Baseline Serum Cystatin C Is a Potential Predictor for Acute Kidney Injury in Patients with Acute Pancreatitis

Automated machine learning for early prediction of acute kidney injury in acute pancreatitis

BACKGROUND

Acute kidney injury (AKI) represents a frequent and grave complication associated with acute pancreatitis (AP), substantially elevating both mortality rates and the financial burden of hospitalization. The aim of our study is to construct a predictive model utilizing automated machine learning (AutoML) algorithms for the early prediction of AKI in patients with AP.

METHODS

We retrospectively analyzed patients who were diagnosed with AP in our hospital from January 2017 to December 2021. These patients were randomly allocated into a training set and a validation set at a ratio of 7:3. To develop predictive models for each set, we employed the least absolute shrinkage and selection operator (LASSO) algorithm along with AutoML. A nomogram was developed based on multivariate logistic regression analysis outcomes. The model's efficacy was assessed using receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA). Additionally, the performance of the model constructed via AutoML was evaluated using decision curve analysis (DCA), feature importance, SHapley Additive exPlanations (SHAP) plots, and locally interpretable model-agnostic explanations (LIME).

RESULTS

This study incorporated a total of 437 patients who met the inclusion criteria. Out of these, 313 were assigned to the training cohort and 124 to the validation cohort. In the training and validation cohorts, AKI occurred in 68 (21.7%) and 29(23.4%) patients, respectively. Comparative analysis revealed that the AutoML models exhibited enhanced performance over traditional logistic regression (LR). Furthermore, the deep learning (DL) model demonstrated superior predictive accuracy, evidenced by an area under the ROC curve of 0.963 in the training set and 0.830 in the validation set, surpassing other comparative models. The key variables identified as significant in the DL model within the training dataset included creatinine (Cr), urea (Urea), international normalized ratio (INR), etiology, smoking, alanine aminotransferase (ALT), hypertension, prothrombin time (PT), lactate dehydrogenase (LDH), and diabetes.

CONCLUSION

The AutoML model, utilizing DL algorithm, offers considerable clinical significance in the early detection of AKI among patients with AP.

Serum Cys C predicts acute kidney injury in patients with acute pancreatitis: A retrospective study

BACKGROUND AND STUDY AIMS

We investigated the value of the serum cystatin C level as a potential predictor of acute kidney injury (AKI) in patients with acute pancreatitis (AP).

PATIENTS AND METHODS

We retrospectively examined patients diagnosed with AP between January 2013 and December 2018. Patients were categorized into two groups based on their serum cystatin C levels after admission: the normal (n-Cys C group) and high serum cystatin C levels groups (h-Cys C group). Patients in the h-Cys C group demonstrated serum cystatin C levels ≥1.05 mg/L. Demographic parameters, laboratory data, and AP severity were compared between the two groups. Receiver operating curve (ROC) analysis was used to evaluate the efficacy of serum cystatin C in predicting persistent AKI.

RESULTS

A total of 379 patients with AP were enrolled: 319 in the n-Cys C group and 60 in the h-Cys C group. Serum cystatin C levels were significantly higher in patients with severe acute pancreatitis (SAP) compared to moderate acute pancreatitis (MAP) (P< 0.05). The h-Cys C group had a higher BISAP score (P < 0.001). Incidences of organ failure and SAP were significantly higher in the h-Cys C group (P < 0.05). ROC analysis indicated that a serum cystatin C cutoff point of 1.055 mg/L optimally predicted persistent AKI (AUC = 0.711). For internal validation, we selected 545 AP patients, treated at our center from 2019 to 2022, including 54 AKI patients. ROC analysis in this validation group yielded a sensitivity of 100% and specificity of 90.9% (AUC = 0.916, 95% CI: 0.894-0.937).

CONCLUSION

Elevated serum cystatin C levels are sensitive indicators of adverse AKI prognosis in AP patients. The cystatin C level at admission can reflect a patient's initial renal function status.

Baseline Serum Estradiol Level Is Associated with Acute Kidney Injury in Patients with Moderately Severe and Severe Acute Pancreatitis

Background. Sexual dimorphism with critical diseases has been documented. However, the role of serum sex hormones for the presence of acute kidney injury (AKI) in moderately or severe acute pancreatitis (MSAP and SAP) patients remains controversial. Here we set out to evaluate whether early (first 48 h) serum estradiol level is associated with AKI in patients with MSAP and SAP. Patients and Methods. We retrospectively collected data from patients with preliminary diagnosis of MSAP and SAP from the Affiliated Hospital of Yangzhou University between January 2014 and June 2018. Serum sex hormones were extracted for further assessment within first 48 h following admission. Logistic regression analysis and the receiving operating characteristic (ROC) curve were applied to evaluate the association and correlation between serum sex hormones and AKI. Results. Data from a total of 122 patients with MSAP or SAP were enrolled in this study. There were no differences in the incidence of AKI between males and females. However, comparing with patients without AKI, those with AKI saw higher estradiol level ( $p\le 0.01$ ) and slight higher progesterone level ( $p=0.014$ ) but similar testosterone level ( $p=0.668$ ). Interestingly, during both the manual selection and the stepwise backward logistic regression analysis, serum estradiol level was independently associated with AKI in patients with MSAP and SAP (OR 4.699, CI 1.783-12.386, and $p=0.002$ ). Additionally, area under the curve of ROC (AUCROC) showed that serum estradiol level was a proper predictor for AKI (area under the curve 0.875). Specifically, the serum estradiol level of 223.15 pg/mL demonstrated a 92.3% sensitive and a 79.3% specificity in predicting AKI of MSAP and SAP patients, respectively. Conclusions. High baseline serum estradiol level appears to be an independent risk factor for AKI in patients with MSAP and SAP. It also tends to be an appropriate indicator for AKI.

Serum magnesium level as a predictor of acute kidney injury in patients with acute pancreatitis

BACKGROUND

Decreased serum magnesium (Mg²⁺) is commonly seen in critically ill patients. Hypomagnesemia is significantly more frequent in patients with severe acute pancreatitis. Acute kidney injury (AKI) in patients with acute pancreatitis (AP) is associated with an extremely high mortality. The association underlying serum Mg²⁺ and AKI in AP has not been elucidated.

AIM

To explore the association between serum Mg²⁺ on admission and AKI in patients with AP.

METHODS

A retrospective observational study was conducted in a cohort of patients (n = 233) with AP without any renal injury before admission to our center from August 2015 to February 2019. Demographic characteristics on admission, severity score, laboratory values and in-hospital mortality were compared between patients with and without AKI.

RESULTS

A total of 233 patients were included for analysis, including 85 with AKI. Compared to patients without AKI, serum Mg²⁺ level was significantly lower in patients with AKI at admission [OR = 6.070, 95%CI: 3.374-10.921, P < 0.001]. Multivariate logistic analysis showed that lower serum Mg²⁺ was an independent risk factor for AKI [OR = 8.47, 95%CI: 3.02-23.72, P < 0.001].

CONCLUSION

Our analysis indicates that serum Mg²⁺ level at admission is independently associated with the development of AKI in patients with AP and may be a potential prognostic factor.

The Systemic Immune-Inflammation Index May Be a Novel and Strong Marker for the Accurate Early Prediction of Acute Kidney Injury in Severe Acute Pancreatitis Patients

OBJECTIVE

This research was performed to investigate the correlation between acute kidney injury (AKI) and systemic immune-inflammation index (SII) in severe acute pancreatitis (SAP) patients.

METHODS

The study included 218 SAP patients from Chongqing Jiangjin Center Hospital during January 2016 to October 2020. The SII was defined as platelet × neutrophil/lymphocyte ratio. After univariate analysis, logistic regression analysis was used for analyzing independent risk factors of AKI in SAP patients. Receiver operating characteristic (ROC) curve was used for analyzing the prognostic value of the SII.

RESULTS

AKI occurred in 74 cases and its incidence rate was 33.9%. The median SII value of AKI patients was higher than that of patients without AKI. After multivariate analysis, SII, age, triglyceride (TG), neutrophil ratio (NEU-R), C-reactive protein (CRP), aspartate aminotransferase (AST), and serum albumin (ALB) were independent predictors of AKI. Serum ALB was an independent protective factor. The optimum threshold truncation value of SII was 2880.1*10^9/L. Compared with other inflammatory factors, SII had a better prediction efficiency.

CONCLUSION

The SII, TG, NEU-R, CRP, and ALB were significant independent predictors of AKI in SAP patients. Serum TG, NEU-R, CRP, and SII were risk factors. Serum ALB was a protective factor. The SII may be a novel, simple, and strong marker for the accurate early prediction of AKI in SAP patients.

MIF inhibitor ISO-1 alleviates severe acute pancreatitis-associated acute kidney injury by suppressing the NLRP3 inflammasome signaling pathway

BACKGROUND

Acute kidney injury (AKI) is an important complication of severe acute pancreatitis (SAP) with a poor prognosis. The methyl ester of (S,R)-3-(4-hydroxyphenyl)-4,5-dihydro-5-isoxazole acetic acid (ISO-1), an inhibitor of macrophage migration inhibitory factor (MIF), has protective effects against many diseases. Our previous study confirmed MIF inhibition alleviated SAP. Here, we explored the effects of ISO-1 in an experimental mouse model of SAP-associated AKI induced by l-arginine.

METHODS

Mice were randomly divided into four treatment groups (n = 6 each): control (CON), SAP, SAP + ISO-1, and ISO-1. Histopathologic examination was used to observe damage in pancreatic and renal tissues. Biochemical and enzyme-linked immunosorbent assays (ELISA) kits were used to measure the serologic indicators amylase, lipase, creatinine, uric acid, interleukin (IL)-6, and tumor necrosis factor (TNF)-α. Immunohistochemistry was used to detect protein expression of NLRP3, ASC and caspase-1, and the infiltration of myeloperoxidase (MPO)-positive neutrophils in kidney tissue. Western blotting was used to detect NLRP3, ASC and caspase-1 and IL-1β protein expression, and real-time PCR was used to measure MIF, IL-6, TNF-α, IL-1β and IL-18 mRNA levels in kidney tissue.

RESULTS

ISO-1 treatment alleviated pathological damage in pancreatic and renal tissues, and reduced the serum levels of amylase, lipase, creatinine, uric acid, IL-6 and TNF-α. ISO-1 also reduced protein expression of NLRP3, ASC, caspase-1 and IL-1β, mRNA expression of MIF, IL-6, TNF-α, IL-1β and IL-18, and the infiltration of MPO-positive neutrophils in kidney tissue.

CONCLUSION

ISO-1 has a protective effect against experimental SAP-associated AKI. And the mechanism may be associated with ISO-1 inhibiting NLRP3 inflammasome signaling pathway.

[Acute kidney injury following acute pancreatitis (AP-AKI): Definition, Pathophysiology, Diagnosis and Therapy]

Acute pancreatitis (AP) is the most frequent gastrointestinal cause for hospitalization and one of the leading causes of in-hospital deaths. Severe acute pancreatitis is often associated with multiorgan failure and especially with acute kidney injury (AKI). AKI can develop early or late in the course of the disease and is a strong determinator of outcome. The mortality in the case of dialysis-dependent AKI and acute pancreatitis raises exponentially in the affected patients. AP-induced AKI (AP-AKI) shows many similarities but also distinct differences to other causes of AKI occurring in the intensive care unit setting. The knowledge of the exact pathophysiology can help to adjust, control and improve therapeutic approaches to the disease. Unfortunately, there are only a few studies dealing with AP and AKI.In this review, we discuss recent data about pathogenesis, causes and management of AP-AKI in patients with severe acute pancreatitis and exploit in this regard the diagnostic and prognostic potential of respective newer serum and urine markers.

Saikosaponin A-Induced Gut Microbiota Changes Attenuate Severe Acute Pancreatitis through the Activation of Keap1/Nrf2-ARE Antioxidant Signaling

Objective

Severe acute pancreatitis (SAP) is a serious and life-threatening disease associated with multiple organ failure and a high mortality rate and is accompanied by distinct oxidative stress and inflammatory responses. Saikosaponin A has strong antioxidant properties and can affect the composition of gut microbiota. We sought to determine the effects of Saikosaponin A interventions on SAP by investigating the changes of gut microbiota and related antioxidant signaling.

Methods

A SAP model was established in Sprague-Dawley (SD) rats through the injection of sodium taurocholate into the biliopancreatic duct and confirmed by elevated levels of serum lipase and amylase. The model was fed a standard diet either with saline solution or with Saikosaponin A. Fecal microbiota transplantation (FMT) from Saikosaponin A-induced rats into the rat model was performed to test the effects of gut microbiota. The composition of gut microbiota was analyzed by using 16S rRNA gene sequencing. We measured apoptotic status, inflammatory biomarkers, and Keap1-Nrf2-ARE ((Kelch-like ECH-associated protein 1) nuclear factor erythroid 2-related factor 2-antioxidant response element) antioxidant signaling.

Results

Saikosaponin A intervention attenuated SAP lesions and reduced the levels of serum amylase and lipase, oxidative stress, and inflammatory responses by reducing pathological scores and affecting the serum level of oxidative and inflammatory factors. Meanwhile, the expression of Keap1-Nrf2-ARE was increased. Saikosaponin A intervention improved microbiota composition by increasing the relative abundance of Lactobacillus and Prevotella species. FMT resulted in similar results as those caused by the Saikosaponin A intervention, suggesting Saikosaponin A may exert its function via the improvement of gut microbiota composition.

Conclusions

Saikosaponin A-induced gut microbiota changes attenuate SAP progression in the rat model and may be a potential natural drug for adjuvant treatment of SAP. Further work is needed to clear up the points.

Machine Learning Models of Acute Kidney Injury Prediction in Acute Pancreatitis Patients

Background. Acute kidney injury (AKI) has long been recognized as a common and important complication of acute pancreatitis (AP). In the study, machine learning (ML) techniques were used to establish predictive models for AKI in AP patients during hospitalization. This is a retrospective review of prospectively collected data of AP patients admitted within one week after the onset of abdominal pain to our department from January 2014 to January 2019. Eighty patients developed AKI after admission (AKI group) and 254 patients did not (non-AKI group) in the hospital. With the provision of additional information such as demographic characteristics or laboratory data, support vector machine (SVM), random forest (RF), classification and regression tree (CART), and extreme gradient boosting (XGBoost) were used to build models of AKI prediction and compared to the predictive performance of the classic model using logistic regression (LR). XGBoost performed best in predicting AKI with an AUC of 91.93% among the machine learning models. The AUC of logistic regression analysis was 87.28%. Present findings suggest that compared to the classical logistic regression model, machine learning models using features that can be easily obtained at admission had a better performance in predicting AKI in the AP patients.

Serum Cystatin C in Early Identification of Acute Kidney Injury in Acute Pancreatitis: Is It an Old Wine in a New Bottle?

How to cite this article: Siddiqui SS. Serum Cystatin C in Early Identification of Acute Kidney Injury in Acute Pancreatitis: Is It an Old Wine in a New Bottle? Indian J Crit Care Med 2020;24(9):744-745.

Evaluation of Serum Cystatin C as an Early Biomarker of Acute Kidney Injury in Patients with Acute Pancreatitis

INTRODUCTION

Acute pancreatitis (AP) is an inflammatory process of pancreas with varying degree of involvement of regional tissues. The aim of this study was to investigate the potential use of serum cystatin C (Cys-C) for the early and accurate diagnosis of acute kidney injury (AKI) in patients of AP.

MATERIALS AND METHODS

This was a prospective study conducted in 1 year. Total of 215 cases of AP fulfilling the inclusion criteria were enrolled in this study. Patients suffering from chronic pancreatitis, neoplasm, chronic liver disease, and chronic kidney disease were excluded from the study. Diagnosis of AP was based on the Atlanta classification 2012. All patients were classified into a non-AKI group (n = 152) and an AKI group (n = 38) according to the dynamic changes in serum creatinine levels. Serum Cys-C was measured by particle-enhanced immune nephelometric assay.

RESULTS

By univariate logistic regression analysis, body mass index (BMI) (OR = 1.44, 95% CI: 1.23-1.68; p < 0.001), blood urea (OR = 1.15, 95% CI: 1.06-1.23; p < 0.001), Cys-C (OR = 1.04, 95% CI: 1.01-1.07; p < 0.05), serum calcium (OR = 0.59, 95% CI: 0.41-0.86; p < 0.05), and serum lactate dehydrogenase (LDH) (OR = 1.001, 95% CI: 1.0-1.001; p < 0.05) were the significant indicators for AKI in patients with AP. Using multivariate logistic regression analysis, urinary albumin and Cys-C were independent and significant indicators of AKI in patients with AP (OR = 1.026, 95% CI: 1.01-1.07; p < 0.01). Receiver operating characteristic (ROC) curve of serum Cys-C, for AKI in patient with AP could be identified with a sensitivity of 92.06% at specificity of 96.0% [area under the curve (AUC) = 0.96, 95% CI: 0.92-0.98] by baseline serum Cys-C (cutoff value = >32.32 mg/L).

CONCLUSION

Increase of baseline serum Cys-C was associated with AKI in patients with AP.

HOW TO CITE THIS ARTICLE

Patel ML, Shyam R, Bharti H, Sachan R, Gupta KK, Parihar A. Evaluation of Serum Cystatin C as an Early Biomarker of Acute Kidney Injury in Patients with Acute Pancreatitis. Indian J Crit Care Med 2020;24(9):777-782.

Acute kidney injury in solitary kidney patients after partial nephrectomy: incidence, risk factors and prediction

Background

To analyze the incidence and risk factors of acute kidney injury (AKI) after partial nephrectomy (PN) in patients with solitary kidney, and to build AKI prediction models using logistic regression and machine learning (ML) approaches.

Methods

Clinical data of 87 solitary kidney patients with renal mass who received PN from January 2003 to March 2019 were collected. The diagnosis of AKI was based on KDIGO criteria. Logistic regression analysis and ML method were used to build prediction models.

Results

AKI developed in 52 (59.8%) patients. The logistic regression model had three variables: ischemia time (P=0.003), surgery time (P=0.001) and preoperative fasted blood glucose level (FBG) (P=0.049). The area under curve (AUC) was 0.826, with the specificity and sensitivity of optimal threshold value 82.9% and 69.2%. The ML model had the following variables: ischemia time, surgery time, age, FBG, mean arterial pressure (MAP), colloid, crystalloid, etc. XGBoost model has the best prediction performance. The AUC was 0.749, lower than that of the logistic regression model with no statistical difference (P=0.258), with the specificity and sensitivity 62.9% and 84.6%, respectively.

Conclusions

The incidence of AKI after PN in patients with a solitary kidney was relatively high, it was associated with longer ischemia time, surgery time and higher FBG level, etc. The performance of ML model had no significant difference with logistic regression model. Prospective studies with larger sample sizes are awaited to test and verify our research findings.

The Marker of Tubular Injury, Kidney Injury Molecule-1 (KIM-1), in Acute Kidney Injury Complicating Acute Pancreatitis: A Preliminary Study

Acute pancreatitis (AP) may be associated with severe inflammation and hypovolemia leading to organ complications including acute kidney injury (AKI). According to current guidelines, AKI diagnosis is based on dynamic increase in serum creatinine, however, creatinine increase may be influenced by nonrenal factor and appears late following kidney injury. Kidney injury molecule-1 (KIM-1) is a promising marker of renal tubular injury and it has not been studied in AP. Our aim was to assess if urinary KIM-1 may be used to diagnose AKI complicating the early stage of AP. We recruited 69 patients with mild to severe AP admitted to a secondary care hospital during the first 24 h from initial symptoms of AP. KIM-1 was measured in urine samples collected on the day of admission and two subsequent days of hospital stay. AKI was diagnosed based on creatinine increase according to Kidney Disease: Improving Global Outcomes 2012 guidelines. Urinary KIM-1 on study days 1 to 3 was not significantly higher in 10 patients who developed AKI as compared to those without AKI and did not correlate with serum creatinine or urea. On days 2 and 3, urinary KIM-1 correlated positively with urinary liver-type fatty acid-binding protein, another marker of tubular injury. On days 2 and 3, urinary KIM-1 was higher among patients with systemic inflammatory response syndrome, and several correlations between KIM-1 and inflammatory markers (procalcitonin, urokinase-type plasminogen activator receptor, C-reactive protein) were observed on days 1 to 3. With a limited number of patients, our study cannot exclude the diagnostic utility of KIM-1 in AP, however, our results do not support it. We hypothesize that the increase of KIM-1 in AKI complicating AP lasts a short time, and it may only be observed with more frequent monitoring of the marker. Moreover, urinary KIM-1 concentrations in AP are associated with inflammation severity.

Meprin-β activity modulates the β-catalytic subunit of protein kinase A in ischemia-reperfusion-induced acute kidney injury

Meprin metalloproteases have been implicated in the progression of kidney injury. Previous work from our group has shown that meprins proteolytically process the catalytic subunit of protein kinase A (PKA-C), resulting in decreased PKA-C kinase activity. The goal of the present study was to determine the PKA-C isoforms impacted by meprin-β and whether meprin-β expression affects downstream mediators of the PKA signaling pathway in ischemia-reperfusion (IR)-induced kidney injury. IR was induced in 12-wk-old male wild-type (WT) and meprin-β knockout (βKO) mice. Madin-Darby canine kidney cells transfected with meprin-β cDNA were also subjected to 2 h of hypoxia. Western blot analysis was used to evaluate levels of total PKA-C, PKA-Cα, PKA-Cβ, phosphorylated (p-)PKA-C, and p-ERK1/2. Meprin-β expression enhanced kidney injury as indicated by levels of neutrophil gelatinase-associated lipocalin and cystatin C. IR-associated decreases were observed in levels of p-PKA-C in kidney tissue from WT mice but not βKO mice, suggesting that meprin-β expression/activity is responsible for the in vivo reduction in kinase activity. Significant increases in levels of PKA-Cβ were observed in kidney lysates for WT mice but not βKO mice at 6 h post-IR. Proximal tubule PKA-Cβ increases in WT but not βKO kidneys were demonstrated by fluorescent microscopy. Furthermore, IR-induced injury was associated with significant increases in p-ERK levels for both genotypes. The present data demonstrate that meprin-β enhances IR-induced kidney injury in part by modulating mediators of the PKA-Cβ signaling pathway.

Does Beta-Trace Protein (BTP) Outperform Cystatin C as a Diagnostic Marker of Acute Kidney Injury Complicating the Early Phase of Acute Pancreatitis?

Acute pancreatitis (AP) belongs to the commonest acute gastrointestinal conditions requiring hospitalization. Acute kidney injury (AKI) often complicates moderately severe and severe AP, leading to increased mortality. Among the laboratory markers proposed for early diagnosis of AKI, few have been studied in AP, including cystatin C and neutrophil gelatinase-associated lipocalin (NGAL). Beta-trace protein (BTP), a low-molecular-weight glycoprotein proposed as an early marker of decreased glomerular filtration, has never been studied in AP. We investigated the diagnostic usefulness of serum BTP for early diagnosis of AKI complicating AP in comparison to previously studied markers. BTP was measured in serum samples collected over the first three days of hospital stay from 73 adult patients admitted within 24 h of mild to severe AP. Thirteen patients (18%) developed AKI in the early phase of AP. Serum BTP was higher in patients who developed AKI, starting from the first day of hospitalization. Strong correlations were observed between BTP and serum cystatin C but not serum or urine NGAL. On admission, BTP positively correlated with endothelial dysfunction. The diagnostic usefulness of BTP for AKI was similar to cystatin C and lower than NGAL. Increased BTP is an early predictor of AKI complicating AP. However, it does not outperform cystatin C or NGAL.

Potential Prognostic Markers of Acute Kidney Injury in the Early Phase of Acute Pancreatitis

Acute kidney injury (AKI) is a serious complication of acute pancreatitis (AP), which occurs in up to 70% of patients with severe AP and significantly increases the risk of mortality. At present, AKI is diagnosed based on dynamic increase in serum creatinine and decreased urine output; however, there is a need for earlier and more accurate biomarkers. The aim of the study was to review current evidence on the laboratory tests that were studied as the potential biomarkers of AKI in AP. We also briefly summarized the knowledge coming from the studies including sepsis or ICU patients since severe acute pancreatitis is associated with systemic inflammation and organ failure. Serum cystatin C and serum or urine NGAL have been shown to predict or diagnose AKI in AP; however, this evidence come from the single center studies of low number of patients. Other markers, such as urinary kidney injury molecule-1, cell cycle arrest biomarkers (tissue inhibitor metalloproteinase-2 and urine insulin-like growth factor-binding protein 7), interleukin-18, liver-type fatty acid-binding protein, or calprotectin have been studied in other populations suffering from systemic inflammatory states. In AP, the potential markers of AKI may be significantly influenced by either dehydration or inflammation, and the impact of these factors may be difficult to distinguish from kidney injury. The subject of AKI complicating AP is understudied. More studies are needed, for both exploratory (to choose the best markers) and clinical (to evaluate the diagnostic accuracy of the chosen markers in real clinical settings).