Scientific corner

Machine learning using clinical data at baseline predicts the medium-term efficacy of ustekinumab in patients with ulcerative colitis

Hiromu Morikubo, Ryuta Tojima, Tsubasa Maeda, Katsuyoshi Matsuoka, Minoru Matsuura, Jun Miyoshi, Satoshi Tamura & Tadakazu Hisamatsu Sci Rep 14, 4386 (2024).

Predicting the therapeutic response to biologics before administration is a key clinical challenge in ulcerative colitis (UC). We previously reported a model for predicting the efficacy of vedolizumab (VDZ) for UC using a machine-learning approach. Ustekinumab (UST) is now available for treating UC, but no model for predicting its efficacy has been developed. When applied to patients with UC treated with UST, our VDZ prediction model showed positive predictive value (PPV) of 56.3% and negative predictive value (NPV) of 62.5%. Given this limited predictive ability, we aimed to develop a UST-specific prediction model with clinical features at baseline including background factors, clinical and endoscopic activity, and blood test results, as we did for the VDZ prediction model. The top 10 features (Alb, monocytes, height, MCV, TP, Lichtiger index, white blood cell count, MCHC, partial Mayo score, and CRP) associated with steroid-free clinical remission at 6 months after starting UST were selected using random forest. The predictive ability of a model using these predictors was evaluated by fivefold cross-validation. Validation of the prediction model with an external cohort showed PPV of 68.8% and NPV of 71.4%. Our study suggested the importance of establishing a drug-specific prediction model.

Scientific corner

P582 Combination of granulocyte–monocyte apheresis and ustekinumab: multicentre and retrospective study

I Rodríguez-Lago, C Herrera-deGuise, M Boscá-Watts, C Rodríguez, E Leo, M Calvo, F Cañete, S Chacón, C Cuarán, A Elorza, E Guerra, E Iglesias, D Sánchez, M Barreiro-de Acosta, D Ginard, J L Cabriada Journal of Crohn’s and Colitis, Volume 18, Issue Supplement_1, January 2024, Page i1135,

Granulocyte–monocyte apheresis (GMA) selectively removes activated leukocytes and immune mediators, and it has shown to be safe and effective in treating ulcerative colitis (UC). Previous reports have also described its combination with biologics, mainly with anti-TNF.

The aim of our study was to evaluate the clinical efficacy and safety of combining GMA after primary non-response (PNR) or loss of response (LOR) to ustekinumab (UST) in patients with UC. A retrospective, multicentric study was performed in 12 IBD Units, including all patients with refractory UC who received combined GMA plus UST. The number of GMA sessions, its frequency, filtered blood volume and time of each session were compiled, along with the clinical data. Efficacy was assessed 1 and 6 months after finishing the GMA by partial Mayo score, CRP and faecal calprotectin. Data regarding UST intensification, need for new immunomodulators/biologics and surgery were also compiled. Descriptive statistics and non-parametric tests were used in the statistical analysis.

Nineteen patients were included (15 UC, 2 Crohn’s disease, 2 unclassified IBD; median age 48 years (IQR, 36-63); 68% male). At baseline, 78% were receiving steroids and 23% immunomodulators. Most patients (89%) had prior exposure to anti-TNF agents and 53% to vedolizumab. Baseline Mayo score was 6.5 (IQR, 5-7), with a median CRP of 9 mg/L (IQR, 4.8-20.8) and faecal calprotectin 1,612 mg/kg (IQR, 873-4,152). GMA was started mostly after PNR in 83%, the median number of GMA sessions was 16 (IQR, 11-27) and 50% of patients started maintenance GMA. Partial Mayo score significantly decreased 6 months after the last GMA session (p=0.019). During follow-up, 27% started a new biologic therapy and 13% required surgery. 64% of patients under steroids at baseline were able to stop them. Adverse events were reported in 5% of patients.

GMA can safely recapture the response to UST in refractory patients after PNR or LOR to this drug.

Scientific corner

Real-world effectiveness and safety of advanced therapies for the treatment of moderate-to-severe ulcerative colitis (UC): evidence from a systematic literature review (SLR)

Makoto Naganuma 1Taku Kobayashi 2Reiko Kunisaki 3Katsuyoshi Matsuoka 4Shojiro Yamamoto 5Ami Kawamoto 6Daisuke Saito 7Kosaku Nanki 8Kazuyuki Narimatsu 9Hisashi Shiga 10Motohiro Esaki 11Shinichiro Yoshioka 12Shingo Kato 13Masayuki Saruta 14Shinji Tanaka 15Eriko Yasutomi 16Kaoru Yokoyama 17Kei Moriya 18Yoshikazu Tsuzuki 19Makoto Ooi 20Mikihiro Fujiya 21Atsushi Nakazawa 22Takayuki Abe 23Tadakazu Hisamatsu 6Japanese UC Study Group J Gastroenterol. 2023 Dec;58(12):1198-1210. doi: 10.1007/s00535-023-02048-w. 

Background: This multicenter observational cohort study aimed to evaluate the utilization and short-term efficacy of advanced therapy (AT) in hospitalized patients with acute severe ulcerative colitis (ASUC).

Methods: In total, 221 patients with ASUC were enrolled between August 2020 and July 2021. The primary endpoint was clinical remission (CR, defined as a patient-reported outcome score < 2 with no blood in the stool) rate on Day 7 and 14 in hospitalized patients who received corticosteroids (CS) and AT.

Results: Among patients with ASUC, 120 and 101 patients received CS or any AT as first-line treatment, respectively. The CR rates on Day 7 and 14 were 22.5% and 35.0%, respectively, in hospitalized patients who received CS as first-line treatment. Most patients who used ATs had CS-dependent or frequent recurrences. Eight different ATs (apheresis, tacrolimus, infliximab, golimumab, tofacitinib, vedolizumab, ustekinumab, and cyclosporine) were used as first-line treatment in patients with ASUC, and the CR rates on Day 7 and 14 were 16.8% and 29.7%, respectively. Twenty-five patients received the second ATs after hospitalizations, and the CR rates on Day 7 and 14 were 0% and 12%, respectively. The CR rates on Day 14 were significantly higher in patients who changed to AT than in those whose dose of CS increased (34.0% vs 10.7%, p = 0.020) among patients who had already used CS before hospitalization.

Conclusion: Most first-use ATs were effective for patients with ASUC, while second-use ATs might have had limited benefits in inducing CR. These findings may contribute to considerations for the management of hospitalized patients.

Real-world efficacy and safety of advanced therapies in hospitalized patients with ulcerative colitis – PubMed (

Real-world efficacy and safety of advanced therapies in hospitalized patients with ulcerative colitis | Journal of Gastroenterology (

Scientific corner

Severe and refractory gastrointestinal toxicity due to immune checkpoint inhibitors: clinical experience in a tertiary referral hospital

Elena Céspedes Martínez, Virginia Robles Alonso, Claudia Herrera-De Guise, Luis Mayorga, Francesc Casellas, María Roca-Herrera, Natalia Borruel, Rev Esp Enferm Dig 2023;115(10):567-573

Introduction: immune checkpoint inhibitors (ICI) are increasingly used to treat several types of cancer. These drugs lead to a wide range of toxicities. Immune-related gastrointestinal adverse events are common and potentially severe. In this manuscript, we recount the real clinical experience in a tertiary center. Methods: a retrospective and observational study was conducted in adult patients under ICI treatment. Included patients had been referred to the Gastrointestinal Service of Hospital Universitario Vall d’Hebron for evaluation of severe toxicities, from January 2017 to January 2020, for whom the clinical, epidemiological and evolutive data were collected. Results: a total of 18 patients were included. Fifty-five percent received anti-programmed cell death protein 1 (PD-1)/anti-programmed death-ligand 1 (anti PD-L1), 11 % received anti-cytotoxic T lymphocyte antigen 4 (CTLA-4) and 33 % received both treatments. The toxicities were manifested as enterocolitis, microscopic colitis and gastritis. Upper gastrointestinal endoscopy was performed in seven patients; all were proved to have histological changes on duodenum biopsies. Treatment was stopped in all patients and steroids were initiated. Sixty-six per cent achieved clinical remission with steroids. Five patients received anti-TNF treatment (infliximab). Only one of the five had responded. Two anti-TNF refractory patients received ustekinumab, with an appropriate clinical response. One patient received apheresis granulocyte as concomitant treatment. A patient with a steroid-dependent course started vedolizumab. Three patients had other immune-related adverse events. Conclusion: gastrointestinal immune-related adverse events are acquiring a higher profile in daily practice and gastroenterologists play an even greater role in the management of these patients.

Severe and refractory gastrointestinal toxicity due to immune checkpoint inhibitors: clinical experience in a tertiary referral hospital – PubMed (

REED – Revista Española de Enfermedades Digestivas

Scientific corner

SY4-03 The efficacy of combination therapy of intensive GMA with biologics or a JAK inhibitor for refractory inflammatory bowel disease

Satoshi Tanida

poster at ISFA 2019 pag 56

Background and Aim: A monotherapy with intensive GMA, biologics or a JAK inhibitor are limited in patients with intractable Crohn’s disease (CD) or ulcerative colitis (UC). We retrospectively evaluated the 10- and 52-week efficacy and safety of combination therapy of intensive GMA with biologics or a JAK inhibitor for intractable UC or CD.
Method: A combination of intensive GMA (2 sessions a week, total 10 times) with tofacitinib (TOF) for active UC was performed and that of intensive GMA with ustekinumab (UST) for active CD was done. Results: Of 6 consecutive UC patients receiving a combination therapy of TOF (20 mg daily for 8 weeks as induction therapy and subsequently 10 mg daily) plus intensive GMA for moderately-to-severely active UC and loss of response to corticosteroids, azathioprine, and/ or biologic therapies, 67% (4 cases) displayed clinical remission according to Mayo score and 100% displayed mucosal healing at 10 weeks. A temporary increase in CPK were seen. Of 5 consecutive CD patients receiving a combination therapy of ustekinumab (every 8 weeks) plus intensive GMA for moderately-to-severely active CD and loss of response to corticosteroids, azathioprine, and/or biologic therapies, 75% displayed cumulative steroid-free clinical remission at 10 weeks and did such remission over 52 weeks under subsequent maintenance monotherapy of UST. The mean CDAI at baseline were 257. Its values at 10 and 52 weeks after the combination therapy with UST plus intensive GMA were 48 and 68, respectively. One case showed mucosal healing at 52 weeks according to SES-CD. No adverse events were observed. Conclusions: Combination therapy of intensive GMA with biologics or a JAK inhibitor appeared to be effective and safe for refractory UC or CD.

Scientific corner

Combination Therapy With Intensive Granulocyte and Monocyte Adsorptive Apheresis Plus Ustekinumab in Patients With Refractory Crohn’s Disease

Satoshi Tanida 1Tsutomu Mizoshita 1Keiji Ozeki 1Takahito Katano 1Mamoru Tanaka 1Hirotada Nishie 1Takaya Shimura 1Yasuyuki Okamoto 1Eiji Kubota 1Hiromi Kataoka 1Takashi Joh 1 , Ther Apher Dial. 2018 Jun;22(3):295-300.

Thus, combination therapy with intensive granulocyte and monocyte absorptive apheresis plus ustekinumab appeared to represent a safe and effective intervention for inducing clinical remission.

Contact UsFor more information

Contact Us