Mesenchymal stromal cell-derived extracellular vesicles therapy openings new translational challenges in immunomodulating acute liver inflammation.

Inflammation plays a critical role in conditions such as acute liver failure, acute-on-chronic liver failure, and ischemia-reperfusion-induced liver injury. Various pathogenic pathways contribute to liver inflammation, involving inflammatory polarization of macrophages and Küpffer cells, neutrophil infiltration, dysregulation of T cell subsets, oxidative stress, and activation of hepatic stellate cells. While mesenchymal stromal cells (MSCs) have demonstrated beneficial properties, their clinical translation is limited by their cellular nature. However, MSC-derived extracellular vesicles (MSC-EVs) have emerged as a promising cell-free therapeutic approach for immunomodulation. MSC-EVs naturally mirror their parental cell properties, overcoming the limitations associated with the use of MSCs. In vitro and in vivo preclinical studies have demonstrated that MSC-EVs replicate the beneficial effects of MSCs in liver injury. This includes the reduction of cell death and oxidative stress, improvement of hepatocyte function, induction of immunomodulatory effects, and mitigation of cytokine storm. Nevertheless, MSC-EVs face challenges regarding the necessity of defining consistent isolation methods, optimizing MSCs culture conditions, and establishing quality control measures for EV characterization and functional assessment. By establishing standardized protocols, guidelines, and affordable cost mass production, clinicians and researchers will have a solid foundation to conduct further studies, validate the therapeutic efficacy of MSC-EVs, and ultimately pave the way for their clinical implementation in acute liver injury.

Central angiotensin-(1-7) attenuates hypoglycemia in sepsis-like conditions via reducing systemic and hepatic inflammation.

Sepsis is understood as the result of initiating systemic inflammation derived from an inadequate host response against pathogens. In its acute phase, sepsis is marked by an exacerbated reaction to infection, tissue damage, organ failure, and metabolic dysfunction. Among these, hypoglycemia, characterized by disorders of the gluconeogenesis pathway, is related to one of the leading causes of mortality in septic patients. Recent research has investigated the involvement of sympathetic efferent neuroimmune pathways during systemic inflammation. These pathways can be stimulated by several centrally administered drugs, including Angiotensin-(1-7) (Ang-(1-7)). Therefore, the present study aims to evaluate the effects of central treatment with Ang-(1-7) on hypoglycemia during endotoxemia. For this, male Wistar Hannover rats underwent stereotaxic surgery for intracerebroventricular (i.c.v.) administration of Ang-(1-7) and cannulation of the jugular vein for lipopolysaccharide (LPS) injection. Our results demonstrate that LPS was capable of inducing hypoglycemia and that prior central treatment with Ang-(1-7) attenuated this effect. Our data also show that Ang-(1-7) reduced plasma concentrations of TNF-α, IL-1ß, IL-6, and nitric oxide, in addition to the decrease and increase of hepatic IL-6 and IL-10 respectively, in animals subjected to systemic inflammation by LPS, resulting in the reduction of systemic and hepatic inflammation, thus attenuating the deleterious effects of LPS on phosphoenolpyruvate carboxykinase protein content. In summary, the data suggest that central treatment with Ang-(1-7) attenuates hypoglycemia induced by endotoxemia, probably through anti-inflammatory action, leading to reestablishing hepatic gluconeogenesis.

Management of liver and gastrointestinal toxicity induced by immune checkpoint inhibitors: Position statement of the AEEH–AEG–SEPD–SEOM–GETECCU / Manejo de las toxicidades digestivas secundarias al tratamiento con inhibidores de checkpoint: documento de posicionamiento de la AEEH-AEG-SEPD-SEOM-GETECCU

The development of the immune checkpoint inhibitors (ICI) is one of the most remarkable achievements in cancer therapy in recent years. However, their exponential use has led to an increase in immune-related adverse events (irAEs). Gastrointestinal and liver events encompass hepatitis, colitis and upper digestive tract symptoms accounting for the most common irAEs, with incidence rates varying from 2% to 40%, the latter in patients undergoing combined ICIs therapy. Based on the current scientific evidence derived from both randomized clinical trials and real-world studies, this statement document provides recommendations on the diagnosis, treatment and prognosis of the gastrointestinal and hepatic ICI-induced adverse events.(AU)

El descubrimiento de los inhibidores de checkpoint inmunológicos (ICI) es uno de los logros más importantes en los últimos años en Oncología. Sin embargo, su uso en aumento ha conlllevado a un incremento de los efectos adversos inmunomediados (irAEs). Los eventos hepáticos y gastrointestinales incluyen la hepatitis, colitis y síntomas de tracto digestivo superior, que son de los irAEs más frecuentes, con incidencias entre el 2 y 40%, ésta última en paciente tratados con combo de ICI. Basados en la evidencia científica tanto de ensayo clínicos randomizados como de estudio de vida real, este documento de consenso aporta recomendaciones sobre el diagnóstico, tratamiento y pronóstico de los efectos adversos hepáticos y gastrointestinales asociados con la inmunoterapia.(AU)

Optimized therapeutic potential of Yinchenhao decoction for cholestatic hepatitis by combined network meta-analysis and network pharmacology.

BACKGROUND: Cholestatic hepatitis is recognized as a significant contributor to the development of liver fibrosis and cirrhosis. As a well-known classic formula for the treatment of cholestatic hepatitis, Yinchenhao decoction (YCHD) is widely used in countries in Asia, including China, Japan, and Korea. However, in recent years, a risk of liver injury has been reported from Rheum palmatum L. and Gardenia jasmonoides J.Ellis which are the main ingredients of YCHD. Therefore, the question arises whether YCHD is still safe enough for the treatment of cholestatic hepatitis or whether an optimized ratio of ingredients should be applied. These is inevitable questions for the clinical application of YCHD. PURPOSE: To provide a scientific basis for the clinical application of YCHD through a combination of meta-analysis and network pharmacology and to find the best ratio of components to ensure optimal therapeutic efficacy and safety. At the same time, a deeper understanding of the mechanisms of YCHD was explored. METHODS: We retrieved relevant trials from various databases including PubMed, Web of Science, EMBASE, Cochrane Library, China National Knowledge Infrastructure (CNKI), VIP and Wanfang databases up to August 2023. After screening for inclusion and exclusion criteria, we assessed efficiency, ALT, AST, and TBIL as outcome parameters. The relevant data underwent a network meta-analysis using STATA 16.0 software. Based on network pharmacology, we screened the disease targets, active ingredients, and targets related to YCHD. The targets were visualized using Cytoscape 3.9.1. Then, potential mechanisms were explored based on bioinformatic techniques. RESULTS: Twenty eligible studies were finally screened and a total of 1,591 patients who fulfilled the inclusion criteria were enrolled in the study. The meta-analysis results indicated that TG-c (treatment group c) [(Artemisia capillaris Thunb. : Gardenia jasminoides J.Ellis : Rheum palmatum L. = 10:5:2-10:5:3) + CT] was the most promising therapeutic approach, demonstrating superior efficacy and notable improvements in both AST and TBIL levels. For ALT, TG-d [(Artemisia capillaris : Gardenia jasminoides : Rheum palmatum = 5:1:1-5:2:1) + CT] exhibited the greatest potential as optimal therapy option. Based on the surface under the cumulative ranking curve (SUCRA) values, TG-c was the best therapy in terms of efficiency and improvement in TBIL levels, while TG-d was the most effective in reducing ALT levels. For AST levels, TG-e [(Artemisia capillaris : Gardenia jasminoides : Rheum palmatum = 5:2:2-5:3:3) + CT] was the most effective therapy. The comprehensive analysis revealed that TG-c exhibited the most pronounced efficacy. Combined network pharmacology, GO enrichment analysis and KEGG pathway enrichment analysis displayed that the key target genes of Artemisia capillaris, Rheum palmatum, and Gardenia jasminoides were closely involved in inflammation response, bile transport, apoptosis, oxidative stress, and regulation of leukocyte migration. Notably, bile secretion dominated the common pathway of the three herbs. On the other hand, Artemisia capillaris exhibited a unique mode of action by regulating the IL-17 signaling pathway, which may play a crucial role in its effectiveness. CONCLUSION: Based on our findings, the optimal TG-C demonstrated the most favorable overall therapeutic efficacy by increasing the dosage of Artemisia capillaris while reducing the dosage of Gardenia jasminoides and Rheum palmatum. This is attributed to the potent ability of Artemisia capillaris. to effectively modulate the IL-17 signaling pathway, thereby exerting a beneficial therapeutic effect. Conversely, Gardenia jasminoides and Rheum palmatum may potentially enhance the activation of the NF-кB signaling pathway, thereby elevating the risk of hepatotoxicity.

Therapeutic inhibition of monocyte recruitment prevents checkpoint inhibitor-induced hepatitis.

BACKGROUND: Checkpoint inhibitor-induced hepatitis (CPI-hepatitis) is an emerging problem with the widening use of CPIs in cancer immunotherapy. Here, we developed a mouse model to characterize the mechanism of CPI-hepatitis and to therapeutically target key pathways driving this pathology. METHODS: C57BL/6 wild-type (WT) mice were dosed with toll-like receptor (TLR)9 agonist (TLR9-L) for hepatic priming combined with anti-cytotoxic T lymphocyte antigen-4 (CTLA-4) plus anti-programmed cell death 1 (PD-1) ("CPI") or phosphate buffered saline (PBS) control for up to 7 days. Flow cytometry, histology/immunofluorescence and messenger RNA sequencing were used to characterize liver myeloid/lymphoid subsets and inflammation. Hepatocyte damage was assessed by plasma alanine transaminase (ALT) and cytokeratin-18 (CK-18) measurements. In vivo investigations of CPI-hepatitis were carried out in Rag2-/- and Ccr2rfp/rfp transgenic mice, as well as following anti-CD4, anti-CD8 or cenicriviroc (CVC; CCR2/CCR5 antagonist) treatment. RESULTS: Co-administration of combination CPIs with TLR9-L induced liver pathology closely resembling human disease, with increased infiltration and clustering of granzyme B+perforin+CD8+ T cells and CCR2+ monocytes, 7 days post treatment. This was accompanied by apoptotic hepatocytes surrounding these clusters and elevated ALT and CK-18 plasma levels. Liver RNA sequencing identified key signaling pathways (JAK-STAT, NF-ΚB) and cytokine/chemokine networks (Ifnγ, Cxcl9, Ccl2/Ccr2) as drivers of CPI-hepatitis. Using this model, we show that CD8+ T cells mediate hepatocyte damage in experimental CPI-hepatitis. However, their liver recruitment, clustering, and cytotoxic activity is dependent on the presence of CCR2+ monocytes. The absence of hepatic monocyte recruitment in Ccr2rfp/rfp mice and CCR2 inhibition by CVC treatment in WT mice was able to prevent the development and reverse established experimental CPI-hepatitis. CONCLUSION: This newly established mouse model provides a platform for in vivo mechanistic studies of CPI-hepatitis. Using this model, we demonstrate the central role of liver infiltrating CCR2+ monocyte interaction with tissue-destructive CD8+ T cells in the pathogenesis of CPI-hepatitis and highlight CCR2 inhibition as a novel therapeutic target.

Soy Protein Concentrate Diets Inversely Affect LPS-Binding Protein Expression in Colon and Liver, Reduce Liver Inflammation, and Increase Fecal LPS Excretion in Obese Zucker Rats.

Dietary soy protein and soy isoflavones have anti-inflammatory properties. Previously, we reported that feeding soy protein concentrate diet (SPC) with low or high isoflavone (LIF or HIF) to young (seven-week-old) obese (fa/fa) Zucker rats inhibits lipopolysaccharide (LPS) translocation and decreases liver inflammation compared to a casein control (CAS) diet. The current study investigated whether SPC-LIF and SPC-HIF diets would reduce liver inflammation in adult obese Zucker rats fed a CAS diet. A total of 21 six-week-old male obese (fa/fa) Zucker rats were given CAS diet for 8 weeks to develop obesity then randomly assigned to CAS, SPC-LIF, or SPC-HIF (seven rats/group) diet for an additional 10 weeks. The expression of LPS-translocation, inflammation, and intestinal permeability markers were quantified by qPCR in liver, visceral adipose tissue (VAT), and colon. LPS concentration was determined in both the colon content and fecal samples by a Limulus amebocyte lysate (LAL) test. SPC-LIF and SPC-HIF diets significantly decreased liver LPS-binding protein (LBP) expression compared to CAS diet (p < 0.01 and p < 0.05, respectively). SPC-HIF diet also significantly decreased liver MCP-1 and TNF-α expression (p < 0.05) and had a trend to decrease liver iNOS expression (p = 0.06). In the colon, SPC-HIF diet significantly increased LBP expression compared to CAS diet (p < 0.05). When samples from all three groups were combined, there was a negative correlation between colon LBP expression and liver LBP expression (p = 0.046). SPC diets did not alter the expression of intestinal permeability markers (i.e., occludin, claudin 3, and zonula occludens-1) in the colon or inflammation markers (i.e., TNF-α and iNOS) in VAT or the colon. LPS levels in the colon content did not differ between any groups. Fecal LPS levels were significantly higher in the SPC-LIF and SPC-HIF groups compared to the CAS group (p < 0.01). In conclusion, SPC, particularly SPC with HIF, reduces liver LBP expression and inflammation makers (i.e., TNF-α and MCP-1 expression) in adult obese Zucker rats, likely by reducing LPS translocation.

Hepatitis after gene therapy, what are the possible causes?

Hepatitis is a common adverse event following gene therapy for haemophilia, often associated with a loss of transgene expression. Investigating the potential causes and implications of this is crucial for the overall success of treatment. Gene therapy trials using adeno-associated virus (AAV) vectors have demonstrated promising results marked by increases in factor FVIII and FIX levels and reductions in episodes of bleeding. However, hepatocellular injury characterised by elevations in alanine aminotransferases (ALT) has been noted. This liver injury is typically transient and asymptomatic, posing challenges in determining its clinical significance. Proposed causes encompass immune-mediated responses, notably T cell cytotoxicity in response to the AAV vector, direct liver injury from the viral capsid or transcribed protein via the unfolded protein response and pre-existing liver conditions. Liver biopsy data conducted years post-gene therapy infusion has shown sinusoidal infiltration without significant inflammation. The overall safety profile of gene therapy remains favourable with no evidence drug-induced liver injury (DILI) based on Hy's Law criteria. Essential pre-therapy monitoring and identifying patients at high risk of liver injury should involve liver function tests and non-invasive fibroscans, while novel blood-based biomarkers are under exploration. Further research is required to comprehend the mechanisms underlying transaminitis, loss of transgene expression and long-term effects on the liver, providing insights for optimising gene therapy for haemophilia.

The ST2+ Treg/amphiregulin axis protects from immune-mediated hepatitis.

Introduction: The alarmin IL-33 has been implicated in the pathology of immune-mediated liver diseases. IL-33 activates regulatory T cells (Tregs) and type 2 innate lymphoid cells (ILC2s) expressing the IL-33 receptor ST2. We have previously shown that endogenous IL-33/ST2 signaling activates ILC2s that aggravate liver injury in murine immune-mediated hepatitis. However, treatment of mice with exogenous IL-33 before induction of hepatitis ameliorated disease severity. Since IL-33 induces expression of amphiregulin (AREG) crucial for Treg function, we investigated the immunoregulatory role of the ST2+ Treg/AREG axis in immune-mediated hepatitis. Methods: C57BL/6, ST2-deficient (Il1rl1-/-) and Areg-/- mice received concanavalin A to induce immune-mediated hepatitis. Foxp3Cre+ x ST2fl/fl mice were pre-treated with IL-33 before induction of immune-mediated hepatitis. Treg function was assessed by adoptive transfer experiments and suppression assays. The effects of AREG and IL-33 on ST2+ Tregs and ILC2s were investigated in vitro. Immune cell phenotype was analyzed by flow cytometry. Results and discussion: We identified IL-33-responsive ST2+ Tregs as an effector Treg subset in the murine liver, which was highly activated in immune-mediated hepatitis. Lack of endogenous IL-33 signaling in Il1rl1-/- mice aggravated disease pathology. This was associated with reduced Treg activation. Adoptive transfer of exogenous IL-33-activated ST2+ Tregs before induction of hepatitis suppressed inflammatory T-cell responses and ameliorated disease pathology. We further showed increased expression of AREG by hepatic ST2+ Tregs and ILC2s in immune-mediated hepatitis. Areg-/- mice developed more severe liver injury, which was associated with enhanced ILC2 activation and less ST2+ Tregs in the inflamed liver. Exogenous AREG suppressed ILC2 cytokine expression and enhanced ST2+ Treg activation in vitro. In addition, Tregs from Areg-/- mice were impaired in their capacity to suppress CD4+ T-cell activation in vitro. Moreover, application of exogenous IL-33 before disease induction did not protect Foxp3Cre+ x ST2fl/fl mice lacking ST2+ Tregs from immune-mediated hepatitis. In summary, we describe an immunoregulatory role of the ST2+ Treg/AREG axis in immune-mediated hepatitis, in which AREG suppresses the activation of hepatic ILC2s while maintaining ST2+ Tregs and reinforcing their immunosuppressive capacity in liver inflammation.

A comprehensive review on the hepatotoxicity of herbs used in the Indian (Ayush) systems of alternative medicine.

Complementary and alternative medicine-related liver injuries are increasing globally. Alternative medicine, as an inclusive healthcare practice, is widely accepted in developing and underdeveloped countries. In this context, the traditional systems of medicine in India have been at the forefront, catering to the preventive and therapeutic spectrum in the absence of conclusive evidence for benefits and lack of data on safety. Contrary to popular belief, it is evident that apart from adverse events caused by contamination and adulteration of alternative medicines, certain commonly used herbal components have inherent hepatotoxicity. This narrative review updates our current understanding and increasing publications on the liver toxicity potential of commonly used herbs in traditional Indian systems of medicine (Ayush), such as Tinospora cordifolia (Willd.) Hook.f. & Thomson (Giloy/Guduchi), Withania somnifera (L.) Dunal (Ashwagandha), Curcuma longa L. (Turmeric), and Psoralea corylifolia L. (Bakuchi/Babchi). This review also highlights the importance of the upcoming liver toxicity profiles associated with other traditional herbs used as dietary supplements, such as Centella asiatica (L.) Urb., Garcinia cambogia Desr., Cassia angustifolia Vahl (Indian senna), and Morinda citrofolia L. (Noni fruit). Fortunately, most reported liver injuries due to these herbs are self-limiting, but can lead to progressive liver dysfunction, leading to acute liver failure or acute chronic liver failure with a high mortality rate. This review also aims to provide adequate knowledge regarding herbalism in traditional practices, pertinent for medical doctors to diagnose, treat, and prevent avoidable liver disease burdens within communities, and improve public health and education.

Granulomatous hepatitis with Crohn's disease: a case report.

A 45-year-old man who was regularly followed up for Crohn's disease (CD) and maintained clinical remission with vedolizumab (VDZ). At 37 years old, he was diagnosed CD from longitudinal ulcers in the distal ileum by balloon-assisted enteroscopy (BAE). During the follow-up, liver enzyme elevation, splenomegaly and thrombocytopenia were in progress. Esophagogastric varices suggested chronic liver disease and portal hypertension. Magnetic resonance elastography (MRE) showed liver stiffness of 3.4 kPa and proton density fat fraction (PDFF) of 1.86%. He was diagnosed with granulomatous hepatitis based on a liver biopsy. The hepatic venous pressure gradient (HVPG) was mildly elevated at 7 mmHg, consistent with the pre-sinusoidal portal hypertension due to granulomatous hepatitis. We report a rare case with granulomatous hepatitis diagnosed from liver injury and portal hypertension, despite the stable intestinal symptoms of CD.

Update on ischemic hepatitis.

PURPOSE OF REVIEW: Ischemic hepatitis (IH) refers to diffuse liver injury secondary to hypoperfusion. The condition is usually seen in the critical care setting and is associated with significant mortality. IH typically occurs in the setting of systemic hypotension superimposed on some form of underlying cardiac dysfunction. This review aims to report what is known and what is new about the etiology, pathophysiology, and clinical features associated with IH. RECENT FINDINGS: In recent years, studies on IH have largely confirmed earlier reports regarding etiologies, comorbid conditions, and associated mortality. Recent study has also shed light on the potential treatment of IH with N -acetyl-cysteine (NAC). SUMMARY: IH is typically associated with underlying cardiac disease, and patients with IH have a very high mortality rate. Treatment remains largely supportive, although the utility of agents such as NAC are being explored.

Multifaceted Characterization for the Hepatic Clearance of Graphene Oxide and Size-Related Hepatic Toxicity.

Understanding the final fate of nanomaterials (NMs) in the liver is crucial for their safer application. As a representative two-dimensional (2D) soft nanomaterial, graphene oxide (GO) has shown to have high potential for applications in the biomedical field, including in biosensing, drug delivery, tissue engineering, therapeutics, etc. GO has been shown to accumulate in the liver after entering the body, and thus, understanding the GO-liver interaction will facilitate the development of safer bio-applications. In this study, the hepatic clearance of two types of PEGylated GOs with different lateral sizes (s-GOs: ~70 nm and l-GOs: ~300 nm) was carefully investigated. We found that GO sheets across the hepatic sinusoidal endothelium, which then may be taken up by the hepatocytes via the Disse space. The hepatocytes may degrade GO into dot-like particles, which may be excreted via the hepatobiliary route. In combination with ICP-MS, LA-ICP-MS, and synchrotron radiation FTIR techniques, we found that more s-GO sheets in the liver were prone to be cleared via hepatobiliary excretion than l-GO sheets. A Raman imaging analysis of ID/IG ratios further indicated that both s-GO and l-GO generated more defects in the liver. The liver microsomes may contribute to GO biotransformation into O-containing functional groups, which plays an important role in GO degradation and excretion. In particular, more small-sized GO sheets in the liver were more likely to be cleared via hepatobiliary excretion than l-GO sheets, and a greater clearance of s-GO will mitigate their hepatotoxicity. These results provide a better understanding of the hepatic clearance of soft NMs, which is important in the safer-by-design of GO.

Deaths Associated with Pediatric Hepatitis of Unknown Etiology, United States, October 2021-June 2023.

During October 2021-June 2023, a total of 392 cases of acute hepatitis of unknown etiology in children in the United States were reported to Centers for Disease Control and Prevention as part of national surveillance. We describe demographic and clinical characteristics, including potential involvement of adenovirus in development of acute hepatitis, of 8 fatally ill children who met reporting criteria. The children had diverse courses of illness. Two children were immunocompromised when initially brought for care. Four children tested positive for adenovirus in multiple specimen types, including 2 for whom typing was completed. One adenovirus-positive child had no known underlying conditions, supporting a potential relationship between adenovirus and acute hepatitis in previously healthy children. Our findings emphasize the importance of continued investigation to determine the mechanism of liver injury and appropriate treatment. Testing for adenovirus in similar cases could elucidate the role of the virus.

Leveraging stem cells to combat hepatitis: a comprehensive review of recent studies.

Hepatitis is a significant global public health concern, with viral infections being the most common cause of liver inflammation. Antiviral medications are the primary treatments used to suppress the virus and prevent liver damage. However, the high cost of these drugs and the lack of awareness and stigma surrounding the disease create challenges in managing hepatitis. Stem cell therapy has arisen as a promising therapeutic strategy for hepatitis by virtue of its regenerative and immunomodulatory characteristics. Stem cells have the exceptional capacity to develop into numerous cell types and facilitate tissue regeneration, rendering them a highly promising therapeutic avenue for hepatitis. In animal models, stem cell therapy has demonstrated worthy results by reducing liver inflammation and improving liver function. Furthermore, clinical trials have been undertaken to assess the safety and effectiveness of stem cell therapy in individuals with hepatitis. This review aims to explore the involvement of stem cells in treating hepatitis and highlight the findings from studies conducted on both animals and humans. The objective of this review is to primarily concentrate on the ongoing and future clinical trials that assess the application of stem cell therapy in the context of hepatitis, including the transplantation of autologous bone marrow-derived stem cells, human induced pluripotent stem cells, and other mesenchymal stem cells. In addition, this review will explore the potential merits and constraints linked to stem cell therapy for hepatitis, as well as its prospective implications in the management of this disease.

Acute grade IV toxic hepatitis due to the e-cigarette.

A 46-year-old woman presented at the emergency department because of acute hepatitis with jaundice. After hepatological work-up including liver biopsy, drug induced liver disease (DILI) was suspected. Patient recovered completely within a few months. One year later she presented again with jaundice due to acute hepatitis. Vaping was the only agent that could be identified as causative agent for DILI. After VAPING cessation, the hepatitis resolved completely. Calculated RUCAM score was 10, making the diagnosis of toxic hepatitis very likely. During follow-up liver tests remained normal. This is the first report of severe DILI secondary to the use of e-cigarettes. In future vaping can be included in the differential diagnosis of DILI.

Prediction of Effectiveness and Toxicities of Immune Checkpoint Inhibitors Using Real-World Patient Data.

PURPOSE: Although immune checkpoint inhibitors (ICIs) have improved outcomes in certain patients with cancer, they can also cause life-threatening immunotoxicities. Predicting immunotoxicity risks alongside response could provide a personalized risk-benefit profile, inform therapeutic decision making, and improve clinical trial cohort selection. We aimed to build a machine learning (ML) framework using routine electronic health record (EHR) data to predict hepatitis, colitis, pneumonitis, and 1-year overall survival. METHODS: Real-world EHR data of more than 2,200 patients treated with ICI through December 31, 2018, were used to develop predictive models. Using a prediction time point of ICI initiation, a 1-year prediction time window was applied to create binary labels for the four outcomes for each patient. Feature engineering involved aggregating laboratory measurements over appropriate time windows (60-365 days). Patients were randomly partitioned into training (80%) and test (20%) sets. Random forest classifiers were developed using a rigorous model development framework. RESULTS: The patient cohort had a median age of 63 years and was 61.8% male. Patients predominantly had melanoma (37.8%), lung cancer (27.3%), or genitourinary cancer (16.4%). They were treated with PD-1 (60.4%), PD-L1 (9.0%), and CTLA-4 (19.7%) ICIs. Our models demonstrate reasonably strong performance, with AUCs of 0.739, 0.729, 0.755, and 0.752 for the pneumonitis, hepatitis, colitis, and 1-year overall survival models, respectively. Each model relies on an outcome-specific feature set, though some features are shared among models. CONCLUSION: To our knowledge, this is the first ML solution that assesses individual ICI risk-benefit profiles based predominantly on routine structured EHR data. As such, use of our ML solution will not require additional data collection or documentation in the clinic.