Artificial Intelligence in Monitoring Inflammatory Bowel Disease: History
Please note this is an old version of this entry, which may differ significantly from the current revision.
Contributor: , , , , , , ,

Crohn’s disease and ulcerative colitis remain debilitating disorders, characterized by progressive bowel damage and possible lethal complications. The growing number of applications for artificial intelligence in gastrointestinal endoscopy has already shown great potential, especially in the field of neoplastic and pre-neoplastic lesion detection and characterization, and is under evaluation in the field of inflammatory bowel disease management. The application of artificial intelligence in inflammatory bowel diseases can range from genomic dataset analysis and risk prediction model construction to the disease grading severity and assessment of the response to treatment using machine learning. 

  • artificial intelligence
  • automated diagnosis
  • inflammatory bowel disease

1. Understanding the Role of Artificial Intelligence in Gastroenterology

Advances in AI are driving important changes in medicine, and it is expected to provide, in the near future, significant improvements in patient care across a wide range of clinical settings [1]. AI has the ability to analyze large amounts of complex data at a significantly faster pace than humans, highlighting details that might be overlooked by the human eye, ensuring a precise and objective evaluation of the data [2]. AI applications include machine learning, neural networks, and deep learning. The fundamental principle is machine learning (ML), which is defined as the ability to automatically build mathematical algorithms from the input of raw training data in order to make decisions in new circumstances without human surveillance [3]. They can learn from experience, without being specifically programmed.
Deep learning (DL) is a fast-growing machine-learning method which has become the dominant approach for recent work in the ML field in recent years. Convolutional neural networks (CNNs), inspired by the neural network of the human brain, can enable a fast and accurate image discrimination and video analysis [4]. These applications of AI can be used in upper gastrointestinal endoscopy, such as the assessment of early gastric cancer, the identification of H. pylori, dysplasia in Barrett’s esophagus or colonoscopy, for colorectal polyp detection, and for assessing advanced neoplasia in colonic polyp or endocytoscopy to predict persistent histological inflammation in inflammatory bowel disease, allowing for breakthroughs in medical imaging recognition [5][6].
Computer-aided diagnosis (CAD) systems have been recently introduced in clinical practice (EndoBrain, GI Genius, Discovery, Endo-Aid, CAD EYE, Endo-screener or Wise vision.), providing the real-time detection and diagnosis of endoscopic lesions, acting as a quality controller and training vector for endoscopists [7]. The main advantages offered by CAD systems compared to traditional imaging methods are a more comprehensive imaging information compiling, better reproducibility, and the ability to implement an automatic selection of the region of interest.
CAD EYETM (Fujifilm, Tokyo, Japan) is the first CAD system to combine computer-aided detection (CADe), which detects gastrointestinal lesions, and computer-aided diagnosis (CADx), which characterizes gastrointestinal lesions on the same platform, demonstrating a better performance than the human eye [8]. CADe uses LCI to enlighten differences in color in the red zone and CADx uses BLI, which varies the light emission ratios of multiple lights with different wavelengths to distinguish polyps by intensifying minute vessels and structures in the mucosa [9]. A retrospective trial of colorectal polyps evaluated its effectiveness by using endoscopic images obtained from seven centers as validation images. The detection sensitivities of white light imaging (WLI) and linked color imaging (LCI) for the CADe system were 94.5% and 96%. The accuracy of WLI and blue light imaging (BLI) in CADx was 93.2% and 94.9% [8]. However, to date, the CAD EYE system can only be used to evaluate colorectal lesions, which it can only classify as neoplastic or hyperplastic, with further applications currently under development (such as diagnosis of cancer invasion depth, prediction of metastasis, and recurrence) [10].

2. Potential Applications of AI in IBD

In IBD, the endoscopic assessment of disease extension and severity, as well as mucosal healing and the early detection of neoplasia, represent key factors in ensuring adequate patient management [11][12]. Emerging as a valuable tool in IBD diagnosis and management, artificial intelligence offers the possibility of the simultaneous analysis of miscellaneous biological data by permitting a large-volume input for machine learning models, such as cross-sectional imaging, endoscopic and histologic imaging, inflammation biomarkers, as well as gut microbiota composition and gene expression [13][14][15]. ML algorithms can learn relevant features from existing patient databases and compare them to the known outcomes, which can, in turn, be used to predict the patient’s prognosis. As the application areas of AI in IBD will continue to expand, one significant area of interest is represented by the long term follow-up of these patients, including the prediction of the treatment response and relapse as well as screening for IBD-associated colonic neoplasia.

3. The Role of Artificial Intelligence in Screening for Early Neoplasia in IBD

The association of longstanding inflammatory bowel diseases (IBDs), especially ulcerative colitis, with colorectal cancer is already well acknowledged. A young age at diagnosis, longer disease duration, higher inflammatory burden, greater extent, family history of colorectal cancer (CRC), and association with primary sclerosing cholangitis are the risk factors for neoplasia development [16][17]. Persistent levels of inflammation, with repeated flares of disease, can lead to the oncogenic insult of the colonic epithelium in these patients [18][19].
Colonoscopic findings in IBD surveillance can be classified as polypoid or nonpolypoid lesions and invisible dysplasia. Sporadic adenomas may appear as discrete, visible lesions, but they also appear as a “field cancerization” that develops in IBD when the entire mucosa is chronically inflamed, increasing the risk of synchronous and metachronous neoplasms [20]. The current guidelines (European Crohn’s and Colitis Organisation—ECCO, American Gastroenterological Association—AGA, and the British Society of Gastroenterology—BSG) recommend that surveillance colonoscopies should begin in 8–10 years after the onset of the symptoms, and should be done at 1, 2–3, and 5 years in high-, intermediate-, and low-risk patients, respectively [21][22][23][24][25]. Patients with colonic stenosis detected within 5 years after diagnosis should have a low threshold for cancer screening, as they are at a high risk of developing CRC and a colonoscopy should be performed annually [26].
Current surveillance strategies include high-definition endoscopy and chromoendoscopy, with indigo-carmine or methylene blue, and targeted biopsies of abnormal appearing mucosa [27]. Virtual chromoendoscopy is considered a suitable alternative to dye chromoendoscopy when using high-definition endoscopy [28][29]. If virtual or dye-based chromoendoscopy are not available, non-targeted biopsies every 10 cm should be taken and additional biopsies should be collected from areas of previously known dysplasia or poor mucosal visibility.
One meta-analysis [27] revealed that chromoendoscopy increases the yield of dysplasia compared with white-light endoscopy (absolute risk increase = 6% (3–9%)). However, conventional chromoendoscopy is a time-consuming and operator-dependent method, requiring an adequate bowel preparation and mucosal healing [30].
Despite the development of high-definition endoscopes and dye-based chromoendoscopy, the mortality and morbidity related to IBD neoplasia remains high [31][32]. In order to address some of the limitations in the current strategies of neoplasia surveillance, such as a high variability in disease presentation and the associated risk, imperfect endoscopic techniques, or a high susceptibility to interobserver variability in lesion assessment, artificial intelligence was explored to aid traditional colonoscopy [33]. Many AI algorithms were developed in order to alert the endoscopist of neoplastic lesions in real-time by using visual and auditory signals during the colonoscopy [34].
With this purpose, CNN were trained to detect neoplastic lesions in the non-IBD population, using still images annotated by expert endoscopists, proving a good sensitivity and specificity for lesion detection. Hassan et al. showed that the GI-Genius Medtronic system reached a sensibility of 99.7% in polyps’ detection [35], while another recent computer-aided detection system demonstrated an increased sensitivity for all, diminutive, protruded, and flat polyps (98%, 98.3% and 97%, respectively) [36]. However, its use for the detection of dysplasia in patients with IBD has not been concluded. Fukunag reported the case of a high-grade dysplasia flat lesion detected by the EndoBRAIN system in a patient with longstanding colitis [37], which was successfully removed via submucosal dissection.
In IBD patients, CADe/CADx systems are useful in the detection and differentiation of colon polyps/lesions and for dysplasia surveillance [38]. Additionally, virtual chromoendoscopy (VCE) was recently evaluated for the potential role of the identification of dysplastic lesions and it seemed to have a similar detection rate of dysplasia in IBD as high-definition WLE (HD-WLE) [39].

4. AI in Aiding IBD Treatment—Disease Progression Prediction/Response to Treatment

In more recent years, the goal of IBD treatment have evolved from traditional clinical remission to a more integrated and complete mucosal healing and deep remission [40][41][42].
Despite ongoing development in IBD therapies, with newer drugs ranging from biologics that interfere with the inflammatory cascade (anti-tumor necrosis factor-α, anti-interleukin-12/23, anti-integrins) to small molecules (JAK-inhibitors) [43][44], clinicians still lack the adequate tools for predicting the treatment response, thus adequately matching patients and drugs, thereby improving the patient outcomes and reducing the financial burden of these treatments [45]. Since the concept of artificial intelligence was popularized, its applicability in disease progression and treatment response prediction has become a major subject of interest. Researchers have used random forest (RF) classifiers on data gathered from hospital databases in order to predict the response to therapy [46]. Waljee and colleagues have conducted many studies in this domain [47][48][49][50][51][52]. In one of the first studies, they attempted to identify three different outcomes in patients treated with thiopurines (clinical response, thiopurine non-adherence, and patients who were most likely to shunt from 6-thioguanine nucleotide [6-TGN] to 6-methylmercaptopurine [6-MMP] metabolites). The models were efficient in predicting the outcomes, with an AUC of 0.86 [95% CI 0.79–0.92] for the clinical response [47]. In a more recent study, they have developed an algorithm using the same cohort and similar outcomes, except they focused on the objective response (defined as absence of intestinal inflammation) with an AUC of 0.79 (95% CI 0.78–0.81). Some of the most important variables included: hemoglobin, lymphocytes, hematocrit, neutrophils, and platelets [48].
Based on the data collected from large clinical trials, prediction models regarding the response to biological treatment (particularly to vedolizumab and ustekinumab) were evaluated [49][50][51][52]. Vedolizumab is a gut selective alpha-4-beta-7 integrin therapy approved for the treatment of ulcerative colitis (UC) as well as Crohn’s disease (CD) [49]. Waljee et al. have used three different RF models (baseline, week 6, and simplified) in order to predict corticosteroid-free Vedolizumab remission in CD patients (defined as no corticosteroid use and CRP reduction to ≤5 mg/dL) at week 52. Of these three, the Week 6 model and the simplified week 6 model (HGB * ALB * VDZ level)/(CRP * weight in kg) had the best accuracy (AUC 0.75; 95% CI 0.64–0.86 and AUC 0.75; 95% CI 0.70–0.81, respectively). Some of the most important variables used for the week 6 model were: CRP, slope of Vedolizumab level, hemoglobin, albumin, the vedolizumab level, and slope of CRP. Patients predicted to be in corticosteroid-free remission by the week 6 model achieved the endpoint in almost one third of cases (35.8%), while those predicted to fail succeeded in 6.7% of cases, therefore allowing the user to identify the majority of patients that are unlikely to achieve remission by week 6 [50].
In another study, the same author used baseline data and week 6 data from patients with UC treated with Vedolizumab (GEMINI II) and developed two models to predict corticosteroid-free remission at week 52, defined as no corticosteroid use and an endoscopic Mayo subscore of 0 or 1. A simplified week 6 model was also created, using a fecal calprotectin cut-off of under 234 μg/g to predict the composite outcome. However, the week 6 model proved to have a higher accuracy, with an AUC of 0.73 [95% CI: 0.65–0.82] [51].
Last but not least, the most recent study conducted by Waljee and colleagues focuses on predicting the biological remission at week 42 (defined as the CRP level under 5 mg/dL) for CD patients treated with ustekinumab in UNITI and IM-UNITI studies. They developed two models: one baseline and one for week 8, and also a simplified version, week 6 albumin-to-CRP ratio. The AUC for the week 8 model was 0.78 (95% CI, 0.69–0.87), with a similar value for the simplified model (0.76 (95% CI, 0.71–0.82)); the baseline levels of Ustekinumab did not improve the performance of the prediction model [52].

This entry is adapted from the peer-reviewed paper 10.3390/diagnostics13040735


  1. Davenport, T.; Kalakota, R. The potential for artificial intelligence in healthcare. Futur. Health J. 2019, 6, 94–98.
  2. Sinonquel, P.; Eelbode, T.; Bossuyt, P.; Maes, F.; Bisschops, R. Artificial intelligence and its impact on quality improvement in upper and lower gastrointestinal endoscopy. Dig. Endosc. 2020, 33, 242–253.
  3. Okagawa, Y.; Abe, S.; Yamada, M.; Oda, I.; Saito, Y. Artificial Intelligence in Endoscopy. Dig. Dis. Sci. 2022, 67, 1553–1572.
  4. Choudhary, K.; DeCost, B.; Chen, C.; Jain, A.; Tavazza, F.; Cohn, R.; Park, C.W.; Choudhary, A.; Agrawal, A.; Billinge, S.J.K.; et al. Recent advances and applications of deep learning methods in materials science. npj Comput. Mater. 2022, 8, 59.
  5. Pannala, R.; Krishnan, K.; Melson, J.; Parsi, M.A.; Schulman, A.R.; Sullivan, S.; Trikudanathan, G.; Trinidade, A.J.; Watson, R.R.; Maple, J.T.; et al. Emerging role of artificial intelligence in GI endoscopy. Gastrointest. Endosc. 2020, 92, 1151–1152.
  6. Chen, G.; Shen, J. Artificial Intelligence Enhances Studies on Inflammatory Bowel Disease. Front. Bioeng. Biotechnol. 2021, 9, 635764.
  7. Rex, D.K.; Mori, Y.; Sharma, P.; Lahr, R.E.; Vemulapalli, K.C.; Hassan, C. Strengths and Weaknesses of an Artificial Intelligence Polyp Detection Program as Assessed by a High-Detecting Endoscopist. Gastroenterology 2022, 163, 354–358.
  8. Kamitani, Y.; Nonaka, K.; Isomoto, H. Current Status and Future Perspectives of Artificial Intelligence in Colonoscopy. J. Clin. Med. 2022, 11, 2923.
  9. van der Sommen, F.; de Groof, J.; Struyvenberg, M.; van der Putten, J.; Boers, T.; Fockens, K.; Schoon, E.J.; Curvers, W.; de With, P.; Mori, Y.; et al. Machine learning in GI endoscopy: Practical guidance in how to interpret a novel field. Gut 2020, 69, 2035–2045.
  10. Kudo, S.-E.; Ichimasa, K.; Villard, B.; Mori, Y.; Misawa, M.; Saito, S.; Hotta, K.; Saito, Y.; Matsuda, T.; Yamada, K.; et al. Artificial Intelligence System to Determine Risk of T1 Colorectal Cancer Metastasis to Lymph Node. Gastroenterology 2021, 160, 1075–1084.e2.
  11. Maaser, C.; Sturm, A.; Vavricka, S.R.; Kucharzik, T.; Fiorino, G.; Annese, V.; Calabrese, E.; Baumgart, D.C.; Bettenworth, D.; Nunes, P.B.; et al. ECCO-ESGAR Guideline for Diagnostic Assessment in IBD Part 1: Initial diagnosis, monitoring of known IBD, detection of complications. J. Crohns Colitis 2019, 13, 144–164.
  12. Sturm, A.; Maaser, C.; Calabrese, E.; Annese, V.; Fiorino, G.; Kucharzik, T.; Vavricka, S.R.; Verstockt, B.; van Rheenen, P.; Tolan, D.; et al. ECCO-ESGAR Guideline for Diagnostic Assessment in IBD Part 2: IBD scores and general principles and technical aspects. J. Crohns Colitis 2019, 13, 273–284.
  13. Wei, Z.; Wang, W.; Bradfield, J.; Li, J.; Cardinale, C.; Frackelton, E.; Kim, C.; Mentch, F.; Van Steen, K.; Visscher, P.M.; et al. Large Sample Size, Wide Variant Spectrum, and Advanced Machine-Learning Technique Boost Risk Prediction for Inflammatory Bowel Disease. Am. J. Hum. Genet. 2013, 92, 1008–1012.
  14. Chen, P.; Zhou, G.; Lin, J.; Li, L.; Zeng, Z.; Chen, M.; Zhang, S. Serum Biomarkers for Inflammatory Bowel Disease. Front. Med. 2020, 7, 123.
  15. Isakov, O.; Dotan, I.; Ben-Shachar, S. Machine Learning-Based Gene Prioritization Identifies Novel Candidate Risk Genes for Inflammatory Bowel Disease. Inflamm. Bowel Dis. 2017, 23, 1516–1523.
  16. Yashiro, M. Ulcerative colitis-associated colorectal cancer. World J. Gastroenterol. 2014, 20, 16389–16397.
  17. Herszenyi, L.; Miheller, P.; Tulassay, Z. Carcinogenesis in inflammatory bowel disease. Dig. Dis. 2007, 25, 267–269.
  18. Marabotto, E.; Kayali, S.; Buccilli, S.; Levo, F.; Bodini, G.; Giannini, E.G.; Savarino, V.; Savarino, E.V. Colorectal Cancer in Inflammatory Bowel Diseases: Epidemiology and Prevention: A Review. Cancers 2022, 14, 4254.
  19. Scarpa, M.; Castagliuolo, I.; Castoro, C.; Pozza, A.; Scarpa, M.; Kotsafti, A.; Angriman, I. Inflammatory colonic carcinogenesis: A review on pathogenesis and immunosurveillance mechanisms in ulcerative colitis. World J. Gastroenterol. 2014, 20, 6774–6785.
  20. Ang, T.L.; Wang, L.M. Artificial intelligence for the diagnosis of dysplasia in inflammatory bowel diseases. J. Gastroenterol. Hepatol. 2022, 37, 1469–1470.
  21. Wallace, M.B.; Sharma, P.; Bhandari, P.; East, J.; Antonelli, G.; Lorenzetii, R.; Vieth, M.; Speranza, I.; Spadaccini, M.; Desai, M.; et al. Impact of Artificial Intelligence on Miss Rate of Colorectal Neoplasia. Gastroenterology 2022, 163, 295–304.
  22. Magro, F.; Gionchetti, P.; Eliakim, R.; Ardizzone, S.; Armuzzi, A.; Barreiro-de Acosta, M.; Burisch, J.; Gecse, K.B.; Hart, A.L.; Hindryckx, P.; et al. Third European Evidence-based Consensus on Diagnosis and Management of Ulcerative Colitis. Part 1: Definitions, Diagnosis, Extra-intestinal Manifestations, Pregnancy, Cancer Surveillance, Surgery, and Ileo-anal Pouch Disorders. J. Crohns Colitis 2017, 11, 649–670.
  23. Rubin, D.T.; Ananthakrishnan, A.N.; Siegel, C.A.; Sauer, B.G.; Long, M.D. ACG Clinical Guideline: Ulcerative Colitis in Adults. Am. J. Gastroenterol. 2019, 114, 384–413.
  24. Lamb, C.A.; Kennedy, N.A.; Raine, T.; Hendy, P.A.; Smith, P.J.; Limdi, J.K.; Hayee, B.; Lomer, M.C.E.; Parkes, G.C.; Selinger, C.; et al. British Society of Gastroenterology consensus guidelines on the management of inflammatory bowel disease in adults. Gut 2019, 68 (Suppl. 3), s1–s106.
  25. Shah, S.C.; Itzkowitz, S.H. Colorectal Cancer in Inflammatory Bowel Disease: Mechanisms and Management. Gastroenterology 2022, 162, 715–730.
  26. Marques, K.F.; Marques, A.F.; Lopes, M.A.; Beraldo, R.F.; Lima, T.B.; Sassaki, L.Y. Artificial intelligence in colorectal cancer screening in patients with inflammatory bowel disease. Artif. Intell. Gastrointest. Endosc. 2022, 3, 1–8.
  27. Laine, L.; Kaltenbach, T.; Barkun, A.; McQuaid, K.R.; Subramanian, V.; Soetikno, R. SCENIC Guideline Development Panel. SCENIC international consensus statement on surveillance and management of dysplasia in inflammatory bowel disease. Gastroenterology 2015, 148, 639–651.
  28. Murthy, S.K.; Feuerstein, J.D.; Nguyen, G.C.; Velayos, F.S. AGA clinical practice update on endoscopic surveillance and management of colorectal dysplasia in inflammatory bowel disease: Expert review. Gastroenterology 2021, 161, 1043–1051.
  29. Bisschops, R.; Bessissow, T.; Joseph, J.A.; Baert, F.; Ferrante, M.; Ballet, V.; Willekens, H.; Demedts, I.; Geboes, K.; De Hertogh, G.; et al. Chromoendoscopy versus narrow band imaging in UC: A prospective randomised controlled trial. Gut 2018, 67, 1087–1094.
  30. Shukla, R.; Salem, M.; Hou, J.K. Use and barriers to chromoendoscopy for dysplasia surveillance in inflammatory bowel disease. World J. Gastrointest. Endosc. 2017, 9, 359–367.
  31. Jess, T.; Rungoe, C.; Peyrin-Biroulet, L. Risk of colorectal cancer in patients with ulcerative colitis: A meta-analysis of population-based cohort studies. Clin. Gastroenterol. Hepatol. 2012, 10, 639–645.
  32. Farraye, F.; Odze, R.D.; Eaden, J.; Itzkowitz, S.H.; McCabe, R.P.; Dassopoulos, T.; Lewis, J.D.; Ullman, T.A.; James, T.; McLeod, R.; et al. AGA medical position statement on the diagnosis and management of colorectal neoplasia in inflammatory bowel disease. Gastroenterology 2010, 138, 738–745.
  33. Kohli, A.; Holzwanger, E.A.; Levy, A.N. Emerging use of artificial intelligence in inflammatory bowel disease. World J. Gastroenterol. 2020, 26, 6923–6928.
  34. Alagappan, M.; Brown, J.R.G.; Mori, Y.; Berzin, T.M. Artificial intelligence in gastrointestinal endoscopy: The future is almost here. World J. Gastrointest. Endosc. 2018, 10, 239–249.
  35. Hassan, C.; Wallace, M.B.; Sharma, P.; Maselli, R.; Craviotto, V.; Spadaccini, M.; Repici, A. New artificial intelligence system: First validation study versus experienced endoscopists for colorectal polyp detection. Gut 2020, 69, 799–800.
  36. Misawa, M.; Kudo, S.-E.; Mori, Y.; Hotta, K.; Ohtsuka, K.; Matsuda, T.; Saito, S.; Kudo, T.; Baba, T.; Ishida, F.; et al. Development of a computer-aided detection system for colonoscopy and a publicly accessible large colonoscopy video database (with video). Gastrointest. Endosc. 2020, 93, 960–967.
  37. Maeda, Y.; Kudo, S.E.; Ogata, N.; Misawa, M.; Mori, Y.; Mori, K.; Ohtsuka, K. Can artificial intelligence help to detect dysplasia in patients with ulcerative colitis? Endoscopy 2021, 53, E273–E274.
  38. Sundaram, S.; Choden, T.; Mattar, M.C.; Desai, S.; Desai, M. Artificial intelligence in inflammatory bowel disease endoscopy: Current landscape and the road ahead. Ther. Adv. Gastrointest. Endosc. 2021, 14, 26317745211017809.
  39. Leifeld, L.; Rogler, G.; Stallmach, A.; Schmidt, C.; Zuber-Jerger, I.; Hartmann, F.; Plauth, M.; Drabik, A.; Hofstadter, F.; Dienes, H.P.; et al. Detect Dysplasia Study Group. White-light or narrow-band imaging colonoscopy in surveillance of ulcerative colitis: A prospective multicenter study. Clin. Gastroenterol. Hepatol. 2015, 13, 1776–1781.
  40. Panaccione, R.; Colombel, J.-F.; Louis, E.; Peyrin-Biroulet, L.; Sandborn, W.J. Evolving definitions of remission in Crohn’s disease. Inflamm. Bowel Dis. 2013, 19, 1645–1653.
  41. Sandborn, W.J.; Hanauer, S.; Van Assche, G.; Panes, J.; Wilson, S.; Petersson, J.; Panaccione, R. Treating beyond symptoms with a view to improving patient outcomes in inflammatory bowel diseases. J. Crohns Colitis 2014, 8, 927–935.
  42. Neurath, M.F.; Travis, S.P. Mucosal healing in inflammatory bowel diseases: A systematic review. Gut 2012, 61, 1619–1635.
  43. Neurath, M.F. Current and emerging therapeutic targets for IBD. Nat. Rev. Gastroenterol. Hepatol. 2017, 14, 269–278.
  44. Weisshof, R.; El Jurdi, K.; Zmeter, N.; Rubin, D.T. Emerging Therapies for Inflammatory Bowel Disease. Adv. Ther. 2018, 35, 1746–1762.
  45. Yu, H.; MacIsaac, D.; Wong, J.J.; Sellers, Z.M.; Wren, A.A.; Bensen, R.; Kin, C.; Park, K.T. Market share and costs of biologic therapies for inflammatory bowel disease in the USA. Aliment. Pharmacol. Ther. 2018, 47, 364–370.
  46. Breiman, L. Random forests. Mach. Learn. 2001, 45, 5–32.
  47. Waljee, A.K.; Joyce, J.C.; Wang, S.; Saxena, A.; Hart, M.; Zhu, J.; Higgins, P.D. Algorithms outperform metabolite tests in predicting response of patients with inflammatory bowel disease to thiopurines. Clin. Gastroenterol. Hepatol. 2010, 8, 143–150.
  48. Waljee, A.K.; Sauder, K.; Patel, A.; Segar, S.; Liu, B.; Zhang, Y.; Zhu, J.; Stidham, R.W.; Balis, U.; Higgins, P.D. Machine Learning Algorithms for Objective Remission and Clinical Outcomes with Thiopurines. J. Crohns Colitis 2017, 11, 801–810.
  49. Sandborn, W.J.; Feagan, B.G.; Rutgeerts, P.; Hanauer, S.; Colombel, J.F.; Sands, B.E.; Lukas, M.; Fedorak, R.N.; Lee, S.; Bressler, B.; et al. Vedolizumab as induction and maintenance therapy for Crohn’s disease. N. Engl. J. Med. 2013, 369, 711–721.
  50. Waljee, A.K.; Liu, B.; Sauder, K.; Zhu, J.; Govani, S.M.; Stidham, R.W.; Higgins, P.D. Predicting Corticosteroid-Free Biologic Remission with Vedolizumab in Crohn’s Disease. Inflamm. Bowel Dis. 2018, 24, 1185–1192.
  51. Waljee, A.K.; Liu, B.; Sauder, K.; Zhu, J.; Govani, S.M.; Stidham, R.W.; Higgins, P.D. Predicting corticosteroid-free endoscopic remission with vedolizumab in ulcerative colitis. Aliment. Pharmacol. Ther. 2018, 47, 763–772.
  52. Waljee, A.K.; Wallace, B.I.; Cohen-Mekelburg, S.; Liu, Y.; Liu, B.; Sauder, K.; Stidham, R.W.; Zhu, J.; Higgins, P.D.R. Development and Validation of Machine Learning Models in Prediction of Remission in Patients With Moderate to Severe Crohn Disease. JAMA Netw. Open 2019, 2, e197386.
This entry is offline, you can click here to edit this entry!
Video Production Service