RESUMEN
Celiac disease (CD) is a chronic autoimmune disorder triggered by the ingestion of gluten-containing food by genetically predisposed individuals. Hence, treatment of CD consists of permanent avoidance of wheat, rye, barley, and other gluten-containing foods. Lifelong adherence to a gluten-free diet (GFD) improves the symptoms of CD, but recent evidence suggests it is also associated with a higher risk for hepatic steatosis and the coexistence or emergence of other cardiometabolic risk factors. Moreover, a higher risk for liver steatosis is also reported by some authors as a potential extraintestinal complication of the CD itself. Recent nomenclature changes designate the association between hepatic steatosis and at least one of five cardiometabolic risk factors as metabolic dysfunction-associated steatotic liver disease (MASLD). An extended network of potentially causative factors underlying the association between MAFLD and CD, before and after dietary therapy is implemented, was recently described. The individualized treatment of these patients is less supported by evidence, with most of the current recommendations relying on empiric clinical judgment. This review focuses on the causative associations between CD and hepatic injury, either as an extraintestinal manifestation of CD or a side effect of GFD, also referring to potential therapeutic strategies for these individuals.
Asunto(s)
Enfermedad Celíaca , Dieta Sin Gluten , Humanos , Enfermedad Celíaca/dietoterapia , Enfermedad Celíaca/complicaciones , Hígado Graso/dietoterapia , Hígado Graso/etiología , Factores de Riesgo , Enfermedades Metabólicas/dietoterapia , Enfermedades Metabólicas/etiologíaRESUMEN
Inflammatory bowel diseases (IBDs) affect over 4.9 million individuals worldwide. Colonoscopy (CS) is the gold-standard technique for diagnosis. The remissive-recurrent pattern of evolution raises the need for non-invasive techniques to monitor disease activity. This review aims to present the advantages of intestinal ultrasound (IUS) in managing IBDs. Our search was conducted on the PubMed, Embase, and Cochrane (CENTRAL) databases, selecting original studies comparing IUS with other imaging and invasive monitoring methods. Our search yielded 8654 results, of which 107 met the inclusion criteria. Increased bowel wall thickness (BWT) and colour Doppler signal (CDS) are discriminative for disease activity. IUS can predict disease outcomes and detect response to treatment or postoperative recurrence. Contrast-enhanced ultrasound (CEUS) and elastography help differentiate fibrotic from inflammatory stenoses. The difficult rectal assessment limits the use of IUS in ulcerative colitis (UC). Transmural healing may develop as a therapeutic target as it is associated with better outcomes. Patients are compliant with this technique, and its results correlate well with CS and other imaging methods. In conclusion, IUS proves to be essential in assessing IBD activity and treatment response, predicting outcomes and detecting complications. CEUS and elastography are researched to improve the diagnostic values of IUS.
RESUMEN
Ulcerative colitis (UC) is a chronic inflammatory bowel disease characterized by periods of exacerbation and remission, making disease monitoring and management challenging. Endoscopy, the gold standard for assessing disease activity and severity, involves invasive procedures and is associated with patient discomfort and risks. Using machine learning (ML) to combine fecal calprotectin with other clinical or biological tests can significantly enhance the non-invasive prediction of endoscopic disease activity (EDA) in UC. Aim: To prove that by fusing fecal calprotectin with other clinical data into an ML model, the performance of the non-invasive prediction of EDA can be significantly improved. Methods: We conducted a prospective, observational, single-center study encompassing 103 patients diagnosed with UC. We employed multilayer perceptron models as the core ML algorithm for predicting EDA. For the constructed models, we utilized the varImp function from the caret library in R to assess the significance of each variable in predicting the outcome. Results: Calprotectin as a sole predictor obtained an accuracy of 70% and an area under the curve (AUC) of 0.68. Combining calprotectin with the list of selected predictors that were fed to the MLP models improved accuracy and the AUC. The accuracy of the algorithm on the test set was 85%. Similarly, the AUC increased to 0.93. This is the first study to propose the use of calprotectin as a predictor in an ML model to estimate UC endoscopic disease activity. Conclusion: The deployment of this ML model can furnish doctors and patients with valuable evaluation of endoscopic disease activity which can be highly beneficial for individuals with UC who need long-term treatment.
RESUMEN
Inflammatory bowel disease (IBD) comprises two types of chronic intestinal disorders: Crohn's disease and ulcerative colitis. In long-standing ulcerative colitis disease activity, histological persistent inflammation has been linked to an increased risk of relapse, and long-term corticosteroid use, even when endoscopic remission is reached. In Crohn's disease, the discontinuous nature of lesions and transmural inflammation have limited the standardized histological assessment. The current evidence from research proposes that besides clinical and endoscopic healing, the achievement of histological healing constitutes an endpoint to assess disease activity and remission in IBD patients concerning better long-term disease outcomes. Histological alterations may persist even in the absence of endoscopic lesions. For these reasons, new advanced techniques promise to revolutionize the field of IBD by improving the endoscopic and histologic assessment, disease characterization, and ultimately patient care, with an established role in daily practice for objective assessment of lesions. This review outlines the importance of including microscopic evaluation in IBD, highlighting the clinical benefits of a deep state of disease remission using validated diagnostic methods and scoring systems for daily clinical practice.
RESUMEN
Irritable bowel syndrome (IBS) has a global prevalence of around 4.1% and is associated with a low quality of life and increased healthcare costs. Current guidelines recommend that IBS is diagnosed using the symptom-based Rome IV criteria. Despite this, when patients seek medical attention, they are usually over-investigated. This issue might be resolved by novel technologies in medicine, such as the use of Artificial Intelligence (AI). In this context, this paper aims to review AI applications in IBS. AI in colonoscopy proved to be useful in organic lesion detection and diagnosis and in objectively assessing the quality of the procedure. Only a recently published study talked about the potential of AI-colonoscopy in IBS. AI was also used to study biofilm characteristics in the large bowel and establish a potential relationship with IBS. Moreover, an AI algorithm was developed in order to correlate specific bowel sounds with IBS. In addition to that, AI-based smartphone applications have been developed to facilitate the monitoring of IBS symptoms. From a therapeutic standpoint, an AI system was created to recommend specific diets based on an individual's microbiota. In conclusion, future IBS diagnosis and treatment may benefit from AI.
RESUMEN
Inflammatory bowel disease represents one of the most life-altering gastrointestinal pathologies, with its multifactorial nature and unclear physiopathology. The most relevant clinical forms, ulcerative colitis and Crohn's disease, clinically manifest with mild to severe flares and remission periods that alter the patient's social, familial and professional integration. The chronic inflammatory activity of the intestinal wall determines severe modifications of the local environment, such as dysbiosis, enteric endocrine, nervous and immune system disruptions and intestinal wall permeability changes. These features are part of the gastrointestinal ecosystem that modulates the bottom-to-top signaling to the central nervous system, leading to a neurobiologic imbalance and clinical affective and/or behavioral symptoms. The gut-brain link is a bidirectional pathway and psychological distress can also affect the central nervous system, which will alter the top-to-bottom regulation, leading to possible functional digestive symptoms and local inflammatory responses. In the middle of this neuro-gastrointestinal system, the microbiome is a key player, as its activities offer basic functional support for both relays. The present article presents current scientific information that links the pathophysiology and clinical aspects of inflammatory bowel disease and psychiatric symptomatology through the complex mechanism of the gut-brain axis and the modulatory effects of the gut microbiota.
RESUMEN
TNF-α inhibitors (TNFis) have revolutionized the treatment of certain chronic immune-mediated diseases, being widely and successfully used in rheumatic inflammatory diseases, and have also proved their efficacy in the treatment of inflammatory bowel disease (IBD). However, among the side effects of these agents are the so-called paradoxical effects. They can be defined as the appearance or exacerbation of a pathological condition that usually responds to this class of drug while treating a patient for another condition. A wide range of paradoxical effects have been reported including dermatological, intestinal and ophthalmic conditions. The causal mechanism of occurrence may implicate an imbalance of cytokines, but is still not fully understood, and remains a matter of debate. These paradoxical reactions often show improvement on discontinuation of the medication or on switching to another TNFi, but in some cases it is a class effect that could lead to the withdrawal of all anti-TNF agents. Close monitoring of patients treated with TNFis is necessary in order to detect paradoxical reactions. In this study we focus on reviewing IBD occurrence as a paradoxical effect of TNFi therapy in patients with rheumatological diseases (rheumatoid arthritis, psoriatic arthritis, ankylosing spondylitis, and juvenile idiopathic arthritis).
RESUMEN
A suitable, non-invasive biomarker for assessing endoscopic disease activity (EDA) in ulcerative colitis (UC) has yet to be identified. Our study aimed to develop a cost-effective and non-invasive machine learning (ML) method that utilizes the cost-free Inflammatory Bowel Disease Questionnaire (IBDQ) score and low-cost biological predictors to estimate EDA. Four random forest (RF) and four multilayer perceptron (MLP) classifiers were proposed. The results show that the inclusion of IBDQ in the list of predictors that were fed to the models improved accuracy and the AUC for both the RF and the MLP algorithms. Moreover, the RF technique performed noticeably better than the MLP method on unseen data (the independent patient cohort). This is the first study to propose the use of IBDQ as a predictor in an ML model to estimate UC EDA. The deployment of this ML model can furnish doctors and patients with valuable insights into EDA, a highly beneficial resource for individuals with UC who need long-term treatment.
RESUMEN
Nonalcoholic fatty liver disease (NAFLD) represents the most common chronic liver disease worldwide, reaching one of the highest prevalences in patients with type 2 diabetes mellitus (T2DM). For now, no specific pharmacologic therapies are approved to prevent or treat NAFLD. Glucagon-like peptide-1 receptor agonists (GLP-1RAs) are currently evaluated as potential candidates for NAFLD treatment in patients with T2DM. Some representatives of this class of antihyperglycemic agents emerged as potentially beneficial in patients with NAFLD after several research studies suggested they reduce hepatic steatosis, ameliorate lesions of nonalcoholic steatohepatitis (NASH), or delay the progression of fibrosis in this population. The aim of this review is to summarize the body of evidence supporting the effectiveness of GLP-1RA therapy in the management of T2DM complicated with NAFLD, describing the studies that evaluated the effects of these glucose-lowering agents in fatty liver disease and fibrosis, their possible mechanistic justification, current evidence-based recommendations, and the next steps to be developed in the field of pharmacological innovation.
RESUMEN
Patients undergoing ablation for atrial fibrillation may be at increased risk of developing gastroesophageal reflux disease. We prospectively studied the presence of symptomatic gastroesophageal reflux disease in naïve patients who underwent atrial fibrillation ablation. METHODS: The presence of typical symptoms suggestive of gastroesophageal reflux disease was clinically assessed by the gastroenterologist at baseline and at 3 months after ablation. In addition to that, all patients underwent upper gastrointestinal endoscopy. RESULTS: Seventy-five patients were included in two groups: 46 patients who underwent atrial fibrillation ablation (study group) and 29 patients without ablation (control group). Patients with atrial fibrillation ablation were younger (57.76 ± 7.66 years versus 67.81 ± 8.52 years; p = 0.001), predominantly male (62.2% versus 33.3%; p = 0.030) and with higher body mass index (28.96 ± 3.12 kg/m2 versus 26.81 ± 5.19 kg/m2; p = 0.046). At three months after the ablation, in the study and control groups, there were 88.9% and 57.1% patients in sinus rhythm, respectively, (p = 0.009). Symptomatic gastroesophageal reflux disease was not more frequent in the study group (42.2% versus 61.9%; p = 0.220). There was no difference in terms of sinus rhythm prevalence in patients with versus without symptomatic gastroesophageal reflux disease (89.5% versus 88.5%; p = 0.709). CONCLUSION: In this small prospective study, typical symptoms suggestive of gastroesophageal reflux disease were not more frequent three months following atrial fibrillation ablation.
RESUMEN
Non-alcoholic fatty liver disease (NAFLD) is the most prevalent liver disease and is the hepatic expression of metabolic syndrome. The development of non-invasive methods for the diagnosis of hepatic steatosis and advanced fibrosis in high-risk patients, especially those with type 2 diabetes mellitus, is highly needed to replace the invasive method of liver biopsy. Elastographic methods can bring significant added value to screening and diagnostic procedures for NAFLD in patients with diabetes, thus contributing to improved NAFLD management. Pharmacological development and forthcoming therapeutic measures that address NAFLD should also be based on new, non-invasive, and reliable tools that assess NAFLD in at-risk patients and be able to properly guide treatment in individuals with both diabetes and NAFLD. This is the first review aiming to outline and discuss recent studies on ultrasound-based hepatic elastography, focusing on NAFLD assessment in patients with diabetes.
RESUMEN
Non-alcoholic fatty liver disease (NAFLD) represents the hepatic expression of the metabolic syndrome and is the most prevalent liver disease. NAFLD is associated with liver-related and extrahepatic morbi-mortality. Among extrahepatic complications, cardiovascular disease (CVD) is the primary cause of mortality in patients with NAFLD. The most frequent clinical expression of CVD is the coronary artery disease (CAD). Epidemiological data support a link between CAD and NAFLD, underlain by pathogenic factors, such as the exacerbation of insulin resistance, genetic phenotype, oxidative stress, atherogenic dyslipidemia, pro-inflammatory mediators, and gut microbiota. A thorough assessment of cardiovascular risk and identification of all forms of CVD, especially CAD, are needed in all patients with NAFLD regardless of their metabolic status. Therefore, this narrative review aims to examine the available data on CAD seen in patients with NAFLD, to outline the main directions undertaken by the CVD risk assessment and the multiple putative underlying mechanisms implicated in the relationship between CAD and NAFLD, and to raise awareness about this underestimated association between two major, frequent and severe diseases.
RESUMEN
According to new research, a possible association between inflammatory bowel disease (IBD) and an increased risk of ischemic heart disease (IHD) has been demonstrated, but this concern is still debatable. The purpose of this review is to investigate the link between IHD and IBD, as well as identify further research pathways that could help develop clinical recommendations for the management of IHD risk in IBD patients. There is growing evidence suggesting that disruption of the intestinal mucosal barrier in IBD is associated with the translocation of microbial lipopolysaccharides (LPS) and other endotoxins into the bloodstream, which might induce a pro-inflammatory cytokines response that can lead to endothelial dysfunction, atherosclerosis and acute cardiovascular events. Therefore, it is considered that the long-term inflammation process in IBD patients, similar to other chronic inflammatory diseases, may lead to IHD risk. The main cardiovascular risk factors, including high blood pressure, dyslipidemia, diabetes, smoking, and obesity, should be checked in all patients with IBD, and followed by strategies to reduce and manage early aggression. IBD activity is an important risk factor for acute cardiovascular events, and optimizing therapy for IBD patients should be followed as recommended in current guidelines, especially during active flares. Large long-term prospective studies, new biomarkers and scores are warranted to an optimal management of IHD risk in IBD patients.
RESUMEN
Background and Objectives: The COVID-19 pandemic has had a considerable impact on inflammatory bowel disease (IBD) patients by limiting their access to medical services due to restrictions and the reorganization of the healthcare systems, which affects their quality of life (QoL). We aimed to assess the impact of the COVID-19 pandemic on the QoL of patients with IBD. Materials and Methods: We conducted a descriptive observational study, which included 90 adult patients diagnosed with IBD. The study sample consisted of two subgroups: a retrospective-pre-pandemic group (group A) and a prospective-pandemic group (group B). Group A included 45 IBD patients who were evaluated in 2018. Group B included 45 patients with confirmed diagnosis of IBD, evaluated between June and December 2021the period of the COVID-19 pandemic (prospective), consecutively recruited. All the patients filled in a QoL assessment questionnaireIBDQ-32. Subsequently, the two samples were comparatively assessed. Results: The average values of the IBDQ scores were significantly lower in 2021 compared to those recorded in 2018: 145.56 vs. 128.3 (p < 0.05). We also we found significant differences between the subscores: IBDQ1 (p = 0.043), IBDQ2 (p = 0.034), IBDQ3 (p = 0.045), IBDQ4 (p = 0.025). Conclusions: IBDQ scores were significantly lower in 2021 compared to 2018 (p < 0.05), showing that during the COVID-19 pandemic, patients with IBD had a more influenced QoL.
Asunto(s)
COVID-19 , Enfermedades Inflamatorias del Intestino , Adulto , Enfermedad Crónica , Humanos , Enfermedades Inflamatorias del Intestino/diagnóstico , Pandemias , Estudios Prospectivos , Calidad de Vida , Estudios RetrospectivosRESUMEN
BACKGROUND AND AIMS: Gastroesophageal reflux disease (GERD) is a common condition present in daily practice with a wide range of clinical phenotypes. In this line, respiratory conditions may be associated with GERD. The Romanian Societies of Gastroenterology and Neurogastroenterology, in association with the Romanian Society of Pneumology, aimed to create a guideline regarding the epidemiology, diagnosis and treatment of respiratory conditions associated with GERD. METHODS: Delphi methodology was used and eleven common working groups of experts were created. The experts reviewed the literature according to GRADE criteria and formulated 34 statements and recommendations. Consensus (>80% agreement) was reached for some of the statements after all participants voted. RESULTS: All the statements and the literature review are presented in the paper, together with their correspondent grade of evidence and the voting results. Based on >80% voting agreement, a number of 22 recommendations were postulated regarding the diagnosis and treatment of GERD-induced respiratory symptoms. The experts considered that GERD may cause bronchial asthma and chronic cough in an important number of patients through micro-aspiration and vagal-mediated tracheobronchial reflex. GERD should be suspected in patients with asthma with suboptimal controlled or after exclusion of other causes, also in nocturnal refractory cough which needs gastroenterological investigations to confirm the diagnosis. Therapeutic test with double dose proton pump inhibitors (PPI) for 3 months is also useful. GERD induced respiratory conditions are difficult to treat; however,proton pump inhibitors and laparoscopic Nissen fundoplication are endorsed for therapy. CONCLUSIONS: This guideline could be useful for the multidisciplinary management of GERD with respiratory symptoms in current practice.
Asunto(s)
Gastroenterología , Reflujo Gastroesofágico , Tos/complicaciones , Tos/tratamiento farmacológico , Reflujo Gastroesofágico/complicaciones , Reflujo Gastroesofágico/diagnóstico , Reflujo Gastroesofágico/terapia , Humanos , Inhibidores de la Bomba de Protones/uso terapéutico , Rumanía/epidemiologíaRESUMEN
Ixekizumab is one of the three biologic agents including Secukinumab and Brodalumab that targets the Interleukin-17 (IL-17) pathway to reduce inflammation in psoriasis and ankylosing spondylitis. In this report we present the case of 42-year-old woman, who was diagnosed with psoriasis and psoriatic arthritis. One week after first administration of Ixekizumab, she developed diffuse abdominal pain, bloody diarrhea (7-8 stools/day) and fever. Following imaging (colonoscopy, computed tomography) and laboratory investigations, she was diagnosed with acute severe ulcerative colitis complicated with toxic megacolon. The medical treatment (first corticotherapy, then infliximab) has failed and the patient needed emergency colectomy. Based on the immunological mechanisms and the observation from other studies, Ixekizumab should be considered an etiology for new-onset inflammatory bowel disease.
RESUMEN
BACKGROUND: Many scores have been suggested to assess the severity of acute pancreatitis upon onset. The extrapancreatic necrosis volume is a novel, promising score that appears to be superior to other scores investigated so far. AIM: To evaluate the discriminatory power of extrapancreatic necrosis volume to identify severe cases of acute pancreatitis. METHODS: A total of 123 patients diagnosed with acute pancreatitis at Institute of Gastroenterology and Hepatology, St Spiridon Hospital between January 1, 2017 and December 31, 2019 were analyzed retrospectively. Pancreatitis was classified according to the revised Atlanta classification (rAC) as mild, moderate, or severe. Severity was also evaluated by computed tomography and classified according to the computed tomography severity index (CTSI) and the modified CTSI (mCTSI). The results were compared with the extrapancreatic volume necrosis to establish the sensitivity and specificity of each method. RESULTS: The CTSI and mCTSI imaging scores and the extrapancreatic necrosis volume were highly correlated with the severity of pancreatitis estimated by the rAC (r = 0.926, P < 0.001 and r = 0.950, P < 0.001; r = 0.784, P < 0.001, respectively). The correlation of C-reactive protein with severity was positive but not as strong, and was not significant (r = 0.133, P = 0.154). The best predictor for the assessment of severe pancreatitis was the extrapancreatic necrosis volume [area under the curve (AUC) = 0.993; 95% confidence interval (CI): 0.981-1.005], with a 99.5% sensitivity and 99.0% specificity at a cutoff value of 167 mL, followed by the mCTSI 2007 score (AUC = 0.972; 95%CI: 0.946-0.999), with a 98.0% sensitivity and 96.5% specificity, and the CTSI 1990 score (AUC = 0.969; 95%CI: 0.941-0.998), with a 97.0% sensitivity and 95.0% specificity. CONCLUSION: Radiological severity scores correlate strongly and positively with disease activity. Extrapancreatic necrosis volume shows the best diagnostic accuracy for severe cases.
RESUMEN
Background and Objectives: Hepatic diseases are an important public health problem. All patients with chronic hepatitis C virus (HCV) infection receive treatment, regardless of hepatic fibrosis severity. However, evaluation of hepatic fibrosis and steatosis is still useful in assessing evolution, prognosis and monitoring of hepatic disease, especially after treatment with direct-acting antivirals (DAAs). The aim of this study was to assess the link between patatin-like phospholipase domain-containing 3 (PNPLA3) polymorphism and the degree of hepatic steatosis and fibrosis in patients with chronic HCV infection, as well as changes in steatosis and fibrosis three monthsafter obtaining a sustained viral response (SVR). Materials and Methods:Ourstudy included 100 patients with chronic hepatitis C (CHC) infection and compensated cirrhosis who received DAA treatment and who were evaluated using Fibromax prior to and 3 months after SVR. The influence of PNPLA3 (CC, CG, GG) genotype among these patients on the degree of post-treatment regression of steatosis and fibrosis was assessed. Results: Regression was noticed in the degree of both hepatic steatosis and hepatic fibrosis post-DAA treatment (three months after SVR). Analysis of the correlation between PNPLA3 genotype and fibrosis indicated that the average level of fibrosis (F) before DAA treatment was higher in patients with the GG genotype than in patients with the CC or CG genotype. Three months after SVR, the average level of fibrosis decreased; however, it remained significantly increased in GG subjects compared to that in CC or CG patients. The degree of hepatic steatosis before treatment was not significantly different among patients with different PNPLA3 genotypes, and no significant correlations were observed three months after SVR. Conclusions: The genetic variants of PNPLA3 influence the evolution of hepatic fibrosis. The GG subtype plays an important role in the degree of hepatic fibrosis both before and after treatment (three months after SVR)and could be a prognostic marker for assessment of post-SVR evolution.
Asunto(s)
Hígado Graso/diagnóstico , Hepatitis C Crónica/complicaciones , Lipasa/genética , Cirrosis Hepática/diagnóstico , Proteínas de la Membrana/genética , Antivirales/uso terapéutico , Hígado Graso/tratamiento farmacológico , Hígado Graso/genética , Genotipo , Hepatitis C Crónica/tratamiento farmacológico , Humanos , Cirrosis Hepática/genética , Cirrosis Hepática/virología , Polimorfismo de Nucleótido Simple , Respuesta Virológica SostenidaRESUMEN
Background and Objectives: Anemia is the most frequent complication of inflammatory bowel diseases. Clinically, anemia can affect important quality-of-life (QoL) components, such as exercise capacity, cognitive function, and the ability to carry out social activities. The disease activity has a significant impact on QoL, mainly due to clinical manifestations, which are more severe during the periods of disease activity. Our aim was to estimate the impact of anemia on QoL in patients with Crohn's disease. Material and Methods. We made a prospective study on 134 patients with Crohn's disease (CD) in a Romanian tertiary center. The CD diagnosis was established by colonoscopy and histopathological examination. In particular cases, additional examinations were required (small bowel capsule endoscopy, computed tomography enterography, and magnetic resonance enterography). Anemia was defined according to the World Health Organization's definition, the activity of the disease was assessed by Crohn's disease activity index (CDAI) score, and the QoL was evaluated by Inflammatory Bowel Disease Questionnaire 32 (IBDQ 32). Results: 44.8% patient had anemia, statistically related to the activity of the disease and corticoids use. We found a strong association between QoL and disease activity on all four sub-scores: patients with more severe activity had a significantly lower IBDQ (260.38 ± 116.96 vs. 163.85 ± 87.20, p = 0.001) and the presence of anemia (127.03 vs. 148.38, p = 0.001). In multiple regression analyses, both disease activity and anemia had an impact on the QoL. Conclusions: Anemia has high prevalence in the CD in northeastern region of Romania. Anemia was more common in female patients, in patients undergoing corticosteroid treatment, and in those with active disease. Both anemia and disease activity had a strong negative and independent impact on QoL.
Asunto(s)
Anemia , Enfermedad de Crohn , Enfermedades Inflamatorias del Intestino , Anemia/epidemiología , Anemia/etiología , Enfermedad de Crohn/complicaciones , Enfermedad de Crohn/epidemiología , Femenino , Humanos , Estudios Prospectivos , Calidad de Vida , Índice de Severidad de la EnfermedadRESUMEN
BACKGROUND: Colonoscopy with biopsy is the "gold" standard for evaluating disease activity in inflammatory bowel diseases (IBD). Current research is geared toward finding non-invasive, cost-efficient methods that estimate disease activity. We aimed to develop a neural network (NN) model for the non-invasive prediction of histologic activity in IBD using routinely available clinical-biological parameters. METHODS: Standard clinical-biological parameters and histologic activity from 371 ulcerative colitis (UC) and 115 Crohn's disease (CD) patient records were collected. A training set, a test set, and a validation set were used for building/validating 2 models for each disease. All models had binary output predicting the active/inactive histologic disease status. For both diseases, the first model used both clinical and biological inputs, while the second used only biological data. RESULTS: First UC model obtained an accuracy of 95.59% on the test set and 96.67% on the validation set. The second UC model achieved accuracies of 88.24% and 86.67% on the test and validation sets, respectively. The First CD classifier resulted in 90.48% accuracy on the test set and 91.67% on the validation set. Finally, the second CD classifier obtained an accuracy of 85.71% on the test set and 91.67% on the validation set. CONCLUSIONS: An accurate and non-invasive artificial intelligence system to predict histologic disease activity in IBD is designed. Our models achieved similar or better results compared to the documented performance of fecal calprotectin (the best non-invasive IBD biomarker to date). Given these favorable results, we anticipate the future utility in the clinical setting of a non-invasive disease activity prediction.