Toward real-time reporting of cancer incidence: methodology, pilot study, and SEER Program implementation.

Background: A lag time between cancer case diagnosis and incidence reporting impedes the ability to monitor the impact of recent events on cancer incidence. Currently, the data submission standard is 22 months after a diagnosis year ends, and the reporting standard is 27.5 months after a diagnosis year ends.

Machine learning and deep learning tools for the automated capture of cancer surveillance data.

The National Cancer Institute and the Department of Energy strategic partnership applies advanced computing and predictive machine learning and deep learning models to automate the capture of information from unstructured clinical text for inclusion in cancer registries. Applications include extraction of key data elements from pathology reports, determination of whether a pathology or radiology report is related to cancer, extraction of relevant biomarker information, and identification of recurrence. With the growing complexity of cancer diagnosis and treatment, capturing essential information with purely manual methods is increasingly difficult.

Central Nervous System (CNS) T-Cell Lymphoma as the Presenting Manifestation of Late-Onset Combined Immunodeficiency.

Late-onset combined immunodeficiency (LOCID), considered now a subset of common variable immunodeficiency (CVID) disorders, is characterized by a predominantly T-cell immune defect. LOCID has a distinct phenotype from CVID with a greater risk of lymphoproliferative complications. As compared to the CVID cohort, LOCID patients also have increased rates of splenomegaly and granulomatous disease.

A dynamic model of the intestinal epithelium integrates multiple sources of preclinical data and enables clinical translation of drug-induced toxicity.

We have built a quantitative systems toxicology modeling framework focused on the early prediction of oncotherapeutic-induced clinical intestinal adverse effects. The model describes stem and progenitor cell dynamics in the small intestinal epithelium and integrates heterogeneous epithelial-related processes, such as transcriptional profiles, citrulline kinetics, and probability of diarrhea. We fitted a mouse-specific version of the model to quantify doxorubicin and 5-fluorouracil (5-FU)-induced toxicity, which included pharmacokinetics and 5-FU metabolism and assumed that both drugs led to cell cycle arrest and apoptosis in stem cells and proliferative progenitors.

Device Exchange to HeartMate 3 LVAD: Impact of Previous Pump Model on Clinical Outcomes.

Background: We describe our clinical experience performing device exchange from a HeartMate II (HM2) or HVAD to a HeartMate 3 (HM3) left ventricular assist device.

Methods: A single-center retrospective study was performed of all patients (N = 14) who underwent a left ventricular assist device exchange from HM2 (n = 7) or HVAD (n = 7) to HM3 between October 2018 and October 2021. The primary outcome was 1-year overall survival, and secondary outcomes included adverse events through discharge.

Delivering the 2022 highlights of .

Happy new year to all our readers at  and welcome to volume 14 of the journal! I would like to take this opportunity to discuss our content highlights and authorship demographics across volume 13 of the journal and look toward the exciting things to come in the upcoming year.

Nonclinical pharmacokinetics and biodistribution of VSV-GP using methods to decouple input drug disposition and viral replication.

Viral replication places oncolytic viruses (OVs) in a unique niche in the field of drug pharmacokinetics (PK) as their self-amplification obscures exposure-response relationships. Moreover, standard bioanalytical techniques are unable to distinguish the input from replicated drug products. Here, we combine two novel approaches to characterize PK and biodistribution (BD) after systemic administration of vesicular stomatitis virus pseudotyped with lymphocytic choriomeningitis virus glycoprotein (VSV-GP) in healthy mice First: to decouple input drug PK/BD versus replication PK/BD, we developed and fully characterized a replication-incompetent tool virus that retained all other critical attributes of the drug.

Amide Modifications in the Seed Region of the Guide Strand Improve the On-Target Specificity of Short Interfering RNA.

RNA interference (RNAi) is a well-established research tool and is also maturing as a novel therapeutic approach. For the latter, microRNA-like off-target activity of short interfering RNAs (siRNAs) remains as one of the main problems limiting RNAi drug development. In this communication, we report that replacement of a single internucleoside phosphodiester in the seed region (nucleotides 2 to 7) of the guide strand with an amide linkage suppressed the undesired microRNA-like off-target activity by at least an order of magnitude.

Using ensembles and distillation to optimize the deployment of deep learning models for the classification of electronic cancer pathology reports.

Objective: We aim to reduce overfitting and model overconfidence by distilling the knowledge of an ensemble of deep learning models into a single model for the classification of cancer pathology reports.

Materials And Methods: We consider the text classification problem that involves 5 individual tasks. The baseline model consists of a multitask convolutional neural network (MtCNN), and the implemented ensemble (teacher) consists of 1000 MtCNNs.

Second primary malignancies in chronic lymphocytic leukaemia: Skin, solid organ, haematological and Richter's syndrome.

Chronic lymphocytic leukaemia (CLL) is invariably accompanied by some degree of immune failure, and CLL patients have a high rate of second primary malignancy (SPM) compared to the general population. We comprehensively documented the incidence of all forms of SPM including skin cancer (SC), solid organ malignancy (SOM), second haematological malignancy (SHM) and separately Richter's syndrome (RS) across all therapy eras. Among the 517 CLL/small lymphocytic lymphoma (SLL) patients, the overall incidence of SPMs with competing risks was SC 31.

Automatic information extraction from childhood cancer pathology reports.

Objectives: The International Classification of Childhood Cancer (ICCC) facilitates the effective classification of a heterogeneous group of cancers in the important pediatric population. However, there has been no development of machine learning models for the ICCC classification. We developed deep learning-based information extraction models from cancer pathology reports based on the ICD-O-3 coding standard.

Unusual presentations of central nervous system myeloid sarcoma.

Myeloid sarcoma (MS), also termed 'chloroma' or 'granulocytic sarcoma', is a tumour mass consisting of myeloid blasts occurring at an anatomical site other than the bone marrow. MS occurs in up to 8% of patients with acute myeloid leukaemia. While MS typically involves the skin or lymph nodes, almost any tissue can be affected, and symptoms largely depend on the organ involved and subsequent mass effect.

Amide Internucleoside Linkages Are Well Tolerated in Protospacer Adjacent Motif-Distal Region of CRISPR RNAs.

The development of CRISPR-Cas9 mediated gene editing technology is revolutionizing molecular biology, biotechnology, and medicine. However, as with other nucleic acid technologies, CRISPR would greatly benefit from chemical modifications that optimize delivery, activity, and specificity of gene editing. Amide modifications at certain positions of short interfering RNAs have been previously shown to improve their RNAi activity and specificity, which motivated the current study on replacement of selected internucleoside phosphates of CRISPR RNAs with amide linkages.

A Transcriptomic Approach to Elucidate the Mechanisms of Gefitinib-Induced Toxicity in Healthy Human Intestinal Organoids.

Gefitinib is a tyrosine kinase inhibitor (TKI) that selectively inhibits the epidermal growth factor receptor (EGFR), hampering cell growth and proliferation. Due to its action, gefitinib has been used in the treatment of cancers that present abnormally increased expression of EGFR. However, side effects from gefitinib therapy may occur, among which diarrhoea is most common, that can lead to interruption of the planned therapy in the more severe cases.

Optimal vocabulary selection approaches for privacy-preserving deep NLP model training for information extraction and cancer epidemiology.

Background: With the use of artificial intelligence and machine learning techniques for biomedical informatics, security and privacy concerns over the data and subject identities have also become an important issue and essential research topic. Without intentional safeguards, machine learning models may find patterns and features to improve task performance that are associated with private personal information.

Objective: The privacy vulnerability of deep learning models for information extraction from medical textural contents needs to be quantified since the models are exposed to private health information and personally identifiable information.