Differentiating Crohn’s disease from intestinal tuberculosis using a fusion correlation neural network

Artificial intelligence-aided colonoscopic differential diagnosis between Crohn's disease and gastrointestinal tuberculosis

BACKGROUND AND AIM

Differentiating between Crohn's disease (CD) and gastrointestinal tuberculosis (GITB) is challenging. We aimed to evaluate the clinical applicability of an artificial intelligence (AI) model for this purpose.

METHODS

The AI model was developed and assessed using an internal dataset comprising 1,132 colonoscopy images of CD and 1,045 colonoscopy images of GITB at a tertiary referral center. Its stand-alone performance was further evaluated in an external dataset comprising 67 colonoscopy images of 17 CD patients and 63 colonoscopy images of 14 GITB patients from other institutions. Additionally, a crossover trial involving three expert endoscopists and three trainee endoscopists compared AI-assisted and unassisted human interpretations.

RESULTS

In the internal dataset, the sensitivity, specificity, and accuracy of the AI model in distinguishing between CD and GITB were 95.3%, 100.0%, and 97.7%, respectively, with an area under the ROC curve of 0.997. In the external dataset, the AI model exhibited a sensitivity, specificity, and accuracy of 77.8%, 85.1%, and 81.5%, respectively, with an area under the ROC curve of 0.877. In the human endoscopist trial, AI assistance increased the pooled accuracy of the six endoscopists from 86.2% to 88.8% (P = 0.010). While AI did not significantly enhance diagnostic accuracy for the experts (96.7% with AI vs 95.6% without, P = 0.360), it significantly improved accuracy for the trainees (81.0% vs 76.7%, P = 0.002).

CONCLUSIONS

This AI model shows potential in aiding the accurate differential diagnosis between CD and GITB, particularly benefiting less experienced endoscopists.

New diagnostic strategies to distinguish Crohn's disease and gastrointestinal tuberculosis

PURPOSE OF REVIEW

Despite advances in our radiological, histological and microbiological armamentarium, distinguishing between Crohn's disease (CD) and intestinal tuberculosis (ITB), especially in a TB endemic country, continues to be a challenging exercise in a significant number of patients. This review aims to summarize current available evidence on novel diagnostic techniques which have a potential to fill the gap in our knowledge of differentiating between ITB and CD.

RECENT FINDINGS

Both ITB and CD are associated with altered host immune responses, and detection of these altered innate and adaptive immune cells has potential to distinguish ITB from CD. ITB and CD have different epigenetic, proteomic and metabolomic signatures, and recent research has focused on detecting these differences. In addition, the gut microbiome, which is involved in mucosal immunity and inflammatory responses, is considerably altered in both ITB and CD, and is another potential frontier, which can be tapped to discriminate between the two diseases. With technological advancements, we have newer radiological modalities including perfusion CT and dual-layer spectral detector CT enterography and evidence is emerging of their role in differentiating ITB from CD. Finally, time will tell whether the advent of artificial intelligence, with rapidly accumulating data in this field, will be the gamechanger in solving this puzzle of diagnostic dilemma between ITB and Crohn's disease.

SUMMARY

Recent advances need to be clinically validated before they can be used as novel diagnostic measures to differentiate Intestinal TB from CD.

Artificial intelligence for discrimination of Crohn's disease and gastrointestinal tuberculosis: A systematic review

BACKGROUND AND AIM

Discrimination of gastrointestinal tuberculosis (GITB) and Crohn's disease (CD) is difficult. Use of artificial intelligence (AI)-based technologies may help in discriminating these two entities.

METHODS

We conducted a systematic review on the use of AI for discrimination of GITB and CD. Electronic databases (PubMed and Embase) were searched on June 6, 2022, to identify relevant studies. We included any study reporting the use of clinical, endoscopic, and radiological information (textual or images) to discriminate GITB and CD using any AI technique. Quality of studies was assessed with MI-CLAIM checklist.

RESULTS

Out of 27 identified results, a total of 9 studies were included. All studies used retrospective databases. There were five studies of only endoscopy-based AI, one of radiology-based AI, and three of multiparameter-based AI. The AI models performed fairly well with high accuracy ranging from 69.6-100%. Text-based convolutional neural network was used in three studies and Classification and regression tree analysis used in two studies. Interestingly, irrespective of the AI method used, the performance of discriminating GITB and CD did not match in discriminating from other diseases (in studies where a third disease was also considered).

CONCLUSION

The use of AI in differentiating GITB and CD seem to have acceptable accuracy but there were no direct comparisons with traditional multiparameter models. The use of multiple parameter-based AI models have the potential for further exploration in search of an ideal tool and improve on the accuracy of traditional models.

Role of soil nutrient elements transport on Camellia oleifera yield under different soil types

BACKGROUND

Most of Camellia oleifera forests have low fruit yield and poor oil quality that are largely associated with soil fertility. Soil physical and chemical properties interact with each other affecting soil fertility and C. oleifera growing under different soil conditions produced different yield and oil composition. Three main soil types were studied, and redundancy, correlation, and double-screening stepwise regression analysis were used for exploring the relationships between C. oleifera nutrients uptake and soil physical and chemical properties, shedding light on the transport law of nutrient elements from root, leaves, and kernel, and affecting the regulation of fruit yield and oil composition.

RESULTS

In the present study, available soil elements content of C. oleifera forest were mainly regulated by water content, pH value, and total N, P and Fe contents. Seven elements (N, P, K, Mg, Cu, Mn and C) were key for kernel's growth and development, with N, P, K, Cu and Mn contents determining 74.0% the yield traits. The transport characteristics of these nutrients from root, leaves to the kernel had synergistic and antagonistic effects. Increasing oil production and unsaturated fatty acid content can be accomplished in two ways: one through increasing N, P, Mg, and Zn contents of leaves by applying corresponding N, P, Mg, Zn foliar fertilizers, while the other through maintaining proper soil moisture content by applying Zn fertilizer in the surface layer and Mg and Ca fertilizer in deep gully.

CONCLUSION

Soil type controlled nutrient absorption by soil pH, water content and total N, P and Fe content. There were synergistic and antagonistic effects on the inter-organ transport of nutrient elements, ultimately affecting N, P, K, Cu and Mn contents in kernel, which determined the yield and oil composition of C. oleifera.

Key factors selection on adolescents with non-suicidal self-injury: A support vector machine based approach

Comparing a family structure to a company, one can often think of parents as leaders and adolescents as employees. Stressful family environments and anxiety levels, depression levels, personality disorders, emotional regulation difficulties, and childhood trauma may all contribute to non-suicidal self-injury (NSSI) behaviors. We presented a support vector machine (SVM) based method for discovering the key factors among mazy candidates that affected NSSI in adolescents. Using SVM as the base learner, and the binary dragonfly algorithm was used to find the feature combination that minimized the objective function, which took into account both the prediction error and the number of selected variables. Unlike univariate model analysis, we used a multivariate model to explore the risk factors, which better revealed the interactions between factors. Our research showed that adolescent education level, anxiety and depression level, borderline and avoidant personality traits, as well as emotional abuse and physical neglect in childhood, were associated with mood disorders in adolescents. Furthermore, gender, adolescent education level, physical abuse in childhood, non-acceptance of emotional responses, as well as paranoid, borderline, and histrionic personality traits, were associated with an increased risk of NSSI. These findings can help us make better use of artificial intelligence technology to extract potential factors leading to NSSI in adolescents from massive data, and provide theoretical support for the prevention and intervention of NSSI in adolescents.