1
|
Koustenis K, Dovrolis N, Viazis N, Ioannou A, Bamias G, Karamanolis G, Gazouli M. Insights into Therapeutic Response Prediction for Ustekinumab in Ulcerative Colitis Using an Ensemble Bioinformatics Approach. Int J Mol Sci 2024; 25:5532. [PMID: 38791570 PMCID: PMC11122545 DOI: 10.3390/ijms25105532] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/02/2024] [Revised: 05/07/2024] [Accepted: 05/16/2024] [Indexed: 05/26/2024] Open
Abstract
INTRODUCTION Optimizing treatment with biological agents is an ideal goal for patients with ulcerative colitis (UC). Recent data suggest that mucosal inflammation patterns and serum cytokine profiles differ between patients who respond and those who do not. Ustekinumab, a monoclonal antibody targeting the p40 subunit of interleukin (IL)-12 and IL-23, has shown promise, but predicting treatment response remains a challenge. We aimed to identify prognostic markers of response to ustekinumab in patients with active UC, utilizing information from their mucosal transcriptome. METHODS We performed a prospective observational study of 36 UC patients initiating treatment with ustekinumab. Colonic mucosal biopsies were obtained before treatment initiation for a gene expression analysis using a microarray panel of 84 inflammatory genes. A differential gene expression analysis (DGEA), correlation analysis, and network centrality analysis on co-expression networks were performed to identify potential biomarkers. Additionally, machine learning (ML) models were employed to predict treatment response based on gene expression data. RESULTS Seven genes, including BCL6, CXCL5, and FASLG, were significantly upregulated, while IL23A and IL23R were downregulated in non-responders compared to responders. The co-expression analysis revealed distinct patterns between responders and non-responders, with key genes like BCL6 and CRP highlighted in responders and CCL11 and CCL22 in non-responders. The ML algorithms demonstrated a high predictive power, emphasizing the significance of the IL23R, IL23A, and BCL6 genes. CONCLUSIONS Our study identifies potential biomarkers associated with ustekinumab response in UC patients, shedding light on its underlying mechanisms and variability in treatment outcomes. Integrating transcriptomic approaches, including gene expression analyses and ML, offers valuable insights for personalized treatment strategies and highlights avenues for further research to enhance therapeutic outcomes for patients with UC.
Collapse
Affiliation(s)
- Kanellos Koustenis
- Gastroenterology Department, Evangelismos-Polykliniki General Hospital, 115 27 Athens, Greece; (K.K.); (N.V.)
| | - Nikolas Dovrolis
- Laboratory of Biology, Department of Basic Medical Sciences, Medical School, National and Kapodistrian University of Athens, Michalakopoulou 176, 115 27 Athens, Greece;
| | - Nikos Viazis
- Gastroenterology Department, Evangelismos-Polykliniki General Hospital, 115 27 Athens, Greece; (K.K.); (N.V.)
| | | | - Giorgos Bamias
- GI-Unit, 3rd Academic Department of Internal Medicine, National and Kapodistrian University of Athens, Sotiria Hospital, 115 27 Athens, Greece;
| | - George Karamanolis
- Gastroenterology Unit, Second Department of Surgery, Aretaieio Hospital, Medical School, National and Kapodistrian University of Athens, 115 27 Athens, Greece;
| | - Maria Gazouli
- Laboratory of Biology, Department of Basic Medical Sciences, Medical School, National and Kapodistrian University of Athens, Michalakopoulou 176, 115 27 Athens, Greece;
| |
Collapse
|
2
|
Ando K, Fujiya M, Ueno N, Ito T, Maemoto A, Nasuno M, Tanaka H, Sakurai K, Katsurada T, Orii F, Ashida T, Motoya S, Kazama T, Yokoyama Y, Hirayama D, Nakase H. Effectiveness and Persistency of Ustekinumab Treatment for Ulcerative Colitis: A Phoenix retrospective Cohort Study. CROHN'S & COLITIS 360 2024; 6:otae024. [PMID: 38711858 PMCID: PMC11071518 DOI: 10.1093/crocol/otae024] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/31/2024] [Indexed: 05/08/2024] Open
Abstract
Background Real-world data regarding ustekinumab (UST) for ulcerative colitis (UC) particularly in biologics-naïve patients is currently limited. This study aimed to elucidate the real-world effectiveness and safety of UST for UC. Methods Overall, 150 patients with UC treated with UST from March 2020 to January 2023 were enrolled across 7 referral hospitals. To assess the clinical efficacy and persistence of UST, retrospective analyses were conducted from weeks 8 to 56. Predictive factors concerning the response and persistence of UST were examined through univariate and multivariate analyses. Results Of the 150 patients, 125 received UST for remission induction, including 36% biologics-naïve. The response and remission rates were 72.8% and 56.0% at week 8 and 73.2% and 63.4% at week 56, respectively. Biologics-naïve patients represented higher response and remission rates at week 8 (84.4% and 73.3%) than those with biologics exposure (66.2% and 46.2%). Patients with prior antitumor necrosis factor (anti-TNF) and vedolizumab (VDZ) exposure had relatively lower response and remission rates (34.5% and 24.1%, respectively). The 1-year cumulative persistence rate was 84.0%. Multivariate analysis revealed that the chronic continuous type and prior anti-TNF and VDZ exposure were negative predictive factors for week 8 responsiveness. Clinical response at week 8 was a predictor of 1-year persistence. Adverse event incidence remained notably low at 6.4%. Conclusions This study highlights the safety and effectiveness of UST as an induction and maintenance therapy for UC. Chronic continuous type and previous anti-TNF and VDZ exposure negatively contributed to short-term effectiveness, whereas short-term effectiveness provided good persistency.
Collapse
Affiliation(s)
- Katsuyoshi Ando
- Division of Gastroenterology, Department of Internal Medicine, Asahikawa Medical University Asahikawa, Japan
| | - Mikihiro Fujiya
- Division of Gastroenterology, Department of Internal Medicine, Asahikawa Medical University Asahikawa, Japan
| | - Nobuhiro Ueno
- Department of General Medicine, Asahikawa Medical University Hospital Asahikawa, Japan
| | - Takahiro Ito
- Inflammatory Bowel Disease Center, Sapporo Higashi-Tokushukai Hospital, Sapporo, Japan
| | - Atsuo Maemoto
- Inflammatory Bowel Disease Center, Sapporo Higashi-Tokushukai Hospital, Sapporo, Japan
| | | | | | - Kensuke Sakurai
- Department of Gastroenterology and Hepatology, Graduate School of Medicine, Hokkaido University, Sapporo, Japan
| | - Takehiko Katsurada
- Department of Gastroenterology and Hepatology, Graduate School of Medicine, Hokkaido University, Sapporo, Japan
| | - Fumika Orii
- Inflammatory Bowel Disease Center, Sapporo Tokushukai Hospital, Sapporo, Japan
| | - Toshifumi Ashida
- Inflammatory Bowel Disease Center, Sapporo Tokushukai Hospital, Sapporo, Japan
| | - Satoshi Motoya
- IBD Center, Sapporo Kosei General Hospital, Sapporo, Japan
| | - Tomoe Kazama
- Department of Gastroenterology and Hepatology, Sapporo Medical University School of Medicine, Sapporo, Japan
| | - Yoshihiro Yokoyama
- Department of Gastroenterology and Hepatology, Sapporo Medical University School of Medicine, Sapporo, Japan
| | - Daisuke Hirayama
- Department of Gastroenterology and Hepatology, Sapporo Medical University School of Medicine, Sapporo, Japan
| | - Hiroshi Nakase
- Department of Gastroenterology and Hepatology, Sapporo Medical University School of Medicine, Sapporo, Japan
| |
Collapse
|
3
|
Arosa L, Camba-Gómez M, Golubnitschaja O, Conde-Aranda J. Predictive, preventive and personalised approach as a conceptual and technological innovation in primary and secondary care of inflammatory bowel disease benefiting affected individuals and populations. EPMA J 2024; 15:111-123. [PMID: 38463620 PMCID: PMC10923750 DOI: 10.1007/s13167-024-00351-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/16/2024] [Accepted: 01/25/2024] [Indexed: 03/12/2024]
Abstract
Inflammatory bowel disease (IBD) is a global health burden which carries lifelong morbidity affecting all age groups in populations with the disease-specific peak of the age groups ranging between 15 and 35 years, which are of great economic importance for the society. An accelerating incidence of IBD is reported for newly industrialised countries, whereas stabilising incidence but increasing prevalence is typical for countries with a Westernised lifestyle, such as the European area and the USA. Although the aetiology of IBD is largely unknown, the interplay between the genetic, environmental, immunological, and microbial components is decisive for the disease manifestation, course, severity and individual outcomes. Contextually, the creation of an individualised patient profile is crucial for the cost-effective disease management in primary and secondary care of IBD. The proposed pathomechanisms include intestinal pathoflora and dysbiosis, chronic inflammation and mitochondrial impairments, amongst others, which collectively may reveal individual molecular signatures defining IBD subtypes and leading to clinical phenotypes, patient stratification and cost-effective protection against health-to-disease transition and treatments tailored to individualised patient profiles-all the pillars of an advanced 3PM approach. The paradigm change from reactive medical services to predictive diagnostics, cost-effective targeted prevention and treatments tailored to individualised patient profiles in overall IBD management holds a promise to meet patient needs in primary and secondary care, to increase the life-quality of affected individuals and to improve health economy in the area of IBD management. This article analyses current achievements and provides the roadmap for future developments in the area in the context of 3P medicine benefiting society at large.
Collapse
Affiliation(s)
- Laura Arosa
- Molecular and Cellular Gastroenterology, Health Research Institute of Santiago de Compostela (IDIS), Laboratory 15, Trav. Choupana S/N, Building C, Level -2, 15706 Santiago de Compostela, Spain
| | - Miguel Camba-Gómez
- Molecular and Cellular Gastroenterology, Health Research Institute of Santiago de Compostela (IDIS), Laboratory 15, Trav. Choupana S/N, Building C, Level -2, 15706 Santiago de Compostela, Spain
| | - Olga Golubnitschaja
- 3P Medicine Research Unit, University Hospital, Rheinische Friedrich-Wilhelms Universität Bonn, 53127 Bonn, Germany
| | - Javier Conde-Aranda
- Molecular and Cellular Gastroenterology, Health Research Institute of Santiago de Compostela (IDIS), Laboratory 15, Trav. Choupana S/N, Building C, Level -2, 15706 Santiago de Compostela, Spain
| |
Collapse
|
4
|
Hsu P, Choi, EJ, Patel, SA, Wong, WH, Olvera, JG, Yao, P, Liu YC, Tsai MS, Wang W, Boland BS, Chang JT. Responsiveness to Vedolizumab Therapy in Ulcerative Colitis is Associated With Alterations in Immune Cell-Cell Communications. Inflamm Bowel Dis 2023; 29:1602-1612. [PMID: 37235748 PMCID: PMC10547234 DOI: 10.1093/ibd/izad084] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/30/2023] [Indexed: 05/28/2023]
Abstract
BACKGROUND Ulcerative colitis (UC) and Crohn's disease are 2 types of inflammatory bowel disease (IBD), a group of chronic digestive disorders caused by aberrant immune responses to intestinal microbes. Although changes in the composition of immune cell subsets in the context of IBD have been previously described, the interactions and communication among cells are less well understood. Moreover, the precise mechanisms of action underlying many biologic therapies, including the anti-α4β7 integrin antagonist vedolizumab, remain incompletely understood. Our study aimed to explore possible additional mechanisms through which vedolizumab acts. METHODS We performed cellular indexing of transcriptomes and epitopes by sequencing (CITE-seq) on peripheral blood and colon immune cells derived from patients with ulcerative colitis treated with the anti-α4β7 integrin antagonist vedolizumab. We applied a previously published computational approach, NicheNet, to predict immune cell-cell interactions, revealing putative ligand-receptor pairs and key transcriptional changes downstream of these cell-cell communications (CCC). RESULTS We observed decreased proportions of T helper 17 (TH17) cells in UC patients who responded to vedolizumab and therefore focused the study on identifying cell-cell communications and signals of TH17 cells with other immune cells. For example, we observed that colon TH17 cells from vedolizumab nonresponders were predicted to have a greater degree of interactions with classical monocytes compared with responders, whereas colon TH17 cells from vedolizumab responders exhibited more interactions with myeloid dendritic cells compared with nonresponders. CONCLUSIONS Overall, our results indicate that efforts to elucidate cell-cell communications among immune and nonimmune cell types may increase the mechanistic understanding of current and investigational therapies for IBD.
Collapse
Affiliation(s)
- Paul Hsu
- Department of Medicine, University of California San Diego, La Jolla, California, USA
| | - Eunice J Choi,
- Department of Chemistry and Biochemistry, University of California San Diego, La Jolla, California, USA
| | - Shefali A Patel,
- Department of Medicine, University of California San Diego, La Jolla, California, USA
| | - William H Wong,
- Department of Medicine, University of California San Diego, La Jolla, California, USA
| | - Jocelyn G Olvera,
- Department of Medicine, University of California San Diego, La Jolla, California, USA
| | - Priscilla Yao,
- Department of Medicine, University of California San Diego, La Jolla, California, USA
| | - Yi Chia Liu
- Department of Medicine, University of California San Diego, La Jolla, California, USA
| | - Matthew S Tsai
- Department of Medicine, University of California San Diego, La Jolla, California, USA
| | - Wei Wang
- Department of Chemistry and Biochemistry, University of California San Diego, La Jolla, California, USA
- Department of Cellular and Molecular Medicine, University of California San Diego, La Jolla, California, USA
| | - Brigid S Boland
- Department of Medicine, University of California San Diego, La Jolla, California, USA
| | - John T Chang
- Department of Medicine, University of California San Diego, La Jolla, California, USA
- Department of Medicine, Jennifer Moreno Department of Veteran Affairs Medical Center, San Diego, CA, 92161, USA
| |
Collapse
|
5
|
Schneider I, Allner C, Mühl L, Melde M, Lissner D, Mantzivi E, Glauben R, Vitali F, Becker E, Atreya I, Müller TM, Atreya R, Siegmund B, Neurath MF, Zundler S. Expression and function of α4β7 integrin predict the success of vedolizumab treatment in inflammatory bowel disease. Transl Res 2023; 253:8-15. [PMID: 36272713 DOI: 10.1016/j.trsl.2022.10.003] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/02/2022] [Revised: 10/08/2022] [Accepted: 10/13/2022] [Indexed: 11/06/2022]
Abstract
Inflammatory bowel diseases are medically intractable and require constant therapy in many cases. While a growing number of biologicals and small molecules is available for treatment, a substantial portion of patients experiences primary non-response to these compounds and head-to-head evidence for therapy selection is scarce. Thus, approaches to predict treatment success in individual patients are a huge unmet need. We had previously suggested that the expression and function of α4β7 integrin on T cells in the peripheral blood correlate to outcomes of therapy with the anti-α4β7 integrin antibody vedolizumab. Here, we conducted a translational multicenter trial to prospectively evaluate this hypothesis. In a cohort of 89 patients with inflammatory bowel disease undergoing regular therapy with vedolizumab, lower baseline expression of α4β7 was associated with short-term clinical response. Consistently, low α4β7 expression in patients achieving remission predicted sustained remission in week 30. Moreover, high dynamic adhesion of CD4+ T cells to MAdCAM-1 and high reduction of adhesion by vedolizumab in vitro at baseline were associated with clinical remission. These data substantiate the potential of α4β7 integrin function and expression to forecast outcomes of vedolizumab therapy. Further translational efforts are necessary to improve the performance of the assays and to implement the concept in clinical practice.
Collapse
Affiliation(s)
- Ines Schneider
- Department of Medicine 1, University Hospital Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany
| | - Clarissa Allner
- Department of Medicine 1, University Hospital Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany
| | - Laura Mühl
- Department of Medicine 1, University Hospital Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany
| | - Michaela Melde
- Department of Medicine 1, University Hospital Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany
| | - Donata Lissner
- Medical Department, Division of Gastroenterology, Infectiology and Rheumatology, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt Universität zu Berlin, Berlin, Germany
| | - Eleni Mantzivi
- Medical Department, Division of Gastroenterology, Infectiology and Rheumatology, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt Universität zu Berlin, Berlin, Germany
| | - Rainer Glauben
- Medical Department, Division of Gastroenterology, Infectiology and Rheumatology, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt Universität zu Berlin, Berlin, Germany
| | - Francesco Vitali
- Department of Medicine 1, University Hospital Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany
| | - Emily Becker
- Department of Medicine 1, University Hospital Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany
| | - Imke Atreya
- Department of Medicine 1, University Hospital Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany; Deutsches Zentrum Immuntherapie (DZI), University Hospital Erlangen, Erlangen, Germany
| | - Tanja M Müller
- Department of Medicine 1, University Hospital Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany; Deutsches Zentrum Immuntherapie (DZI), University Hospital Erlangen, Erlangen, Germany
| | - Raja Atreya
- Department of Medicine 1, University Hospital Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany; Deutsches Zentrum Immuntherapie (DZI), University Hospital Erlangen, Erlangen, Germany
| | - Britta Siegmund
- Medical Department, Division of Gastroenterology, Infectiology and Rheumatology, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt Universität zu Berlin, Berlin, Germany
| | - Markus F Neurath
- Department of Medicine 1, University Hospital Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany; Deutsches Zentrum Immuntherapie (DZI), University Hospital Erlangen, Erlangen, Germany
| | - Sebastian Zundler
- Department of Medicine 1, University Hospital Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany; Deutsches Zentrum Immuntherapie (DZI), University Hospital Erlangen, Erlangen, Germany.
| |
Collapse
|
6
|
Singh A, Fenton CG, Anderssen E, Paulssen RH. Identifying predictive signalling networks for Vedolizumab response in ulcerative colitis. Int J Colorectal Dis 2022; 37:1321-1333. [PMID: 35543875 PMCID: PMC9167201 DOI: 10.1007/s00384-022-04176-w] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Accepted: 05/01/2022] [Indexed: 02/04/2023]
Abstract
BACKGROUND In ulcerative colitis (UC), the molecular mechanisms that drive disease development and patient response to therapy are not well understood. A significant proportion of patients with UC fail to respond adequately to biologic therapy. Therefore, there is an unmet need for biomarkers that can predict patients' responsiveness to the available UC therapies as well as ascertain the most effective individualised therapy. Our study focused on identifying predictive signalling pathways that predict anti-integrin therapy response in patients with UC. METHODS We retrieved and pre-processed two publicly accessible gene expression datasets (GSE73661 and GSE72819) of UC patients treated with anti-integrin therapies: (1) 12 non-IBD controls and 41 UC patients treated with Vedolizumab therapy, and (2) 70 samples with 58 non-responder and 12 responder UC patient samples treated with Etrolizumab therapy without non-IBD controls. We used a diffusion-based signalling model which is mainly focused on the T-cell receptor signalling network. The diffusion model uses network connectivity between receptors and transcription factors. RESULTS The network diffusion scores were able to separate VDZ responder and non-responder patients before treatment better than the original gene expression. On both anti-integrin treatment datasets, the diffusion model demonstrated high predictive performance for discriminating responders from non-responders in comparison with 'nnet'. We have found 48 receptor-TF pairs identified as the best predictors for VDZ therapy response with AUC ≥ 0.76. Among these receptor-TF predictors pairs, FFAR2-NRF1, FFAR2-RELB, FFAR2-EGR1, and FFAR2-NFKB1 are the top best predictors. For Etrolizumab, we have identified 40 best receptor-TF pairs and CD40-NFKB2 as the best predictor receptor-TF pair (AUC = 0.72). We also identified subnetworks that highlight the network interactions, connecting receptors and transcription factors involved in cytokine and fatty acid signalling. The findings suggest that anti-integrin therapy responses in cytokine and fatty acid signalling can stratify UC patient subgroups. CONCLUSIONS We identified signalling pathways that may predict the efficacy of anti-integrin therapy in UC patients and personalised therapy alternatives. Our results may lead to the advancement of a promising clinical decision-making tool for the stratification of UC patients.
Collapse
Affiliation(s)
- Amrinder Singh
- Clinical Bioinformatics Research Group, Department of Clinical Medicine, Faculty of Health Sciences, UiT- The Arctic University of Norway, Tromsø, Norway
| | - Christopher G. Fenton
- Genomics Support Centre Tromso, UiT- The Arctic University of Norway, Department of Clinical Medicine, Faculty of Health Sciences, UiT- The Arctic University of Norway, Tromso, Norway
| | - Endre Anderssen
- Genomics Support Centre Tromso, UiT- The Arctic University of Norway, Department of Clinical Medicine, Faculty of Health Sciences, UiT- The Arctic University of Norway, Tromso, Norway
| | - Ruth H. Paulssen
- Clinical Bioinformatics Research Group, Department of Clinical Medicine, Faculty of Health Sciences, UiT- The Arctic University of Norway, Tromsø, Norway ,Genomics Support Centre Tromso, UiT- The Arctic University of Norway, Department of Clinical Medicine, Faculty of Health Sciences, UiT- The Arctic University of Norway, Tromso, Norway
| |
Collapse
|
7
|
Miyoshi J, Maeda T, Matsuoka K, Saito D, Miyoshi S, Matsuura M, Okamoto S, Tamura S, Hisamatsu T. Machine learning using clinical data at baseline predicts the efficacy of vedolizumab at week 22 in patients with ulcerative colitis. Sci Rep 2021; 11:16440. [PMID: 34385588 PMCID: PMC8361029 DOI: 10.1038/s41598-021-96019-x] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/08/2021] [Accepted: 08/04/2021] [Indexed: 12/21/2022] Open
Abstract
Predicting the response of patients with ulcerative colitis (UC) to a biologic such as vedolizumab (VDZ) before administration is an unmet need for optimizing individual patient treatment. We hypothesized that the machine-learning approach with daily clinical information can be a new, promising strategy for developing a drug-efficacy prediction tool. Random forest with grid search and cross-validation was employed in Cohort 1 to determine the contribution of clinical features at baseline (week 0) to steroid-free clinical remission (SFCR) with VDZ at week 22. Among 49 clinical features including sex, age, height, body weight, BMI, disease duration/phenotype, treatment history, clinical activity, endoscopic activity, and blood test items, the top eight features (partial Mayo score, MCH, BMI, BUN, concomitant use of AZA, lymphocyte fraction, height, and CRP) were selected for logistic regression to develop a prediction model for SFCR at week 22. In the validation using the external Cohort 2, the positive and negative predictive values of the prediction model were 54.5% and 92.3%, respectively. The prediction tool appeared useful for identifying patients with UC who would not achieve SFCR at week 22 during VDZ therapy. This study provides a proof-of-concept that machine learning using real-world data could permit personalized treatment for UC.
Collapse
Affiliation(s)
- Jun Miyoshi
- Department of Gastroenterology and Hepatology, Kyorin University School of Medicine, 6-20-2 Shinkawa, Mitaka-shi, Tokyo, 181-8611, Japan
| | - Tsubasa Maeda
- Department of Electrical, Electronic and Computer Engineering, Faculty of Engineering, Gifu University, 1-1 Yanagido, Gifu-shi, Gifu, 501-1193, Japan
| | - Katsuyoshi Matsuoka
- Division of Gastroenterology and Hepatology, Department of Internal Medicine, Toho University Sakura Medical Center, 564-1 Simoshizu, Sakura-shi, Chiba, 285-0841, Japan
| | - Daisuke Saito
- Department of Gastroenterology and Hepatology, Kyorin University School of Medicine, 6-20-2 Shinkawa, Mitaka-shi, Tokyo, 181-8611, Japan
| | - Sawako Miyoshi
- Department of General Medicine, Kyorin University School of Medicine, 6-20-2 Shinkawa, Mitaka-shi, Tokyo, 181-8611, Japan
| | - Minoru Matsuura
- Department of Gastroenterology and Hepatology, Kyorin University School of Medicine, 6-20-2 Shinkawa, Mitaka-shi, Tokyo, 181-8611, Japan
| | - Susumu Okamoto
- Department of General Medicine, Kyorin University School of Medicine, 6-20-2 Shinkawa, Mitaka-shi, Tokyo, 181-8611, Japan
| | - Satoshi Tamura
- Department of Electrical, Electronic and Computer Engineering, Faculty of Engineering, Gifu University, 1-1 Yanagido, Gifu-shi, Gifu, 501-1193, Japan.
| | - Tadakazu Hisamatsu
- Department of Gastroenterology and Hepatology, Kyorin University School of Medicine, 6-20-2 Shinkawa, Mitaka-shi, Tokyo, 181-8611, Japan.
| |
Collapse
|