Development of a generalizable natural language processing pipeline to extract physician-reported pain from clinical reports: Generated using publicly-available datasets and tested on institutional clinical reports for cancer patients with bone metastases.

OBJECTIVE: The majority of cancer patients suffer from severe pain at the advanced stage of their illness. In most cases, cancer pain is underestimated by clinical staff and is not properly managed until it reaches a critical stage. Therefore, detecting and addressing cancer pain early can potentially improve the quality of life of cancer patients. The objective of this research project was to develop a generalizable Natural Language Processing (NLP) pipeline to find and classify physician-reported pain in the radiation oncology consultation notes of cancer patients with bone metastases. MATERIALS AND METHODS: The texts of 1249 publicly-available hospital discharge notes in the i2b2 database were used as a training and validation set. The MetaMap and NegEx algorithms were implemented for medical terms extraction. Sets of NLP rules were developed to score pain terms in each note. By averaging pain scores, each note was assigned to one of the three verbally-declared pain (VDP) labels, including no pain, pain, and no mention of pain. Without further training, the generalizability of our pipeline in scoring individual pain terms was tested independently using 30 hospital discharge notes from the MIMIC-III database and 30 consultation notes of cancer patients with bone metastasis from our institution's radiation oncology electronic health record. Finally, 150 notes from our institution were used to assess the pipeline's performance at assigning VDP. RESULTS: Our NLP pipeline successfully detected and quantified pain in the i2b2 summary notes with 93% overall precision and 92% overall recall. Testing on the MIMIC-III database achieved precision and recall of 91% and 86% respectively. The pipeline successfully detected pain with 89% precision and 82% recall on our institutional radiation oncology corpus. Finally, our pipeline assigned a VDP to each note in our institutional corpus with 84% and 82% precision and recall, respectively. CONCLUSION: Our NLP pipeline enables the detection and classification of physician-reported pain in our radiation oncology corpus. This portable and ready-to-use pipeline can be used to automatically extract and classify physician-reported pain from clinical notes where the pain is not otherwise documented through structured data entry.

Cellular mRNA recruits the ribosome via eIF3-PABP bridge to initiate internal translation.

IRES-mediated translation of key cell fate regulating genes has been implicated in tumorigenesis. Concerted action of canonical eukaryotic initiation factors and IRES transacting factors (ITAFs) was shown to regulate cellular IRES mediated translation; however, the precise molecular mechanism of ribosome recruitment to cellular IRESes remains unclear. Here we show that the X-linked inhibitor of apoptosis (XIAP) IRES operates in an evolutionary conserved viral like mode and the structural integrity, particularly in the vicinity of AUG, is critical for ribosome recruitment. The binding of eIF3 together with PABP potentiates ribosome recruitment to the IRES. Our data support the model in which eIF3 binds directly to the XIAP IRES RNA in a structure-dependent manner and acts as a scaffold for IRES RNA, PABP and the 40S ribosome.

The role of IRES trans-acting factors in carcinogenesis.

Regulation of protein expression through RNA metabolism is a key aspect of cellular homeostasis. Upon specific cellular stresses, distinct transcripts are selectively controlled to modify protein output in order to quickly and appropriately respond to stress. Reprogramming of the translation machinery is one node of this strict control that typically consists of an attenuation of the global, cap-dependent translation and accompanying switch to alternative mechanisms of translation initiation, such as internal ribosome entry site (IRES)-mediated initiation. In cancer, many aspects of the RNA metabolism are frequently misregulated to provide cancer cells with a growth and survival advantage. This includes changes in the expression and function of RNA binding proteins termed IRES trans-acting factors (ITAFs) that are central to IRES translation. In this review, we will examine select emerging, as well as established, ITAFs with important roles in cancer initiation and progression, and in particular their role in IRES-mediated translation. This article is part of a Special Issue entitled: Translation and Cancer.

Safety and Efficacy of 2D Brachytherapy vs. 3D Image-Guided Adaptive Brachytherapy for Locally Advanced Cervical Cancer-A Single Institution Retrospective Study.

BACKGROUND: The treatment paradigm for locally advanced cervical cancer (LACC) has shifted from two-dimensional-brachytherapy (2D-BT) to three-dimensional-image-guided adaptive BT (3D-IGABT). In this retrospective study, we report our experience with the change from 2D-BT to 3D-IGABT. METHODS: We reviewed 146 LACC patients (98 3D-IGABT and 48 2D-BT) who received chemoradiation between 2004 and 2019. The multivariable odds ratio (OR) for treatment-related toxicities and hazard ratios (HR) for locoregional control (LRC), distant control (DC), failure-free survival (FFS), cancer-specific survival (CSS) and overall survival (OS) are reported. RESULTS: The median follow-up was 50.3 months. There was a significant decrease in overall late toxicities in the 3D-IGABT group compared to the 2D-BT group (OR 0.22[0.10-0.52]), late gastrointestinal (OR 0.31[0.10-0.93]), genitourinary (OR 0.31[0.09-1.01]) and vaginal toxicities (0% vs. 29.6%). Grade ≥ 3 toxicity was low in both groups (2D-BT: 8.2% acute, 13.3% late vs. 3D-IGABT: 6.3% acute, 4.4% late, NS). The five-year LRC, DC, FFS, CSS and OS for 3D-IGABT were 92.0%, 63.4%, 61.7%, 75.4% and 73.6%, compared to 87.3%, 71.8%, 63.7%, 76.3% and 70.8% for 2D-BT (NS). CONCLUSIONS: 3D-IGABT for the treatment of LACC is associated with a decrease in overall late gastrointestinal, genitourinary and vaginal toxicities. The disease control or survival outcomes were comparable to contemporary 3D-IGABT studies.

A Scalable Radiomics- and Natural Language Processing-Based Machine Learning Pipeline to Distinguish Between Painful and Painless Thoracic Spinal Bone Metastases: Retrospective Algorithm Development and Validation Study.

BACKGROUND: The identification of objective pain biomarkers can contribute to an improved understanding of pain, as well as its prognosis and better management. Hence, it has the potential to improve the quality of life of patients with cancer. Artificial intelligence can aid in the extraction of objective pain biomarkers for patients with cancer with bone metastases (BMs). OBJECTIVE: This study aimed to develop and evaluate a scalable natural language processing (NLP)- and radiomics-based machine learning pipeline to differentiate between painless and painful BM lesions in simulation computed tomography (CT) images using imaging features (biomarkers) extracted from lesion center point-based regions of interest (ROIs). METHODS: Patients treated at our comprehensive cancer center who received palliative radiotherapy for thoracic spine BM between January 2016 and September 2019 were included in this retrospective study. Physician-reported pain scores were extracted automatically from radiation oncology consultation notes using an NLP pipeline. BM center points were manually pinpointed on CT images by radiation oncologists. Nested ROIs with various diameters were automatically delineated around these expert-identified BM center points, and radiomics features were extracted from each ROI. Synthetic Minority Oversampling Technique resampling, the Least Absolute Shrinkage And Selection Operator feature selection method, and various machine learning classifiers were evaluated using precision, recall, F1-score, and area under the receiver operating characteristic curve. RESULTS: Radiation therapy consultation notes and simulation CT images of 176 patients (mean age 66, SD 14 years; 95 males) with thoracic spine BM were included in this study. After BM center point identification, 107 radiomics features were extracted from each spherical ROI using pyradiomics. Data were divided into 70% and 30% training and hold-out test sets, respectively. In the test set, the accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve of our best performing model (neural network classifier on an ensemble ROI) were 0.82 (132/163), 0.59 (16/27), 0.85 (116/136), and 0.83, respectively. CONCLUSIONS: Our NLP- and radiomics-based machine learning pipeline was successful in differentiating between painful and painless BM lesions. It is intrinsically scalable by using NLP to extract pain scores from clinical notes and by requiring only center points to identify BM lesions in CT images.

Phase II trial of concurrent sunitinib, temozolomide, and radiotherapy with adjuvant temozolomide for newly diagnosed MGMT unmethylated glioblastoma.

Background: The overall prognosis of glioblastoma (GBM) remains dismal, particularly for patients with unmethylated O6-methylguanine-DNA-methyltransferase (MGMT) promoter. In this phase II trial, we tested the combination of the antiangiogenic agent sunitinib with radiotherapy and temozolomide (TMZ) for newly diagnosed unmethylated MGMT GBM patients. Methods: We enrolled 37 patients with unmethylated MGMT promoter GBM, age 18-70, and KPS ≥70. Patients received 12.5 mg of daily sunitinib for 7 days, followed by concurrent chemoradiation plus 12.5 mg sunitinib, then adjuvant TMZ. The primary endpoint was progression-free survival (PFS), and secondary endpoints were overall survival (OS), safety, and neutrophil-to-lymphocyte ratio (NLR) biomarker. Results: At a median follow-up time of 15.3 months (range: 3.1-71.3 months), the median PFS was 7.15 months (95% CI: 5.4-10.5) and the 6-month PFS was 54.0%. Median OS was 15.0 months (95% CI: 13.8-19.4) and 2-year OS rate was 17.1%. Patients receiving >3 cycles of adjuvant TMZ, undergoing surgery at progression, and presenting a post-concurrent NLR ≤6 experienced a significant improved OS with hazard ratios of 0.197 (P = .001), 0.46 (P = .049), and 0.38 (P = .021), respectively, on multivariable analysis. Age >65 years predicted for worse OS with hazard ratio of 3.92 (P = .037). Grade ≥3 thrombocytopenia occurred in 22.9%, grade ≥3 neutropenia in 20%, and grade ≥3 thromboembolic events in 14.3% of patients. There were no grade 5 events. Conclusion: Our findings suggest a potential benefit of combining sunitinib with chemoradiation in newly diagnosed GBM patients with unmethylated MGMT status and provide a strong rationale to test this combination in future studies.

Advances in Radiation Oncology for the Treatment of Cervical Cancer.

BACKGROUND: Over the past two decades, there has been significant advancement in the management of cervical cancer, particularly in the domain of definitive chemoradiotherapy for locally advanced cervical cancer (LACC). Indeed, radiation treatment paradigms have shifted from a two-dimensional (2D) approach solely based on anatomical bony landmarks, to an image-guided three-dimensional (3D) approach, with the goal of delivering doses more precisely to clinical targets with an increased sparing of organs-at-risk. METHODS: This is a narrative review on the advances in radiation technologies for the treatment of cervical cancer. Using the PubMed database, we identified articles published in English up until November 18, 2021 on the treatment of LACC with external beam radiotherapy (EBRT) and brachytherapy. A search of the Clinicaltrials.gov and Clinicaltrialsregister.eu retrieved information on ongoing clinical trials on the topic of combined immunotherapy and radiotherapy in cervical cancer. RESULTS: We highlight the historical evolution from the use of 2D radiotherapy to 3D-conformal radiotherapy, and then intensity modulated radiotherapy (IMRT) for the delivery of EBRT. We also discuss advances in brachytherapy, notably the transition to 3D image-guided adaptive brachytherapy (3D-IGABT). In this context, we highlight large cohort studies that were recently constructed and have shown significant improvement in local control and treatment-related toxicities with 3D-IGABT. Finally, we discuss other advances in the field, notably the use of stereotactic body radiotherapy (SBRT) as a substitute to brachytherapy, and the addition of immunotherapy to chemoradiation. CONCLUSIONS: The use of IG-IMRT and 3D-IGABT have considerably improved treatment outcomes and toxicity profiles for patients with LACC, and are now considered the gold standard in many countries. The use of SBRT boost as a replacement for brachytherapy has been associated with increased toxicity and decreased efficacy and should be used with caution in the context of clinical trials. New experimental approaches include the addition of immunotherapy to chemoradiation regimens.

Radiomics-based machine learning models to distinguish between metastatic and healthy bone using lesion-center-based geometric regions of interest.

Radiomics-based machine learning classifiers have shown potential for detecting bone metastases (BM) and for evaluating BM response to radiotherapy (RT). However, current radiomics models require large datasets of images with expert-segmented 3D regions of interest (ROIs). Full ROI segmentation is time consuming and oncologists often outline just RT treatment fields in clinical practice. This presents a challenge for real-world radiomics research. As such, a method that simplifies BM identification but does not compromise the power of radiomics is needed. The objective of this study was to investigate the feasibility of radiomics models for BM detection using lesion-center-based geometric ROIs. The planning-CT images of 170 patients with non-metastatic lung cancer and 189 patients with spinal BM were used. The point locations of 631 BM and 674 healthy bone (HB) regions were identified by experts. ROIs with various geometric shapes were centered and automatically delineated on the identified locations, and 107 radiomics features were extracted. Various feature selection methods and machine learning classifiers were evaluated. Our point-based radiomics pipeline was successful in differentiating BM from HB. Lesion-center-based segmentation approach greatly simplifies the process of preparing images for use in radiomics studies and avoids the bottleneck of full ROI segmentation.

Late Gastrointestinal Tolerance After Prostate Radiotherapy: Is the Anal Canal the Culprit? A Narrative Critical Review.

INTRODUCTION: Late gastro-intestinal toxicities (LGIT) secondary to pelvic radiotherapy (RT) are well described in the literature. LGIT are mainly related to rectal or ano-rectal irradiation; however, involvement of the anal canal (AC) in the occurrence of LGIT remains poorly described and understood. MATERIALS AND METHODS: The aim of this work was to explore the potential role of the AC in the development of LGIT after prostate irradiation and identify predictive factors that could be optimized in order to limit these toxicities. This narrative literature review was realized using the Pubmed database. We identified original articles published between June 1997 and July 2019, relating to LGIT after RT for localized prostate cancer and for which AC was identified independently. Articles defining the AC as part of an anorectal or rectal volume only were excluded. RESULTS: A history of abdominal surgery or cardio-vascular risk, anticoagulant or tobacco use, and the occurrence of acute GIT during RT increases the risk of LGIT. A dose-effect relationship was identified between dose to the AC and development of LGIT. Identification and contouring of the AC and adjacent anatomical structures (muscles or nerves) are justified to apply specific dose constraints. As a limitation, our review mainly considered on 3DCRT which is no longer the standard of care nowadays; we did not identify any reports in the literature using moderately hypofractionated RT for the prostate and AC specific dosimetry. CONCLUSION: These results suggest that the AC may have an important role in the development of LGIT after pelvic RT for prostate cancer. The individualization of the AC during planning should be recommended in prospective studies.

Extreme weekly locoregional hypofractionated radiation in elderly women with non-metastatic breast cancer.

BACKGROUND AND PURPOSE: Breast cancer locoregional (LR) radiation in the elderly requires careful consideration between the benefits of aggressive treatment and its potential toll on these patients. Extreme weekly LR hypofractionated radiation (HFRT), delivering >5 Gy per fraction, may be better suited in such a population. It represents a good compromise between RT omission and exhaustive daily radiation. This study aims to report the local and LR control rate as well as the acute and long-term side effects of the elderly patients treated with HFRT in our institution, and to compare these results to those from the literature. MATERIALS AND METHODS: We conducted a retrospective study by reviewing medical records of elderly patients with breast cancer treated with adjuvant once-weekly LR HFRT between 2011 and 2020. Fifty patients presenting with primary non-metastatic node-positive breast tumors were included. Treatment outcomes including local/LR control and overall survival were reported. Early and late toxicity profiles were also assessed. RESULTS: After a median follow-up of 4.8 years, only one local recurrence in the chest wall occurred and there was no regional recurrence. The distant metastatic rate was 6%. The long-term recurrence-free survival rate was 80% at 5 years. The cause specific survival rate was 90% at 5 years. The overall survival rate was 69.4% and 55.5% at 3 and 5 years, respectively. There were 44 (88%) patients with Grade 1 or 2 early toxicity. There was no Grade 3 or higher acute toxicity registered. Late toxicity was mainly Grade 1 or 2 subcutaneous fibrosis, lymphoedema, and neuropathy except for one patient with Grade 3 fibrosis. CONCLUSION: Extreme LR HFRT is well tolerated with good outcomes and is a good alternative for elderly and frail patients. Our results confirm the efficacy and safety of such a regimen. Further randomized trials assessing both oncologic outcome and toxicity profile are justified.

Post-Operative Radiotherapy in Prostate Cancer: Is It Time for a Belt and Braces Approach?

Approximately 30% of patients treated with radical prostatectomy (RP) for prostate cancers experience biochemical recurrence (BCR). Post-operative radiation therapy (RT) can be either offered immediately after the surgery in case of aggressive pathological features or proposed early if BCR occurs. Until recently, little data were available regarding the optimal RT timing, protocol, volumes to treat, and the benefit of adding androgen deprivation therapies to post-operative RT. In this review, we aim to pragmatically discuss current literature data on these points. Early salvage RT appears to be the optimal post-operative approach, improving oncological outcomes especially with low prostate-specific antigen (PSA) levels, as well as sparing several unnecessary adjuvant treatments. The standard RT dose is still 64-66 Gy to the prostate bed in conventional fractionation, but hypofractionation protocols are emerging pending on late toxicity data. Several scientific societies have published contouring atlases, even though they are heterogeneous and deserve future consensus. During salvage RT, the inclusion of pelvic lymph nodes is also controversial, but preliminary data show a possible benefit for PSA > 0.34 ng/ml at the cost of increased hematological side effects. Concomitant ADT and its duration are also discussed, possibly advantageous (at least in terms of metastasis-free survival) for PSA rates over 0.6 ng/ml, taking into account life expectancy and cardiovascular comorbidities. Intensified regimens, for instance, with new-generation hormone therapies, could further improve outcomes in carefully selected patients. Finally, recent advances in molecular imaging, as well as upcoming breakthroughs in genomics and artificial intelligence tools, could soon reshuffle the cards of the current therapeutic strategy.

Pax-5 is a potent regulator of E-cadherin and breast cancer malignant processes.

Pax-5, an essential transcription factor for B lymphocyte development, has been linked with the development and progression of lymphoid cancers and carcinoma. In contrast to B-cell cancer lesions, the specific expression signatures and roles of Pax-5 in breast cancer progression are relatively unknown. In the present study, we set out to profile Pax-5 expression in mammary tissues and elucidate the cellular and molecular roles of Pax-5 in breast cancer processes. Using immunohistology on mammary tissue arrays, Pax-5 was detected in a total of 298/306 (97.6%) samples tested. Interestingly, our studies reveal that Pax-5 inhibits aggressive features and confers anti-proliferative effects in breast carcinoma cells in contrast to its oncogenic properties in B cell cancers. More precisely, Pax-5 suppressed breast cancer cell migration, invasion and tumor spheroid formation while concomitantly promoting cell adhesion properties. We also observed that Pax-5 inhibited and reversed breast cancer epithelial to mesenchymal phenotypic transitioning. Mechanistically, we found that the Pax-5 transcription factor binds and induces gene expression of E-cadherin, a pivotal regulator of epithelialisation. Globally, we demonstrate that Pax-5 is predominant expressed factor in mammary epithelial cells. We also present an important role for Pax-5 in the phenotypic transitioning processes and aggressive features associated with breast cancer malignancy and disease progression.

Assessment of selective mRNA translation in mammalian cells by polysome profiling.

Regulation of protein synthesis represents a key control point in cellular response to stress. In particular, discreet RNA regulatory elements were shown to allow to selective translation of specific mRNAs, which typically encode for proteins required for a particular stress response. Identification of these mRNAs, as well as the characterization of regulatory mechanisms responsible for selective translation has been at the forefront of molecular biology for some time. Polysome profiling is a cornerstone method in these studies. The goal of polysome profiling is to capture mRNA translation by immobilizing actively translating ribosomes on different transcripts and separate the resulting polyribosomes by ultracentrifugation on a sucrose gradient, thus allowing for a distinction between highly translated transcripts and poorly translated ones. These can then be further characterized by traditional biochemical and molecular biology methods. Importantly, combining polysome profiling with high throughput genomic approaches allows for a large scale analysis of translational regulation.

Nucleotide composition of cellular internal ribosome entry sites defines dependence on NF45 and predicts a posttranscriptional mitotic regulon.

The vast majority of cellular mRNAs initiate their translations through a well-defined mechanism of ribosome recruitment that occurs at the 5'-terminal 7-methylguanosine cap with the help of several canonical protein factors. A subset of cellular and viral mRNAs contain regulatory motifs in their 5' untranslated regions (UTRs), termed internal ribosome entry sites (IRES), that sidestep this canonical mode of initiation. On cellular mRNAs, this mechanism requires IRES trans-acting protein factors (ITAFs) that facilitate ribosome recruitment downstream of the cap. While several ITAFs and their target mRNAs have been empirically identified, the in silico prediction of targets has proved difficult. Here, we report that a high AU content (>60%) of the IRES-containing 5' UTRs serves as an excellent predictor of dependence on NF45, a recently identified ITAF. Moreover, we provide evidence that cells deficient in NF45 ITAF activity exhibit reduced IRES-mediated translation of X-linked inhibitor of apoptosis protein (XIAP) and cellular inhibitor of apoptosis protein 1 (cIAP1) mRNAs that, in turn, leads to dysregulated expression of their respective targets, survivin and cyclin E. This specific defect in IRES translation explains in part the cytokinesis impairment and senescence-like phenotype observed in HeLa cells expressing NF45 RNA interference (RNAi). This study uncovers a novel role for NF45 in regulating ploidy and highlights the importance of IRES-mediated translation in cellular homeostasis.