Machine learning, as a crucial branch of artificial intelligence, has demonstrated tremendous potential in the research and clinical work of kidney diseases. Machine learning can be utilized to analyze clinical, pathological, medical imaging, and multi-omics data related to kidney diseases, facilitating early diagnosis, efficacy prediction, exploration of pathogenesis, and other related research. Machine learning can be used to construct corresponding models based on different types of kidney disease databases, thereby playing a significant role in risk factor analysis, disease diagnosis, and drug efficacy prediction of kidney diseases. This article provided a comprehensive review of the role of machine learning in nephrology, offering a fresh perspective for the research, diagnosis, and treatment of kidney diseases.
To investigate the effects of normal and injured microenvironments derived from renal tubular epithelial cell line TCMK-1 cells on the proliferation, migration, and differentiation of metanephric mesenchymal cells (MMCs), and to identify the signaling pathways involved.
Methods
The normal microenvironment supernatant was prepared using the TCMK-1 cells, while the injured microenvironment supernatant was generated by treating TCMK-1 cells with 5 μg/mL cisplatin. The epithelial induction medium was prepared by using 50 ng/ml basic fibroblast growth factor and 10 ng/ml transforming growth factor α. In the proliferation experiment, the MMCs were divided into control group (regular culture medium), normal microenvironment group, and injured microenvironment group. Cell proliferation was detected by the cell counting kit-8 method. In the migration experiment, the MMCs were divided into control group, cisplatin group (regular culture medium+ 5 μg/ml cisplatin), normal microenvironment group, and injured microenvironment group. The cell migration ability was assessed by means of the transwell chamber assay. In the differentiation experiment, the MMCs were divided into control group, epithelial induction group (epithelial induction medium), epithelial induction plus normal microenvironment group, and epithelial induction plus injured microenvironment group. After 10 days of culture, Western blotting was used to detect the protein expression of E-cadherin, mesenchymal marker α-smooth muscle actin, and renal tubular epithelial-specific marker aquaporin 2. In the pathway verification experiment, Western blotting was used to detect the expression levels of canonical wingless/integrated (Wnt) pathway proteins, including Wnt3A, β-catenin, and T-cell factor 4. The small molecule inhibitor MSAB of the canonical Wnt pathway was added to assess its effect on epithelial differentiation.
Results
Compared with the control group, the proliferative activity of MMCs was inhibited in both the normal microenvironment group and the injured microenvironment group (both P<0.05), while the migration ability of the two groups increased (both P<0.01). Compared with the control group and the epithelial induction group, the expression of E-cadherin in the MMCs of both the normal microenvironment group and the injured microenvironment group increased, while the expression of α-smooth muscle actin decreased. Additionally, the expression of aquaporin 2 in the injured microenvironment group also increased. The expression of canonical Wnt pathway-related proteins as Wnt3A, β-catenin, and T-cell factor 4 was higher in the injured microenvironment group (all P<0.05), and the addition of MSAB could inhibit the effect of the injured microenvironment in promoting the epithelial differentiation of MMCs (P<0.05).
Conclusion
Both the normal and injured microenvironments of the renal tubular epithelial cells slightly inhibited the proliferation of the MMCs, but promoted their migration. The injured microenvironment of the renal tubular epithelial cells activated the canonical Wnt pathway and promoted the differentiation of MMCs into renal tubular epithelial cells.
To analyze the clinical characteristics and prognostic factors of patients with end-stage renal disease (ESRD) complicated with sepsis in the intensive care unit (ICU).
Methods
A retrospective analysis was conducted on ICU patients with ESRD complicated with sepsis form 2008 to 2022 of the medical information mart for intensive care IV (MIMIC-IV, v3.0) database. Data on demographic characteristics, vital signs, laboratory indicators, comorbidities, hospital-based diagnostic and therapeutic procedures, disease severity scores, and endpoint indicators were collected. The patients were divided into the survival group and non-survival group based on their 30-day survival status after ICU admission. The clinical characteristics of the two groups of patients were compared, and a multi-factor logistic regression analysis was used to screen for risk factors affecting patient survival within one month after ICU admission. A regression model was constructed, and a receiver operating characteristic (ROC) curve was plotted to explore its predictive effect on prognosis.
Results
A total of 1, 214 patients were included, and 318 died within one month after admission to the ICU, with a mortality rate of 26.2%. Compared to the survival group, patients in the non-survival group had significantly older age, higher heart and respiratory rates, lower mean arterial pressure, and elevated scores in the simplified acute physiology score Ⅱ (SAPS Ⅱ), sequential organ failure assessment (SOFA), and Oxford acute severity of illness score (OASIS) (all P<0.05). Multivariate logistic analysis revealed that older age, higher levels of red blood cell distribution width, lactic acid, Charlson comorbidity index, and SOFA score, as well as complication with cerebrovascular disease were independent risk factors for the patients mortality, while higher base excess and dialysis acted as protective factors. The prediction model achieved an area under the ROC curve of 0.79, with a sensitivity of 0.69 and a specificity of 0.76, significantly outperforming the predictive performance of SOFA, SAPS Ⅱ, or OASIS alone.
Conclusion
During the ICU stay of the patients with ESRD complicated with sepsis, clinicians should monitor changes in red cell distribution width, lactate, base excess, Charlson comorbidity index, and SOFA, ensure adequate dialysis, and actively prevent complications such as cerebrovascular disease.
To explore the effect of combined therapy of sevelamer carbonate with cinacalcet on hyperphosphatemia and blood pressure variation in maintenance hemodialysis (MHD) patients.
Methods
A retrospective study was conducted to analyze the clinical data of 82 patients with MHD complicated with hyperphosphatemia admitted to our hospital from January 2022 to December 2023. According to the treatment method, they were divided into a single group and a combination group, with 41 patients in each group. The single group was treated with sevelamer carbonate, while the combination group was treated with sevelamer carbonate plus cinacalcet. Both groups were treated for 3 months. Calcium and phosphorus metabolism indexes, blood pressure variation, renal function, and microinflammation status of the patients before and after treatment were compared, and the occurrence of adverse reactions was also compared between the two groups.
Results
After the 3 months treatment, serum calcium levels of the two groups increased, and the serum calcium level of the combination group was also higher than that of the single group (all P<0.05). The levels of blood phosphorus, intact parathyroid hormone, systolic blood pressure variability, diastolic blood pressure variability, blood urea nitrogen, serum creatinine, β2-microglobulin, high-sensitivity C-reactive protein, tumor necrosis factor-α, and interleukin-6 in both groups decreased after the treatment, and the above indexes were also lower in the combination group than in the single group (P<0.05). There was no significant difference in the total incidence of adverse reactions between the two groups (P>0.05).
Conclusion
The combined therapy of sevelamer carbonate with cinacalcet could increase blood calcium, reduce blood phosphorus and intact parathyroid hormone, and improve blood pressure variability in the MHD patients complicated with hyperphosphatemia.
IgA nephropathy is an autoimmune kidney disease characterized by glomerular deposition of galactose-deficient IgA1. Its pathogenesis is primarily attributed to the "multi-hit hypothesis", encompassing mucosal immune abnormalities, formation of immune complexes, complement activation, and renal fibrosis. Recent studies have demonstrated that in the pathogenesis of IgA nephropathy, hyperactivation of the mammalian target of rapamycin (mTOR) signaling pathway could promote mesangial cell proliferation, suppressing autophagy, and exacerbating fibrosis. This article reviewed the progress in the study of the role of mTOR signaling pathway in the pathogenesis of IgA nephropathy, and explored its potential as a therapeutic target of IgA nephropathy.
IgA nephropathy (IgAN) is the most common primary glomerular disease worldwide, with 20% to 40% of IgAN patients eventually progressing to end-stage renal disease. There is currently no specific drug for IgAN treatment, and its clinical treatment is based on renin-angiotensin aldosterone system inhibitors, with the addition of corticosteroid steroids and immunosuppressants if necessary. Research has confirmed that the alternative pathway for complement activation is the most common complement activation pathway in IgAN, and complement factor H and its related proteins are important regulatory proteins of the pathway. With the continuous deepening of research, more and more scholars have begun to pay attention to the role of complement H factor in the pathogenesis of IgAN. This article systematically reviewed the role of complement H factor and its related proteins in IgAN, providing reference for exploring biomarkers for IgAN diagnosis and prognosis, and developing targeted drugs such as complement inhibitors.
Diabetic kidney disease (DKD), the most common and severe complication of diabetes, represents a leading global cause of chronic kidney disease (CKD) and the foremost etiology of end-stage renal disease (ESRD). This condition imposes substantial disease burdens on patients, families, and healthcare systems worldwide. The development of risk prediction models to identify high-risk individuals for DKD at an early stage, coupled with personalized diagnostic and therapeutic strategies, holds critical importance for reducing the incidence and progression of DKD. Over the past several decades, numerous scholars have constructed predictive models for early DKD occurrence. With the advancement of big data and artificial intelligence, building predictive models through machine learning and deep learning algorithms has become a research hotspot. This article provided an overview of the methods for constructing risk models for the early occurrence of DKD, compared the advantages and disadvantages of traditional prediction methods, machine learning, and deep learning algorithms, and summarized the current research status of risk prediction models for the early occurrence of DKD, aiming to provide a reference for the construction of prediction models and early clinical intervention of DKD.
To analyze the teaching of mouse kidney transparent fluorescent specimen preparation and light-sheet fluorescence microscopy imaging skills.
Methods
The participants included 2 doctoral students and 2 other scientific researchers, and the training instructor was a senior renal biological imaging technician. The training lasted for 31 days. At different time points during the training, the success rate of fluorescent antibody injection in mice, preoperative mortality rate, cardiac perfusion bleeding rate, success rate of kidney sampling, kidney transparency degree, and kidney fluorescence imaging effect were evaluated and statistically analyzed.
Results
Compared with those of the first day of training, the success rates of fluorescent antibody injection and kidney harvesting were higher on the fifth day of training, while the preoperative mortality rate of mice and the bleeding rate during cardiac perfusion were lower (all P<0.01). On the 10th, 20th, and 30th days of training, the transparency of the kidneys gradually improved. And on the 30th day, the transparency of the mouse kidneys met the standard. On the 31st day of training, the imaging effect of the light-sheet fluorescence microscopy for the participating students also met the standard.
Conclusion
A 31-day analytical teaching program covering 8 experimental operation skills and 5 teaching essentials enabled the trainees to master the preparation of transparent fluorescent specimens of mouse kidneys and the imaging skills of light-sheet fluorescence microscopy.
To explore the effect of mind mapping combined with case-based learning (CBL) method in clinical teaching of nephrology.
Methods
A total of 50 residents and graduate students who participated in standardized training in the Department of Internal Medicine of the First Medical Center of the Chinese PLA General Hospital from October 2021 to October 2023 were selected as the study subjects and randomly divided into two groups, a test group (mind mapping+ CBL, n=25) and a control group (traditional teaching method, n=25). The test group was taught with mind mapping combined with CBL employing a "symptoms - examination - diagnosis - treatment" closed-loop training approach, while the control group were taught with the traditional teaching method. The theoretical and practical skill scores as well as teaching satisfaction were compared between the two groups.
Results
The test group achieved significantly higher theoretical scores (92.60±3.27 vs 90.08±2.86, P=0.006) and practical skill scores (89.44±2.77 vs 87.12±4.04, P=0.022) than the control group. The teaching satisfaction survey also showed that the test group had higher ratings for clarity of teaching objectives [8.00 (7.00-8.00] vs. 7.00 (6.00-7.00), P=0.005), practicality of teaching methods [8.00 (8.00-9.00] vs. 7.00 (6.00-8.00], P=0.002), and total satisfaction score (30.48±3.00 vs. 27.84±3.84, P=0.009) than the control group.
Conclusion
Compared with traditional teaching method, the mind mapping combined with CBL in clinical teaching of nephrology effectively enhanced the learners′ learning outcomes in both theoretical knowledge and practical skills of nephrology.