Corrigendum: Transfer learning approach based on computed tomography images for predicting late xerostomia after radiotherapy in patients with oropharyngeal cancer.

[This corrects the article DOI: 10.3389/fmed.2022.993395.].

Transfer learning approach based on computed tomography images for predicting late xerostomia after radiotherapy in patients with oropharyngeal cancer.

Background and purpose: Although the latest breakthroughs in radiotherapy (RT) techniques have led to a decrease in adverse event rates, these techniques are still associated with substantial toxicity, including xerostomia. Imaging biomarkers could be useful to predict the toxicity risk related to each individual patient. Our preliminary work aims to develop a radiomic-based support tool exploiting pre-treatment CT images to predict late xerostomia risk in 3 months after RT in patients with oropharyngeal cancer (OPC). Materials and methods: We performed a multicenter data collection. We enrolled 61 patients referred to three care centers in Apulia, Italy, out of which 22 patients experienced at least mild xerostomia 3 months after the end of the RT cycle. Pre-treatment CT images, clinical and dose features, and alcohol-smoking habits were collected. We proposed a transfer learning approach to extract quantitative imaging features from CT images by means of a pre-trained convolutional neural network (CNN) architecture. An optimal feature subset was then identified to train an SVM classifier. To evaluate the robustness of the proposed model with respect to different manual contouring practices on CTs, we repeated the same image analysis pipeline on "fake" parotid contours. Results: The best performances were achieved by the model exploiting the radiomic features alone. On the independent test, the model reached median AUC, accuracy, sensitivity, and specificity values of 81.17, 83.33, 71.43, and 90.91%, respectively. The model was robust with respect to diverse manual parotid contouring procedures. Conclusion: Radiomic analysis could help to develop a valid support tool for clinicians in planning radiotherapy treatment, by providing a risk score of the toxicity development for each individual patient, thus improving the quality of life of the same patient, without compromising patient care.

What to Do and What Not to Do in the Management of Cancer Pain: A Physician Survey and Expert Recommendations.

BACKGROUND: Despite the prevalence of pain among patients with cancer and the availability of pertinent guidelines, the clinical management of oncological pain is decisively insufficient. To address this issue, we evaluated current trends in clinical practice and subsequently generated a list of ten corrective actions-five things to do and five things not to do-for the diagnosis, management, and monitoring of cancer pain. METHODS: The survey included 18 questions about clinical practice surrounding background pain and breakthrough cancer pain (BTcP). Survey questions were developed by a scientific board of 10 physician experts and communicated via email to an expanded panel of physicians in Italy. Responses were tabulated descriptively for analysis. RESULTS: Of 51 invited physicians, 32 (63%) provided complete survey responses. The responses revealed several incongruencies with current guideline recommendations: physicians did not always diagnose or monitor pain using diagnostically validated or disease-specific instruments; frequently based clinical decision-making on time availability or convenience; and pharmacological therapy was often inappropriate (eg, prescribing NSAIDs or corticosteroids for BTcP). The list of corrective actions generated by the scientific board favored a guideline-oriented approach that systematically characterizes oncological pain and implements treatment based on pain characteristics (eg, fast-acting transmucosal opioids for BTcP) and evidence-based recommendations. CONCLUSION: Oncologists require better education and training about the diagnosis, treatment, and monitoring of oncological pain. Physicians should be aware of current guideline recommendations as well as available pharmacological tools for BTcP.

Breakthrough Cancer Pain Clinical Features and Differential Opioids Response: A Machine Learning Approach in Patients With Cancer From the IOPS-MS Study.

PURPOSE: A large proportion of patients with cancer suffer from breakthrough cancer pain (BTcP). Several unmet clinical needs concerning BTcP treatment, such as optimal opioid dosages, are being investigated. In this analysis the hypothesis, we explore with an unsupervised learning algorithm whether distinct subtypes of BTcP exist and whether they can provide new insights into clinical practice. METHODS: Partitioning around a k-medoids algorithm on a large data set of patients with BTcP, previously collected by the Italian Oncologic Pain Survey group, was used to identify possible subgroups of BTcP. Resulting clusters were analyzed in terms of BTcP therapy satisfaction, clinical features, and use of basal pain and rapid-onset opioids. Opioid dosages were converted to a unique scale and the BTcP opioids-to-basal pain opioids ratio was calculated for each patient. We used polynomial logistic regression to catch nonlinear relationships between therapy satisfaction and opioid use. RESULTS: Our algorithm identified 12 distinct BTcP clusters. Optimal BTcP opioids-to-basal pain opioids ratios differed across the clusters, ranging from 15% to 50%. The majority of clusters were linked to a peculiar association of certain drugs with therapy satisfaction or dissatisfaction. A free online tool was created for new patients' cluster computation to validate these clusters in future studies and provide handy indications for personalized BTcP therapy. CONCLUSION: This work proposes a classification for BTcP and identifies subgroups of patients with unique efficacy of different pain medications. This work supports the theory that the optimal dose of BTcP opioids depends on the dose of basal opioids and identifies novel values that are possibly useful for future trials. These results will allow us to target BTcP therapy on the basis of patient characteristics and to define a precision medicine strategy also for supportive care.

Long-term survival of an advanced colorectal cancer patient treated with Regorafenib: Case report and literature review.

Two phase 3 trials reported a prolonged survival in the third-line setting of colorectal cancer patients treated with regorafenib with the longest duration of treatment of 16 months. Herein, we reported a unique case of a patient refractory to conventional chemotherapy who showed a prolonged stable disease with regorafenib.

Factors Influencing the Clinical Presentation of Breakthrough Pain in Cancer Patients.

Background: The aim of this study was to identify potential variables influencing the clinical presentation of breakthrough cancer pain (BTP). Methods: Cancer patients with a diagnosis of BTP were enrolled. Demographic and clinical characteristics, as well as background pain and BTP characteristics were collected. Multivariate analyses were conducted to assess the correlation between BTP characteristics and the variables examined. Results: Data of 4016 patients were analysed. Average daily number of BTP episodes was 2.4, mean intensity was 7.5, and a mean duration was 43.3 min. A short onset BTP was observed in 68.9% of patients. In 30.5% of patients BTP was predictable. There were 86.0% of participants who reported a marked interference of BTP with their daily activities. Furthermore, 86.8% of patients were receiving opioids for the management of BTP. The average time to meaningful pain relief was 16.5 min and 70.9% of patients were satisfied with their BTP medications. Age, head and neck cancer, Karnofsky, background pain intensity, predictable and fast onset BTP were independently associated with the number of BTP episodes. BTP pain intensity was independently associated with background pain intensity, fast onset BTP, and Karnofsky. Neuropathic pain mechanism was independently associated with unpredictable BTP. Variables independently associated with a longer duration of BTP were age, place of visit, cancer diagnosis, disease-oriented therapy, background pain intensity and mechanism, and unpredictable BTP. Age, Karnofsky, background pain intensity, fast onset, and long duration of BTP were independently associated with interference with daily activity. Conclusions: BTP has a variable presentation depending on interdependent relationships among its different characteristics.

MicroRNA in pancreatic adenocarcinoma: predictive/prognostic biomarkers or therapeutic targets?

Pancreatic ductal adenocarcinoma (PDAC) is a tumor with a poor prognosis, short overall survival and few chemotherapeutic choices. MicroRNAs (miRNAs) are non-coding, single-stranded RNAs of around 22 nucleotides involved in the pathogenic mechanisms of carcinogenesis and metastasis. They have been studied in many tumors in order to identify potential diagnostic, prognostic or therapeutic targets. In the current literature, many studies have analyzed the role of miRNAs in PDAC. In fact, the absence of appropriate biomarkers, the difficultly of early detection of this tumor, and the lack of effective chemotherapy in patients with unresectable disease have focused attention on miRNAs as new, interesting advance in this malignancy. In this review we analyzed the role of miRNAs in PDAC in order to understand the mechanisms of action and the difference between the onco-miRNA and the tumor suppressor miRNA. We also reviewed all the data related to the use of these molecules as predictive as well as prognostic biomarkers in the course of the disease. Finally, the possible therapeutic use of miRNAs or anti-miRNAs in PDAC is also discussed. In conclusion, although there is still no clinical application for these molecules in PDAC, it is our opinion that the preclinical evidence of the role of specific miRNAs in carcinogenesis, the possibility of using miRNAs as diagnostic or prognostic biomarkers, and their potential therapeutic role, warrant future studies in PDAC.

Third-line trabectedin for a metastatic desmoplastic small round cell tumour treated with multimodal therapy.

BACKGROUND: Desmoplastic small round cell tumour (DSRCT) is a rare and aggressive cancer that usually develops in the peritoneal cavity of young males. Its prognosis is dismal, with current treatment options including the combination of multi-agent chemotherapy, aggressive surgery, radiation therapy, and autologous stem cell transplantation. Hyperthermic intraperitoneal chemotherapy (HIPEC) may also be an option. CASE REPORT: Herein we report the administration of the marine-derived multi-target antineoplastic agent, trabectedin, in a patient with DSRCT, heavily pre-treated with conventional multi-agent chemotherapy, HIPEC, and surgery. RESULTS: The patient achieved a prolonged partial response and an extended period of stable disease with third-line trabectedin, following disease progression after conventional multi-agent chemotherapy, HIPEC, and surgery. CONCLUSION: Trabectedin may be a treatment option in multimodal therapy for the management of DSRCT and warrants further research to explore the impact of trabectedin in the treatment of this disease.

The role of microRNA in head and neck cancer: current knowledge and perspectives.

Head and neck cancer is one of the most commonly diagnosed malignancies worldwide. Patients with advanced disease stages frequently develop recurrences or distant metastasis, which results a five-year survival rates of less than 60% despite considerable advances in multimodality therapy. A better understanding of molecular basis of tumorigenesis is required to improve clinical outcomes and to develop new anti-cancer drugs. microRNAs (miRNAs) are a class of small, non-coding, RNA molecules that modulate gene expression post-transcriptionally. They are important regulator in normal biological process; however miRNAs deregulation has been observed in many different tumors and is involved in tumorigenesis. miRNAs may act as tumor suppressors or as oncogenes. Several studies on head and neck cancer demonstrated how aberrant expression of miRNAs is involved in proliferation, metastasis, chemoresistence, and radioresistance. In addition, miRNAs are excellent biomarker targets because they circulate stable in human body fluids and can be obtained with non-invasive methods. Moreover, miRNAs up and down regulation has been correlated with specific cancer phenotype (poor prognosis, aggressiveness and resistance to treatment), playing a role as prognostic biomarkers. This review summarizes current finding on miRNAs in head and neck cancer and their potential role as target for next drug therapy.