] The J-scores of diffuse lesion classes 2 or 3, GBM doubling class 3, presence of mesangiolysis, polar vasculosis, and arteriolar hyalinosis were, respectively, 1, 2, 4, 1, and 2. […] After adjusting clinical factors, the J-score was a significant predictor of renal outcome. […] Mesangiolysis, polar vasculosis, and doubling of GBMfeatures of the JRPS systemwere significantly associated with renal outcome. Prediction of DN patients renal outcome was better with the J-score than without it. […] Therefore, in addition to clinical factors, the J-score seemed a significant predictor of renal outcome after renal biopsy.
  • #27 A new pathological scoring system by the Japanese classification to predict renal outcome in diabetic nephropathy | PLOS One
    https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0190923
    We evaluated the impact of the pathological changes of DN recently proposed by the JRPS, and discovered the importance of finding mesangiolysis, doubling of GBM, and polar vasculosis on predicting renal outcome. In addition, we created a new pathological DN scoring system to predict patients renal outcome. Based on this J-score system, we could, indeed, predict renal outcome; and we found that if the J-score is 5, the predicted renal outcome is excellent, with the expected renal outcome 18 years. However, if the J-score is 16, the predicted renal outcome is poor, with the expected renal outcome 2 years.
  • #28 Diabetic Nephropathy and CKD—Analysis of Individual Patient Serum Creatinine Trajectories: A Forgotten Diagnostic Methodology for Diabetic CKD Prognostication and Prediction
    https://www.mdpi.com/2077-0383/4/7/1348
    Diabetic nephropathy or diabetic kidney disease is defined by characteristic structural and functional changes, with the predominant structural changes described being mesangial expansion, glomerular basement membrane thickening, and glomerular sclerosis. Functional characteristics include hyperfiltration, microalbuminuria, macroalbuminuria with incipient progressive proteinuria that is then often followed by a slowly progressive decline in glomerular filtration rate (GFR) and, over time, ending inexorably in symptomatic end-stage renal disease (ESRD) requiring renal replacement therapy. […] For unclear reasons, the degree of albuminuria is not necessarily linked to disease progression in patients with diabetic nephropathy associated with either type 1 or type 2 diabetes. […] It must therefore be recognized that diabetic nephropathy is a very heterogenous disease entity. […] The analysis of serum creatinine trajectories, both in real-time and retrospectively, does indeed provide supplementary superior diagnostic and prognostic insights in the management of the nephrology patient.
  • #29 Diabetes and kidney disease Information | Mount Sinai – New York
    https://www.mountsinai.org/health-library/diseases-conditions/diabetes-and-kidney-disease
    Diabetic kidney disease is a major cause of sickness and death in people with diabetes. It can lead to the need for dialysis or a kidney transplant. […] Kidney damage is more likely if you have uncontrolled blood sugar (glucose). […] When kidney damage is caught in its early stages, it can be slowed with treatment. Once larger amounts of protein appear in the urine, kidney damage will slowly get worse. […] Follow your provider’s advice to keep your condition from getting worse.
  • #30 Risk Prediction and Management of Chronic Kidney Disease in People Living with Type 2 Diabetes Mellitus
    https://e-dmj.org/journal/view.php?number=2801
    The KidneyIntelX algorithm has been externally validated in multinational cohorts from HICs with proven clinical utility. […] Nevertheless, there is an emergence of studies investigating the use of machine-learning algorithms to predict the risk of ESKD with good prediction ability. […] Early identification and risk stratification of people who have increased risk of rapid CKD progression will facilitate timely intervention to prevent ESKD and premature mortality. […] While there is robust evidence supporting cardiorenal risk reduction strategies among people with T2DM, the next essential step is to ensure their equitable and affordable access, especially in resource-constrained settings and under-privileged populations. […] Simple and inexpensive risk-based approaches such as KFRE can improve detection, risk stratification, patient empowerment and timely intervention to reduce therapeutic inertia and improve health outcomes.