Understanding patient needs and predicting outcomes in IgA nephropathy using data analytics and artificial intelligence: a narrative review.

This narrative review explores two case scenarios related to immunoglobulin A nephropathy (IgAN) and the application of predictive monitoring, big data analysis and artificial intelligence (AI) in improving treatment outcomes. The first scenario discusses how online service providers accurately understand consumer preferences and needs through the use of AI-powered big data analysis. The author, a clinical nephrologist, contemplates the potential application of similar methodologies, including AI, in his medical practice to better understand and meet patient needs. The second scenario presents a case study of a 20-year-old man with IgAN. The patient exhibited recurring symptoms, including gross haematuria and tonsillitis, over a 2-year period. Through histological examination and treatment with renin-angiotensin system blockade and corticosteroids, the patient experienced significant improvement in kidney function and reduced proteinuria over 15 years of follow-up. The case highlights the importance of individualized treatment strategies and the use of predictive tools, such as AI-based predictive models, in assessing treatment response and predicting long-term outcomes in IgAN patients. The article further discusses the collection and analysis of real-world big data, including electronic health records, for studying disease natural history, predicting treatment responses and identifying prognostic biomarkers. Challenges in integrating data from various sources and issues such as missing data and data processing limitations are also addressed. Mathematical models, including logistic regression and Cox regression analysis, are discussed for predicting clinical outcomes and analysing changes in variables over time. Additionally, the application of machine learning algorithms, including AI techniques, in analysing big data and predicting outcomes in IgAN is explored. In conclusion, the article highlights the potential benefits of leveraging AI-powered big data analysis, predictive monitoring and machine learning algorithms to enhance patient care and improve treatment outcomes in IgAN.

Oleogelation of extra virgin olive oil by different gelators affects lipid digestion and polyphenol bioaccessibility.

The possibility to steer extra virgin olive oil (EVOO) digestion and polyphenol bioaccessibility through oleogelation was investigated. EVOO was converted into oleogels using lipophilic (monoglycerides, rice wax, sunflower wax, phytosterols) or hydrophilic (whey protein aerogel particles, WP) gelators. In-vitro digestion demonstrated that the oleogelator nature influenced both lipid digestion and polyphenol bioaccessibility. WP-based oleogels presented ∼100% free fatty acid release compared to ∼64% for unstructured EVOO and ∼40 to ∼55% for lipophilic-based oleogels. This behavior was attributed to the ability of WP to promote micelle formation through oleogel destructuring. Contrarily, the lower lipolysis of EVOO gelled with lipophilic gelators compared to unstructured EVOO suggested that the gelator obstructed lipase accessibility. Tyrosol and hydroxytyrosol bioaccessibility increased for WP oleogels (∼27%), while liposoluble-based oleogels reduced it by 7 to 13%. These findings highlight the deep effect of the gelator choice on the digestion fate of EVOO components in the human body.

Circulating metabolites improve the prediction of renal impairment in patients with type 2 diabetes.

INTRODUCTION: Low glomerular filtration rate (GFR) is a leading cause of reduced lifespan in type 2 diabetes. Unravelling biomarkers capable to identify high-risk patients can help tackle this burden. We investigated the association between 188 serum metabolites and kidney function in type 2 diabetes and then whether the associated metabolites improve two established clinical models for predicting GFR decline in these patients. RESEARCH DESIGN AND METHODS: Two cohorts comprising 849 individuals with type 2 diabetes (discovery and validation samples) and a follow-up study of 575 patients with estimated GFR (eGFR) decline were analyzed. RESULTS: Ten metabolites were independently associated with low eGFR in the discovery sample, with nine of them being confirmed also in the validation sample (ORs range 1.3-2.4 per 1SD, p values range 1.9×10-2-2.5×10-9). Of these, five metabolites were also associated with eGFR decline (ie, tiglylcarnitine, decadienylcarnitine, total dimethylarginine, decenoylcarnitine and kynurenine) (ß range -0.11 to -0.19, p values range 4.8×10-2 to 3.0×10-3). Indeed, tiglylcarnitine and kynurenine, which captured all the information of the other three markers, improved discrimination and reclassification (all p<0.01) of two clinical prediction models of GFR decline in people with diabetes. CONCLUSIONS: Further studies are needed to validate our findings in larger cohorts of different clinical, environmental and genetic background.

Independent Prognostic and Predictive Role of Interstitial Macrophages in Kidney Biopsies of IgA Nephropathy Patients.

A relevant percentage of IgAN patients experience a progressive decline in kidney function. According to the KDIGO guidelines, proteinuria and eGFR are the only validated prognostic markers. The role of interstitial macrophages in kidney biopsies of IgAN patients and the outcome of patients treated with renin-angiotensin system inhibitors (RASBs) alone or combined with glucocorticoids were evaluated. Clinical and laboratory records (age, gender, hypertension, hematuria, proteinuria, eGFR, serum creatinine, and therapy), MEST-C parameters of the Oxford classification, C4d deposition, peritubular capillaries, and glomerular and interstitial macrophages in 47 IgAN patients undergoing kidney biopsy consecutively between 2003 and 2016 were examined. A high number of interstitial macrophages significantly correlated with peritubular capillary rarefaction and impairment of kidney function. Cox's multivariable regression analysis revealed that a value > 19.5 macrophages/HPF behaved as an independent marker of an unfavorable outcome. Patients exhibiting > 19.5 macrophages/HPF treated at the time of diagnosis with RASBs combined with methylprednisolone had an estimated probability of a favorable outcome higher than patients treated with RASBs alone. Thus, a value > 19.5 macrophages/HPF in IgAN biopsies can predict an unfavorable outcome and endorse a well-timed administration of glucocorticoids. Studies evaluating urine biomarkers associated with peritubular capillary rarefaction in patients with marked macrophage infiltration may help personalized treatment decisions.

Molecular Profiling of Tissue Samples with Chronic Rejection from Patients with Chronic Lung Allograft Dysfunction: A Pilot Study in Cystic Fibrosis Patients.

Chronic rejection (CR) is the main culprit for reduced survival and quality of life in patients undergoing lung transplantation (Ltx). High-throughput approaches have been used to unveil the molecular pathways of CR, mainly in the blood and/or in bronchoalveolar lavage. We hypothesized that a distinct molecular signature characterizes the biopsies of recipients with clinically confirmed histological signs of CR. Eighteen cystic fibrosis patients were included in the study and RNA sequencing was performed in 35 scheduled transbronchial biopsies (TBBs): 5 with acute cellular rejection, 9 with CR, and 13 without any sign of post-LTx complication at the time of biopsy; 8 donor lung samples were used as controls. Three networks with 33, 26, and 36 differentially expressed genes (DEGs) were found in TBBs with CR. Among these, seven genes were common to the identified pathways and possibly linked to CR and five of them (LCN2, CCL11, CX3CL1, CXCL12, MUC4) were confirmed by real-time PCR. Immunohistochemistry was significant for LCN2 and MUC4. This study identified a typical gene expression pattern in TBBs with histological signs of CR and the LCN2 gene appeared to play a central role. Thus, it could be crucial in CR pathophysiology.

Post-hoc analysis of a tool to predict kidney failure in patients with IgA nephropathy.

BACKGROUND: Recently, a tool based on two different artificial neural networks has been developed. The first network predicts kidney failure (KF) development while the second predicts the time frame to reach this outcome. In this study, we conducted a post-hoc analysis to evaluate the discordant results obtained by the tool. METHODS: The tool performance was analyzed in a retrospective cohort of 1116 adult IgAN patients, as were the causes of discordance between the predicted and observed cases of KF. RESULTS: There was discordance between the predicted and observed KF in 216 IgAN patients (19.35%) all of whom were elderly, hypertensive, had high serum creatinine levels, reduced renal function and moderate or severe renal lesions. Many of these patients did not receive therapy or were non-responders to therapy. In other IgAN patients the tool predicted KF but the outcome was not reached because patients responded to therapy. Therefore, in the discordant group (prediction did not match the observed outcome) the proportion of patients having or not having KF was strongly associated with treatment (P < 0.0001). CONCLUSIONS: The post-hoc analysis shows that discordance in a low number of patients is not an error, but rather the effect of positive response to therapy. Thus, the tool could both help physicians to determine the prognosis of the disease and help patients to plan for their future.

Ethical and medical dilemmas in paid living kidney donor transplantation.

Due to the shortage of deceased and genetically- or emotionally-related living donors, living unrelated paid donor (LURpD) kidney transplantation has been considered; however, this practice may result in medical, ethical and social dilemmas, induce organ trading (commodification), and even criminal activities. Commodification also risks undermining public trust in the transplant system and impeding the development of proper altruistic or deceased donor programs by ignoring altruism, volunteerism, and dignity. However, despite many objections by authoritative organizations, black market practices are involved in up to 10% of all transplants worldwide. The authors strongly discourage any payment or rewards for organ donation, and instead urge the governments of all countries to provide adequate and accessible kidney health care. However, it is an undeniable fact that paid-living donor transplantation is increasing despite all objections, disapprovals and regulations. We feel it as our responsibility not to ignore this uncertain and undesirable practice, but rather to underline the necessity for strict rules and prohibitions to minimize unacceptable medical, social and ethical risks as long as it exists. Furthermore, economic profit, be it direct or indirect, must not be the goal of those involved, and the employment of intermediaries must be avoided entirely. Additionally, the donor should be in a position where not donating has no detrimental effect on his/her future in any way (free agency). In our view, every country has the obligation and responsibility to provide adequate kidney health care and to make kidney transplantation accessible to those in need. This provision is key to stop transplant tourism and commercialization of kidney transplantation. The nephrology community has a duty to establish structures that optimize organ availability within strict ethical limits. The legal position of LURpD varies considerably worldwide. Strictly respecting each country's legislation and local values is mandatory to minimize medical and ethical risks and controversies.

Prediction of chronic kidney disease and its progression by artificial intelligence algorithms.

BACKGROUND AND OBJECTIVE: Aim of nephrologists is to delay the outcome and reduce the number of patients undergoing renal failure (RF) by applying prevention protocols and accurately monitoring chronic kidney disease (CKD) patients. General practitioners and nephrologists are involved in the first and in the late stages of the disease, respectively. Early diagnosis of CKD is an important step in preventing the progression of kidney damage. Our aim was to review publications on machine learning algorithms (MLAs) that can predict early CKD and its progression. METHODS: We conducted a systematic review and selected 55 articles on the application of MLAs in CKD. PubMed, Medline, Scopus, Web of Science and IEEE Xplore Digital Library of the Institute of Electrical and Electronics Engineers were searched. The search terms were chronic kidney disease, artificial intelligence, data mining and machine learning algorithms. RESULTS: MLAs use enormous numbers of predictors combining them in non-linear and highly interactive ways. This ability increases when new data is added. We observed some limitations in the publications: (i) databases were not accurately reviewed by physicians; (ii) databases did not report the ethnicity of the patients; (iii) some databases collected variables that were not important for the diagnosis and progression of CKD; (iv) no information was presented on the native kidney disease causing CKD; (v) no validation of the results in external independent cohorts was provided; and (vi) no insights were given on the MLAs that were used. Overall, there was limited collaboration among experts in electronics, computer science and physicians. CONCLUSIONS: The application of MLAs in kidney diseases may enhance the ability of clinicians to predict CKD and RF, thus improving diagnostic assistance and providing suitable therapeutic decisions. However, it is necessary to improve the development process of MLA tools.

[The origins of the Renal Immunopathology Group of the Italian Society of Nephrology].

This article describes the birth and development of the Renal Immunopathology Group of the Italian Society of Nephrology. It collects the stories of nephrologists and pathologists who, since the early Seventies up to the first decade of this century, devoted their professional lives to the study of renal pathology with a strong personal involvement, characterized by enthusiasm, commitment, ability, strong spirit of cooperation, and friendship. All this enabled the Group to: propose the criteria for a standardized histological and immuno-histological examination of renal biopsies and reporting; produce several multicenter studies, whose results were also published in important international journals; to set up a national registry of renal biopsies; to organize a number of courses, some of which were associated with the publication of monographs, on various renal diseases. This article also traces the history of renal pathology in Italy from the second half of the Sixties - when young Italian nephrologists and pathologists from different institutions moved to French laboratories to learn new techniques to apply to renal biopsies - up to the present days. It also shows us how Italian renal pathology has been an essential tool for the development of the nephrological clinical practice and the advancement of scientific research.

Oleogelation of extra virgin olive oil by different oleogelators affects the physical properties and the stability of bioactive compounds.

Extra virgin olive oil (EVOO) was gelled with 10% monoglycerides, (MG), rice wax (RW), γ-oryzanol, and ß-sitosterol (PS), or ethylcellulose (EC). The oleogel structure and the stability of bioactive compounds were investigated during storage up to 120 days at 20, 30, and 40 °C. All samples were self-standing but presented different structures. PS produced the firmest gel, whereas EC caused the lowest firmness and rheological values. Structural properties did not change during storage, except for EC oleogel. Structuring triggered a depletion in phenolic content and α-tocopherol, which was more pronounced when a higher temperature was required for oleogel preparation (MG ~ RW < PS < EC). However, during storage phenolics and α-tocopherol decreased following zero-order kinetics with a higher susceptibility in unstructured oil, suggesting in all cases a protective effect of the gel network.

The molecular mechanisms of inflammation and scarring in the kidneys of immunoglobulin A nephropathy : Gene involvement in the mechanisms of inflammation and scarring in kidney biopsy of IgAN patients.

Kidney biopsy is the cornerstone for the diagnosis of immunoglobulin A nephropathy (IgAN). The immunofluorescence technique evidences the IgA deposits in the glomeruli; the routine histology shows degree of active and chronic renal lesions. The spectrum of renal lesions is highly variable, ranging from minor or no detectable lesions to diffuse proliferative or crescentic lesions. Over the past three decades, renal transcriptomic studies have been performed on fresh or frozen renal tissue, and formalin-fixed paraffin-embedded kidney tissue specimens obtained from archival histological repositories. This paper aims to describe (1) the transcriptomic profiles of the kidney biopsy and (2) the potential urinary biomarkers that can be used to monitor the follow-up of IgAN patients. The use of quantitative Real-Time Polymerase Chain Reaction (qRT-PCR), microarrays and RNA-sequencing (RNA-seq) techniques on renal tissue and separated compartments of the nephron such as glomeruli and tubule-interstitium has clarified many aspects of the renal damage in IgAN. Recently, the introduction of the single-cell RNA-seq techniques has overcome the limitations of the previous methods, making that it is possible to study the whole renal tissue without the dissection of the nephron segments; it also allows better analysis of the cell-specific gene expression involved in cell differentiation. These gene products could represent effective candidates for urinary biomarkers for clinical decision making. Finally, some of these molecules may be the targets of old drugs, such as corticosteroids, renin-angiotensin-aldosterone blockers, and new drugs such as monoclonal antibodies. In the era of personalized medicine and precision therapy, high-throughput technologies may better characterize different renal patterns of IgAN and deliver targeted treatments to individual patients.

Determination of hydroxytyrosol and tyrosol in human urine after intake of extra virgin olive oil produced with an ultrasounds-based technology.

Extra virgin olive oil (EVOO) is a known source of antioxidants, such as phenolic compounds, useful in the prevention of non-infectious diseases (atherosclerosis, diabetes, cancer, and other diseases). In the present study, EVOO obtained using an innovative ultrasounds-based technology was found richer in total polyphenols, hydroxytyrosol and tyrosol, than EVOO obtained using a conventional mechanical technology. The urinary excretion in humans of hydroxytyrosol and tyrosol, after the administration of ultrasounds and mechanical EVOOs, respectively, was assessed and compared. The analytes were determined in urine samples, collected for 24 h, of six healthy people (3 men and 3 women, age 22-70 years and body mass index <30 kg/m2) who ingested 20 g of oil for six consecutive days. A commercial refined olive oil was also used in the study to determine the baseline excretion levels of the two metabolites. High correlation coefficients (≥0.9311) were found between the amounts of the analytes ingested daily with EVOOs and those determined in the 24-h urines. The results clearly indicated that the EVOO obtained with the ultrasound process was characterized by the highest concentration of biophenols which were consequently available in greater quantities after ingestion, indicating that it represents a high-quality product containing high levels of beneficial compounds such as biophenols readily assimilable by the human body.

Development and testing of an artificial intelligence tool for predicting end-stage kidney disease in patients with immunoglobulin A nephropathy.

We have developed an artificial neural network prediction model for end-stage kidney disease (ESKD) in patients with primary immunoglobulin A nephropathy (IgAN) using a retrospective cohort of 948 patients with IgAN. Our tool is based on a two-step procedure of a classifier model that predicts ESKD, and a regression model that predicts development of ESKD over time. The classifier model showed a performance value of 0.82 (area under the receiver operating characteristic curve) in patients with a follow-up of five years, which improved to 0.89 at the ten-year follow-up. Both models had a higher recall rate, which indicated the practicality of the tool. The regression model showed a mean absolute error of 1.78 years and a root mean square error of 2.15 years. Testing in an independent cohort of 167patients with IgAN found successful results for 91% of the patients. Comparison of our system with other mathematical models showed the highest discriminant Harrell C index at five- and ten-years follow-up (81% and 86%, respectively), paralleling the lowest Akaike information criterion values (355.01 and 269.56, respectively). Moreover, our system was the best calibrated model indicating that the predicted and observed outcome probabilities did not significantly differ. Finally, the dynamic discrimination indexes of our artificial neural network, expressed as the weighted average of time-dependent areas under the curve calculated at one and two years, were 0.80 and 0.79, respectively. Similar results were observed over a 25-year follow-up period. Thus, our tool identified individuals who were at a high risk of developing ESKD due to IgAN and predicted the time-to-event endpoint. Accurate prediction is an important step toward introduction of a therapeutic strategy for improving clinical outcomes.

Formalin-fixed paraffin-embedded renal biopsy tissues: an underexploited biospecimen resource for gene expression profiling in IgA nephropathy.

Primary IgA nephropathy (IgAN) diagnosis is based on IgA-dominant glomerular deposits and histological scoring is done on formalin-fixed paraffin embedded tissue (FFPE) sections using the Oxford classification. Our aim was to use this underexploited resource to extract RNA and identify genes that characterize active (endocapillary-extracapillary proliferations) and chronic (tubulo-interstitial) renal lesions in total renal cortex. RNA was extracted from archival FFPE renal biopsies of 52 IgAN patients, 22 non-IgAN and normal renal tissue of 7 kidney living donors (KLD) as controls. Genome-wide gene expression profiles were obtained and biomarker identification was carried out comparing gene expression signatures a subset of IgAN patients with active (N = 8), and chronic (N = 12) renal lesions versus non-IgAN and KLD. Bioinformatic analysis identified transcripts for active (DEFA4, TNFAIP6, FAR2) and chronic (LTB, CXCL6, ITGAX) renal lesions that were validated by RT-PCR and IHC. Finally, two of them (TNFAIP6 for active and CXCL6 for chronic) were confirmed in the urine of an independent cohort of IgAN patients compared with non-IgAN patients and controls. We have integrated transcriptomics with histomorphological scores, identified specific gene expression changes using the invaluable repository of archival renal biopsies and discovered two urinary biomarkers that may be used for specific clinical decision making.

Immunosuppressive agents for treating IgA nephropathy.

BACKGROUND: IgA nephropathy is the most common glomerulonephritis world-wide. IgA nephropathy causes end-stage kidney disease (ESKD) in 15% to 20% of affected patients within 10 years and in 30% to 40% of patients within 20 years from the onset of disease. This is an update of a Cochrane review first published in 2003 and updated in 2015. OBJECTIVES: To determine the benefits and harms of immunosuppression strategies for the treatment of IgA nephropathy. SEARCH METHODS: We searched the Cochrane Kidney and Transplant Register of Studies up to 9 September 2019 through contact with the Information Specialist using search terms relevant to this review. Studies in the Register are identified through searches of CENTRAL, MEDLINE, and EMBASE, conference proceedings, the International Clinical Trials Register (ICTRP) Search Portal and ClinicalTrials.gov. SELECTION CRITERIA: We included randomised controlled trials (RCTs) and quasi-RCTs of treatment for IgA nephropathy in adults and children and that compared immunosuppressive agents with placebo, no treatment, or other immunosuppressive or non-immunosuppressive agents. DATA COLLECTION AND ANALYSIS: Two authors independently assessed study risk of bias and extracted data. Estimates of treatment effect were summarised using random effects meta-analysis. Treatment effects were expressed as relative risk (RR) and 95% confidence intervals (95% CI) for dichotomous outcomes and mean difference (MD) and 95% CI for continuous outcomes. Risks of bias were assessed using the Cochrane tool. Evidence certainty was evaluated using GRADE methodology. MAIN RESULTS: Fifty-eight studies involving 3933 randomised participants were included. Six studies involving children were eligible. Disease characteristics (kidney function and level of proteinuria) were heterogeneous across studies. Studies evaluating steroid therapy generally included patients with protein excretion of 1 g/day or more. Risk of bias within the included studies was generally high or unclear for many of the assessed methodological domains. In patients with IgA nephropathy and proteinuria > 1 g/day, steroid therapy given for generally two to four months with a tapering course probably prevents the progression to ESKD compared to placebo or standard care (8 studies; 741 participants: RR 0.39, 95% CI 0.23 to 0.65; moderate certainty evidence). Steroid therapy may induce complete remission (4 studies, 305 participants: RR 1.76, 95% CI 1.03 to 3.01; low certainty evidence), prevent doubling of serum creatinine (SCr) (7 studies, 404 participants: RR 0.43, 95% CI 0.29 to 0.65; low certainty evidence), and may lower urinary protein excretion (10 studies, 705 participants: MD -0.58 g/24 h, 95% CI -0.84 to -0.33;low certainty evidence). Steroid therapy had uncertain effects on glomerular filtration rate (GFR), death, infection and malignancy. The risk of adverse events with steroid therapy was uncertain due to heterogeneity in the type of steroid treatment used and the rarity of events. Cytotoxic agents (azathioprine (AZA) or cyclophosphamide (CPA) alone or with concomitant steroid therapy had uncertain effects on ESKD (7 studies, 463 participants: RR 0.63, 95% CI 0.33 to 1.20; low certainty evidence), complete remission (5 studies; 381 participants: RR 1.47, 95% CI 0.94 to 2.30; very low certainty evidence), GFR (any measure), and protein excretion. Doubling of serum creatinine was not reported. Mycophenolate mofetil (MMF) had uncertain effects on the progression to ESKD, complete remission, doubling of SCr, GFR, protein excretion, infection, and malignancy. Death was not reported. Calcineurin inhibitors compared with placebo or standard care had uncertain effects on complete remission, SCr, GFR, protein excretion, infection, and malignancy. ESKD and death were not reported. Mizoribine administered with renin-angiotensin system inhibitor treatment had uncertain effects on progression to ESKD, complete remission, GFR, protein excretion, infection, and malignancy. Death and SCr were not reported. Leflunomide followed by a tapering course with oral prednisone compared to prednisone had uncertain effects on the progression to ESKD, complete remission, doubling of SCr, GFR, protein excretion, and infection. Death and malignancy were not reported. Effects of other immunosuppressive regimens (including steroid plus non-immunosuppressive agents or mTOR inhibitors) were inconclusive primarily due to insufficient data from the individual studies in low or very low certainty evidence. The effects of treatments on death, malignancy, reduction in GFR at least of 25% and adverse events were very uncertain. Subgroup analyses to determine the impact of specific patient characteristics such as ethnicity or disease severity on treatment effectiveness were not possible. AUTHORS' CONCLUSIONS: In moderate certainty evidence, corticosteroid therapy probably prevents decline in GFR or doubling of SCr in adults and children with IgA nephropathy and proteinuria. Evidence for treatment effects of immunosuppressive agents on death, infection, and malignancy is generally sparse or low-quality. Steroid therapy has uncertain adverse effects due to a paucity of studies. Available studies are few, small, have high risk of bias and generally do not systematically identify treatment-related harms. Subgroup analyses to identify specific patient characteristics that might predict better response to therapy were not possible due to a lack of studies. There is no evidence that other immunosuppressive agents including CPA, AZA, or MMF improve clinical outcomes in IgA nephropathy.