Forecasting severe respiratory disease hospitalizations using machine learning algorithms.

Background: Forecasting models predicting trends in hospitalization rates have the potential to inform hospital management during seasonal epidemics of respiratory diseases and the associated surges caused by acute hospital admissions. Hospital bed requirements for elective surgery could be better planned if it were possible to foresee upcoming peaks in severe respiratory illness admissions. Forecasting models can also guide the use of intervention strategies to decrease the spread of respiratory pathogens and thus prevent local health system overload.

Real world study of sacituzumab govitecan in metastatic triple-negative breast cancer in the United Kingdom.

Background: Treatment options for pre-treated patients with metastatic triple-negative breast cancer (mTNBC) remain limited. This is the first study to assess the real-world safety and efficacy of sacituzumab govitecan (SG) in the UK.

Methods: Data was retrospectively collected from 16 tertiary UK cancer centres.

Ulcer Bleeding in the United States: Epidemiology, Treatment Success, and Resource Utilization.

Background And Goals: Peptic ulcer disease is the most frequent cause of upper gastrointestinal bleeding. We sought to establish the epidemiology and hemostasis success rate of the different treatment modalities in this setting.

Methods: Retrospective cohort study using the National Inpatient Sample.

Clinical evaluation of atlas-based auto-segmentation in breast and nodal radiotherapy.

Objectives: Accurate contouring of anatomical structures allows for high-precision radiotherapy planning, targeting the dose at treatment volumes and avoiding organs at risk. Manual contouring is time-consuming with significant user variability, whereas auto-segmentation (AS) has proven efficiency benefits but requires editing before treatment planning. This study investigated whether atlas-based AS (ABAS) accuracy improves with template atlas group size and character-specific atlas and test case selection.

Combatting over-specialization bias in growing chemical databases.

Background: Predicting in advance the behavior of new chemical compounds can support the design process of new products by directing the research toward the most promising candidates and ruling out others. Such predictive models can be data-driven using Machine Learning or based on researchers' experience and depend on the collection of past results. In either case: models (or researchers) can only make reliable assumptions about compounds that are similar to what they have seen before.

Multivariate Sequential Analytics for Cardiovascular Disease Event Prediction.

Background: Automated clinical decision support for risk assessment is a powerful tool in combating cardiovascular disease (CVD), enabling targeted early intervention that could avoid issues of overtreatment or undertreatment. However, current CVD risk prediction models use observations at baseline without explicitly representing patient history as a time series.

Objective: The aim of this study is to examine whether by explicitly modelling the temporal dimension of patient history event prediction may be improved.

Medication adherence prediction through temporal modelling in cardiovascular disease management.

Background: Chronic conditions place a considerable burden on modern healthcare systems. Within New Zealand and worldwide cardiovascular disease (CVD) affects a significant proportion of the population and it is the leading cause of death. Like other chronic diseases, the course of cardiovascular disease is usually prolonged and its management necessarily long-term.

Concept: A randomised multicentre trial of first line chemotherapy comparing three weekly cabazitaxel versus weekly paclitaxel in HER2 negative metastatic breast cancer.

Background: Paclitaxel is commonly used as first-line chemotherapy for HER2-negative metastatic breast cancer (MBC) patients. However, with response rates of 21.5-53.

Human Versus Machine: How Do We Know Who Is Winning? ROC Analysis for Comparing Human and Machine Performance under Varying Cost-Prevalence Assumptions.

Background: Receiver operating characteristic (ROC) analysis is commonly used for comparing models and humans; however, the exact analytical techniques vary and some are flawed.

Objectives: The aim of the study is to identify common flaws in ROC analysis for human versus model performance, and address them.

Methods: We review current use and identify common errors.

A Novel Approach for Time Series Forecasting of Influenza-like Illness Using a Regression Chain Method.

Influenza is a communicable respiratory illness that can cause serious public health hazards. Due to its huge threat to the community, accurate forecasting of Influenza-like-illness (ILI) can diminish the impact of an influenza season by enabling early public health interventions. Machine learning models are increasingly being applied in infectious disease modelling, but are limited in their performance, particularly when using a longer forecasting window.

A mental models approach for defining explainable artificial intelligence.

Background: Wide-ranging concerns exist regarding the use of black-box modelling methods in sensitive contexts such as healthcare. Despite performance gains and hype, uptake of artificial intelligence (AI) is hindered by these concerns. Explainable AI is thought to help alleviate these concerns.

A patch of positively charged residues regulates the efficacy of clinical DR5 antibodies in solid tumors.

Receptor clustering is the first and critical step to activate apoptosis by death receptor-5 (DR5). The recent discovery of the autoinhibitory DR5 ectodomain has challenged the long-standing view of its mechanistic activation by the natural ligand Apo2L. Because the autoinhibitory residues have remained unknown, here we characterize a crucial patch of positively charged residues (PPCR) in the highly variable domain of DR5.

Mechanobehavior and mandibular ramus length in different facial phenotypes.

Objectives: To test the hypotheses that mechanobehavior scores (MBS) were correlated with mandibular ramus lengths (Co-Go) and differed between facial phenotypes.

Materials And Methods: Subjects gave informed consent to participate. Co-Go (mm), mandibular plane angles (SN-GoGn, °), and three-dimensional anatomy were derived from cephalometric radiography or cone beam computed tomography.

Diagnosis at gut point: rapid identification of pneumoperitoneum via point-of-care ultrasound.

Undifferentiated abdominal pain is a common presentation often requiring immediate medical or surgical intervention. Providing an accurate diagnosis involves a detailed patient history and thorough physical exam. Point of care ultrasound is gaining acceptance as a rapid diagnostic tool that can be used to accurately detect life-threatening conditions while potentially avoiding unnecessary radiation exposure and facilitating rapid treatment.

Postoperative chemotherapy improves survival in patients with resected high-risk Stage II colorectal cancer: results of a systematic review and meta-analysis.

Aim: The aim was to assess the benefit of adjuvant chemotherapy in high-risk Stage II colorectal cancer.

Method: A systematic literature review and meta-analysis was performed comparing survival in patients with resected Stage II colorectal cancer and high-risk features having postoperative chemotherapy vs no chemotherapy.

Results: Of 1031 articles screened, 29 were included, reporting on 183 749 participants.

Neural response to pictorial health warning labels can predict smoking behavioral change.

In order to improve our understanding of how pictorial health warning labels (HWLs) influence smoking behavior, we examined whether brain activity helps to explain smoking behavior above and beyond self-reported effectiveness of HWLs. We measured the neural response in the ventromedial prefrontal cortex (vmPFC) and the amygdala while adult smokers viewed HWLs. Two weeks later, participants' self-reported smoking behavior and biomarkers of smoking behavior were reassessed.

Neoadjuvant chemotherapy and trastuzumab versus neoadjuvant chemotherapy followed by post-operative trastuzumab for patients with HER2-positive breast cancer.

Neoadjuvant chemotherapy plus trastuzumab (NCT) increases the rate of pathological complete response (pCR) and event-free survival (EFS) compared to neoadjuvant chemotherapy (NC) alone in women with HER2 positive breast cancer (BC). pCR in this setting is associated with improved EFS. Whether NCT preferentially improves EFS in comparison to NC followed by adjuvant trastuzumab initiated postoperatively (NCAT) has not been addressed.

Imaging of cellular proliferation in liver metastasis by [18F]fluorothymidine positron emission tomography: effect of therapy.

Although [(18)F]fluorothymidine positron emission tomography (FLT-PET) permits estimation of tumor thymidine kinase-1 expression, and thus, cell proliferation, high physiological uptake of tracer in liver tissue can limit its utility. We evaluated FLT-PET combined with a temporal-intensity information-based voxel-clustering approach termed kinetic spatial filtering (FLT-PET(KSF)) for detecting drug response in liver metastases. FLT-PET and computed tomography data were collected from patients with confirmed breast or colorectal liver metastases before, and two weeks after the first cycle of chemotherapy.

Human epidermal growth factor receptor 2-positive breast cancer relapsing post-adjuvant trastuzumab: pattern of recurrence, treatment and outcome.

Background: The purpose of this study is to evaluate the response to and benefit of first-line metastatic treatment (including re-exposure to trastuzumab) for patients relapsing after exposure to adjuvant trastuzumab (AT).

Patients And Methods: All HER2-positive breast cancer cases relapsing after exposure to AT at our institutions were identified. Clinico-pathologic details, pattern of relapse, and treatment in the metastatic setting were documented.

Management and outcome of HER2-positive early breast cancer treated with or without trastuzumab in the adjuvant trastuzumab era.

Background: Adjuvant trastuzumab (AT) is known to significantly improve survival of women with HER2(+) early breast cancer. This study explores the use and nonuse of AT in early breast cancer, as well as the efficacy in a neoadjuvant and adjuvant population, within a routine clinical setting.

Patients And Methods: Histopathology reports of invasive breast cancer resected at Imperial College Healthcare NHS Trust (ICHT) between January 2006 and December 2008 were reviewed.

Semantic Space models for classification of consumer webpages on metadata attributes.

To deal with the quantity and quality issues with online healthcare resources, creating web portals centred on particular health topics and/or communities of users is a strategy to provide access to a reduced corpus of information resources that meet quality and relevance criteria. In this paper we use hyperspace analogue to language (HAL) to model the language use patterns of webpages as Semantic Spaces. We have applied machine learning methods, including support vector machine (SVM), decision forest, and a novel summed similarity measure (SSM) to automatically classify online webpages on their Semantic Space models.

Acute myeloid leukaemia secondary to treatment with capecitabine for metastatic colorectal cancer.

A 63-year-old woman was diagnosed with acute myelo-monocytic leukaemia, associated with MLL gene rearrangement, 16 months after completion of oral capecitabine for metastatic colon cancer. Capecitabine, recommended for use in metastatic breast and colon cancer and more recently as adjuvant treatment of colon cancer, has not previously been reported to be associated with secondary cancer.