Artificial intelligence for predictive biomarker discovery in immuno-oncology: a systematic review.

BACKGROUND: The widespread use of immune checkpoint inhibitors (ICIs) has revolutionised treatment of multiple cancer types. However, selecting patients who may benefit from ICI remains challenging. Artificial intelligence (AI) approaches allow exploitation of high-dimension oncological data in research and development of precision immuno-oncology. MATERIALS AND METHODS: We conducted a systematic literature review of peer-reviewed original articles studying the ICI efficacy prediction in cancer patients across five data modalities: genomics (including genomics, transcriptomics, and epigenomics), radiomics, digital pathology (pathomics), and real-world and multimodality data. RESULTS: A total of 90 studies were included in this systematic review, with 80% published in 2021-2022. Among them, 37 studies included genomic, 20 radiomic, 8 pathomic, 20 real-world, and 5 multimodal data. Standard machine learning (ML) methods were used in 72% of studies, deep learning (DL) methods in 22%, and both in 6%. The most frequently studied cancer type was non-small-cell lung cancer (36%), followed by melanoma (16%), while 25% included pan-cancer studies. No prospective study design incorporated AI-based methodologies from the outset; rather, all implemented AI as a post hoc analysis. Novel biomarkers for ICI in radiomics and pathomics were identified using AI approaches, and molecular biomarkers have expanded past genomics into transcriptomics and epigenomics. Finally, complex algorithms and new types of AI-based markers, such as meta-biomarkers, are emerging by integrating multimodal/multi-omics data. CONCLUSION: AI-based methods have expanded the horizon for biomarker discovery, demonstrating the power of integrating multimodal data from existing datasets to discover new meta-biomarkers. While most of the included studies showed promise for AI-based prediction of benefit from immunotherapy, none provided high-level evidence for immediate practice change. A priori planned prospective trial designs are needed to cover all lifecycle steps of these software biomarkers, from development and validation to integration into clinical practice.

Factors influencing clinical trial participation of women with fibromyalgia across the United States: a cross-sectional survey.

Although fibromyalgia is a widespread chronic pain condition where 90 percent of patients are women, they are underrepresented in Randomized Clinical Trials (RCTs). We aim to describe the willingness to participate, assess different factors, and explore the impact of sociodemographic and clinical characteristics on perceived barriers to trial participation. This is a cross-sectional survey targeting women with fibromyalgia. Univariate and multivariate logistic regression were performed. Of the 436 women with fibromyalgia, 56 percent were very likely to participate in RCTs. Minorities expressed less interest than non-minorities, while higher pain scores, previous participation, and younger patients reported a higher interest. Barriers significantly associated with a reduced willingness were: the participant's perception (side effects, distance, potential negative impact), the center (reputation), the trial protocol (number of visits, placebo), and trial awareness by their physician. In a multivariate analysis, older age, low education, lower income, and higher pain scores were associated with perceived barriers to RCT participation. Despite the high interest to participate, factors such as side effects, the center's distance, number of visits, placebo treatments, and the institution's reputation must be considered in clinical trials for women with fibromyalgia.

Streamlining clinical research: an ESMO awareness call to improve sponsoring and monitoring of clinical trials.

BACKGROUND: During recent years, the burden of bureaucracy in clinical research has increased dramatically, adversely impacting the activity of investigators and clinical research teams. Although compliance with the Declaration of Helsinki, the guidelines for Good Clinical Practice (GCP), and other applicable regulations remains unquestionable, their overinterpretation and substitution by the internal operating procedures of sponsors and Contract Research Organizations (CROs) have increased the administrative burden. A survey conducted by the European Society for Medical Oncology (ESMO) Clinical Research Observatory (ECRO) among 940 investigators confirmed that they considered that the administrative burden in clinical research is excessive; that administrative procedures could be reduced without affecting the safety and the rights of the patients and the quality of the data; and that bureaucracy represents an obstacle for clinical research. METHODS: A panel of physicians with extensive experience in clinical research, composed by members of the ECRO and the ESMO Scientific Medical and Public Policy divisions, analyzed clinical trial procedures related to administrative workflow, pharmacovigilance, and medical care. RESULTS: The panel identified situations that generate debate between investigators and sponsors/CROs and selected real clinical scenarios that exemplify such situations. The panel discussed and proposed specific recommendations for those situations, based on GCP. CONCLUSIONS: This initiative aspires to streamline clinical research procedures and to become a platform for discussion among all clinical trial stakeholders, with the aim of promoting the sustainability of clinical research and the care of cancer patients.

Oncology phase I trial design and conduct: time for a change - MDICT Guidelines 2022.

In 2021, the Food and Drug Administration Oncology Center of Excellence announced Project Optimus focusing on dose optimization for oncology drugs. The Methodology for the Development of Innovative Cancer Therapies (MDICT) Taskforce met to review and discuss the optimization of dosage for oncology trials and to develop a practical guide for oncology phase I trials. Defining a single recommended phase II dose based on toxicity may define doses that are neither the most effective nor the best tolerated. MDICT recommendations address the need for robust non-clinical data which are needed to inform trial design, as well as an expert team including statisticians and pharmacologists. The protocol must be flexible and adaptive, with clear definition of all endpoints. Health authorities should be consulted early and regularly. Strategies such as randomization, intrapatient dose escalation, and real-world eligibility criteria are encouraged whereas serial tumor sampling is discouraged in the absence of a strong rationale and appropriately validated assay. Endpoints should include consideration of all longitudinal toxicity. The phase I dose escalation trial should define the recommended dose range for later testing in randomized phase II trials, rather than a single recommended phase II dose, and consider scenarios where different populations may require different dosages. The adoption of these recommendations will improve dosage selection in early clinical trials of new anticancer treatments and ultimately, outcomes for patients.

Challenges and knowledge gaps with immune checkpoint inhibitors monotherapy in the management of patients with non-small-cell lung cancer: a survey of oncologist perceptions.

BACKGROUND: Immune checkpoint-inhibitors (ICIs) are changing outcomes in different cancer settings, notably for patients with non-small-cell lung cancer (NSCLC). There are, however, still important gaps of evidence for clinical practice when using these novel treatments. In this study, we assessed physicians' opinion and experience on challenges for clinical practice with ICIs monotherapy in NSCLC. METHODS: A survey was conducted on experienced physicians treating patients with NSCLC with ICIs. Two rounds of pilot tests were carried out for validation among a group of experts. Topics under analysis were in relation to treatment of elderly populations, performance status, brain metastases, use of steroids or antibiotics, the effects of gut microbiome, autoimmune diseases, human immunodeficiency virus infection, solid organ transplants, use of anti-programmed cell death protein 1 versus anti-programmed death-ligand 1 drugs, atypical tumour responses, predictors of response, duration of treatment and a final open question on additional relevant challenges. RESULTS: Two hundred and twenty-one answers were collected, including 106 (48%) valid answers from experts for final analysis (physicians who have treated at least 20 patients with NSCLC with ICIs). The vast majority agreed that the selected topics in this study are important challenges ahead and more evidence is needed. Moreover, predictors of response, treating brain metastasis, shorter duration of treatment, the effects of gut microbiome and concomitant use of steroids were voted the most important topics to be further addressed in prospective clinical research. CONCLUSIONS: This survey contributed to understanding which are the main challenges for clinical practice with ICIs monotherapy in NSCLC. It can also contribute to guide further clinical research, considering the opinions and experience of those who regularly treat NSCLC patients with ICIs.

COVID-19 in cancer patients: update from the joint analysis of the ESMO-CoCARE, BSMO, and PSMO international databases.

BACKGROUND: COVID-19 has significantly affected patients with cancer and revealed unanticipated challenges in securing optimal cancer care across different disciplines. The European Society for Medical Oncology COVID-19 and CAncer REgistry (ESMO-CoCARE) is an international, real-world database, collecting data on the natural history, management, and outcomes of patients with cancer and SARS-CoV-2 infection. METHODS: This is the 2nd CoCARE analysis, jointly with Belgian (Belgian Society of Medical Oncology, BSMO) and Portuguese (Portuguese Society of Medical Oncology, PSMO) registries, with data from January 2020 to December 2021. The aim is to identify significant prognostic factors for COVID-19 hospitalization and mortality (primary outcomes), as well as intensive care unit admission and overall survival (OS) (secondary outcomes). Subgroup analyses by pandemic phase and vaccination status were carried out. RESULTS: The cohort includes 3294 patients (CoCARE: 2049; BSMO: 928, all hospitalized by eligibility criteria; PSMO: 317), diagnosed in four distinct pandemic phases (January to May 2020: 36%; June to September 2020: 9%; October 2020 to February 2021: 41%; March to December 2021: 12%). COVID-19 hospitalization rate was 54% (CoCARE/PSMO), ICU admission 14%, and COVID-19 mortality 22% (all data). At a 6-month median follow-up, 1013 deaths were recorded with 73% 3-month OS rate. No significant change was observed in COVID-19 mortality among hospitalized patients across the four pandemic phases (30%-33%). Hospitalizations and ICU admission decreased significantly (from 78% to 34% and 16% to 10%, respectively). Among 1522 patients with known vaccination status at COVID-19 diagnosis, 70% were non-vaccinated, 24% had incomplete vaccination, and 7% complete vaccination. Complete vaccination had a protective effect on hospitalization (odds ratio = 0.24; 95% confidence interval [0.14-0.38]), ICU admission (odds ratio = 0.29 [0.09-0.94]), and OS (hazard ratio = 0.39 [0.20-0.76]). In multivariable analyses, COVID-19 hospitalization was associated with patient/cancer characteristics, the first pandemic phase, the presence of COVID-19-related symptoms or inflammatory biomarkers, whereas COVID-19 mortality was significantly higher in symptomatic patients, males, older age, ethnicity other than Asian/Caucasian, Eastern Cooperative Oncology Group performance status ≥2, body mass index <25, hematological malignancy, progressive disease versus no evident disease, and advanced cancer stage. CONCLUSIONS: The updated CoCARE analysis, jointly with BSMO and PSMO, highlights factors that significantly affect COVID-19 outcomes, providing actionable clues for further reducing mortality.

Antimicrobial resistance of Pseudomonas aeruginosa isolated from patients with pneumonia during the COVID-19 pandemic and pre-pandemic periods in Northeast Brazil.

Healthcare-related infections caused by resistant microorganisms are a severe public health problem and are becoming increasingly prevalent in the hospital environment, especially Pseudomonas aeruginosa. This work aimed to evaluate the resistance profile of Pseudomonas aeruginosa to antimicrobials before the COVID-19 pandemic and during the pandemic period. Bacteria strains were obtained from tracheal aspiration, sputum, and bronchoalveolar lavage for diagnosis and phenotypic characterization. Matrix assisted laser-desorption ionization-time of flight mass spectrometry (MALD-TOF MS) was used to identify strains. Automated Phoenix and VITEK® 2 Compact system and the disc diffusion method were performed to determine the antimicrobial susceptibility profile. A total of 41,000 medical reports from adult patients with pneumonia were analyzed. Of these, 951 patients were positive for P. aeruginosa, of which 373 were related to the pre-pandemic period and 578 to the pandemic period. Older men (≥60 years) were more prevalent in both periods. P. aeruginosa strains were resistant to imipenem in both periods: 38.8 and 42.5%, respectively, followed by meropenem (34.2 and 39.2%), ciprofloxacin (33.6 and 36.7%), and levofloxacin (34.9 and 43.5%). Intensive care units had the highest percentage of affected patients (62 and 65%) compared with other sectors, with a prevalence of 71% in the public network before COVID-19 and 59% during the pandemic. Our data showed a prevalence of P. aeruginosa in elderly patients in both the pre-pandemic and pandemic periods. In addition, an increase in P. aeruginosa resistance to beta-lactams, quinolones, carbapenems, and cephalosporins was observed during the COVID-19 pandemic compared with the period before the pandemic, especially in ICUs.

COVID-19 in patients with cancer: first report of the ESMO international, registry-based, cohort study (ESMO-CoCARE).

BACKGROUND: ESMO COVID-19 and CAncer REgistry (ESMO-CoCARE) is an international collaborative registry-based, cohort study gathering real-world data from Europe, Asia/Oceania and Africa on the natural history, management and outcomes of patients with cancer infected with severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2). PATIENTS AND METHODS: ESMO-CoCARE captures information on patients with solid/haematological malignancies, diagnosed with coronavirus disease 2019 (COVID-19). Data collected since June 2020 include demographics, comorbidities, laboratory measurements, cancer characteristics, COVID-19 clinical features, management and outcome. Parameters influencing COVID-19 severity/recovery were investigated as well as factors associated with overall survival (OS) upon SARS-CoV-2 infection. RESULTS: This analysis includes 1626 patients from 20 countries (87% from 24 European, 7% from 5 North African, 6% from 8 Asian/Oceanian centres), with COVID-19 diagnosis from January 2020 to May 2021. Median age was 64 years, with 52% of female, 57% of cancer stage III/IV and 65% receiving active cancer treatment. Nearly 64% patients required hospitalization due to COVID-19 diagnosis, with 11% receiving intensive care. In multivariable analysis, male sex, older age, Eastern Cooperative Oncology Group (ECOG) performance status ≥2, body mass index (BMI) <25 kg/m2, presence of comorbidities, symptomatic disease, as well as haematological malignancies, active/progressive cancer, neutrophil-to-lymphocyte ratio (NLR) ≥6 and OnCovid Inflammatory Score ≤40 were associated with COVID-19 severity (i.e. severe/moderate disease requiring hospitalization). About 98% of patients with mild COVID-19 recovered, as opposed to 71% with severe/moderate disease. Advanced cancer stage was an additional adverse prognostic factor for recovery. At data cut-off, and with median follow-up of 3 months, the COVID-19-related death rate was 24.5% (297/1212), with 380 deaths recorded in total. Almost all factors associated with COVID-19 severity, except for BMI and NLR, were also predictive of inferior OS, along with smoking and non-Asian ethnicity. CONCLUSIONS: Selected patient and cancer characteristics related to sex, ethnicity, poor fitness, comorbidities, inflammation and active malignancy predict for severe/moderate disease and adverse outcomes from COVID-19 in patients with cancer.

Antimicrobial resistance of Pseudomonas aeruginosa isolated from patients with pneumonia during the COVID-19 pandemic and pre-pandemic periods in Northeast Brazil

Healthcare-related infections caused by resistant microorganisms are a severe public health problem and are becoming increasingly prevalent in the hospital environment, especially Pseudomonas aeruginosa. This work aimed to evaluate the resistance profile of Pseudomonas aeruginosa to antimicrobials before the COVID-19 pandemic and during the pandemic period. Bacteria strains were obtained from tracheal aspiration, sputum, and bronchoalveolar lavage for diagnosis and phenotypic characterization. Matrix assisted laser-desorption ionization-time of flight mass spectrometry (MALD-TOF MS) was used to identify strains. Automated Phoenix and VITEK® 2 Compact system and the disc diffusion method were performed to determine the antimicrobial susceptibility profile. A total of 41,000 medical reports from adult patients with pneumonia were analyzed. Of these, 951 patients were positive for P. aeruginosa, of which 373 were related to the pre-pandemic period and 578 to the pandemic period. Older men (≥60 years) were more prevalent in both periods. P. aeruginosa strains were resistant to imipenem in both periods: 38.8 and 42.5%, respectively, followed by meropenem (34.2 and 39.2%), ciprofloxacin (33.6 and 36.7%), and levofloxacin (34.9 and 43.5%). Intensive care units had the highest percentage of affected patients (62 and 65%) compared with other sectors, with a prevalence of 71% in the public network before COVID-19 and 59% during the pandemic. Our data showed a prevalence of P. aeruginosa in elderly patients in both the pre-pandemic and pandemic periods. In addition, an increase in P. aeruginosa resistance to beta-lactams, quinolones, carbapenems, and cephalosporins was observed during the COVID-19 pandemic compared with the period before the pandemic, especially in ICUs.