ABSTRACT
Health literacy is the ability of a person to read and understand medical text and to use that information to make informed healthcare decisions. Unfortunately, medical articles are difficult to comprehend by common people as they use complex language and domain-specific terms. Improving health literacy is important for empowering communities against emerging threats and the COVID-19 pandemic bears testimony to this statement. One way to improve health literacy is easing access to complex healthcare information by summarising medical texts and simplifying them lexically by translating specific medical terminology to laymen's terms. In this paper we propose a system that performs extractive summarization on the medical article given as input followed by named entity recognition for identifying medical terms. The meanings of identified medical entities are then found through web scraping and displayed to the user along with the summary. We have experimented with state-of-the-art summarization models and Albert (A lite BERT) has provided the best ROUGE-1 score of 0.3789 and ROUGE-L of 0.2084. © 2022 IEEE.
ABSTRACT
Background: Coronavirus disease 2019 (COVID-19) resulted in a global pandemic, which led to deferral of surgeries for early stage breast cancer during March-June 2020. Institutional guidelines were developed to use neoadjuvant endocrine therapy (NET) as a bridge to surgery. As a follow up to initial data presented at SABCS 2020 demonstrating patient acceptance of NET, the present study provides results from a survey which explored psychosocial factors associated with medication compliance. Objective: Primary objective was to identify any barriers to compliance with NET. Method: This was a single institution, prospective study that surveyed patients diagnosed with DCIS and early stage breast cancer at Perlmutter Cancer Center at NYU Langone Hospital and NYU Langone Hospital-Long Island from March 15, 2020-June 1, 2020. Questions were based on the Beliefs about Medicines Questionnaire specific for endocrine therapy (BMQ-AET) and the Medication Adherence Report Scale. Responses were recorded on a Likert scale and included 7 questions regarding perceptions about breast cancer treatment, 10 questions addressing experience with NET, and 5 questions gauging at adherence to NET. Inclusion criteria were males and females older than 18 years old, with an initial diagnosis of DCIS or early stage HR+ Her2/neu-breast cancer, who were prescribed NET. Descriptive statistics were calculated and subgroups were compared using Fisher's exact tests. Analyses were performed using SAS version 9.4. Results: From March 15-June 1, 2020, 13 patients were diagnosed with DCIS and 29 patients with HR+ Her2/neu-breast cancer for whom NET was recommended. Demographics are shown in Table 1. All 42 patients were female with an average age of 60.9 years. Majority of patients were post-menopause (74%) and predominantly white (64%), with an income of less than $60, 000 (52.4%). Average NET duration was 6.7 weeks. Survey responses displayed in Table 2 indicate statistically significant p values in bold. Patients >50 years old, post-menopause and invasive breast cancer had a stronger belief that NET would be helpful, resulting in greater perception to breast cancer treatment and higher adherence to NET. Patients treated with NET for greater than 4 weeks also felt that NET would make them feel well compared to ≤4 weeks. Interestingly, no significant differences in responses based on education or income level were observed. Conclusion: COVID-19 pandemic presented a unique opportunity to use NET, which is often underutilized outside of clinical trials. In this single institution prospective study, we found that post-menopause patients greater than 50 years old with invasive breast cancer perceived hormonal therapy as beneficial to their health, resulting in increased medication compliance. These findings can be used when counseling patients currently treated with NET as well as those patients may be appropriate for NET in the post-COVID era.
ABSTRACT
Background: Neoadjuvant endocrine therapy (NET) has long been limited to patients who were deemed medically unfit for immediate surgery or on clinical trials. Coronavirus disease 2019 (COVID-19) resulted in a global pandemic, which led to deferral of elective surgeries including breast surgeries for early stage breast cancer patients during March-June 2020. Institutional guidelines were developed based on societal recommendations, including NCCN, to use NET as a bridge to surgery. Objective: Primary objective was to establish a database of early stage HR+ Her2/neu-breast cancer patients diagnosed during COVID-19 who were treated with NET as a bridge to surgery. Secondary endpoints include correlation between duration of NET and changes in pathological variables. Method: This was a single institution, retrospective observational study from Perlmutter Cancer Center at NYU Langone Hospital and NYU Langone Hospital-Long Island of DCIS and early stage breast cancer patients diagnosed from March 15, 2020-June 1, 2020 during COVID-19 pandemic. Inclusion criteria were males and females older than 18 years of age and initial diagnosis of DCIS or early stage HR+ Her2/neu-breast cancer who did not require neoadjuvant chemotherapy by established guidelines. Descriptive statistics were calculated separately by DCIS and invasive breast cancer using SAS version 9.4. Results: From March 15-S June 1, 2020, 13 patients who were diagnosed with DCIS and 41 patients with early stage HR+ Her2/neu-invasive breast cancer received NET (Table 1). Of the 41 patients with invasive breast cancer, 19 (46%) had Oncotype DX assay on biopsy specimens;12/19 (63%) had scores 10-14 and 7/19 (37%) had scores 15-25. 38/41 (92.7%) had post-surgery Ki-67% and 16/38 (42.1%) demonstrated maturation arrest (Ki-67 <2.7%). 26/41 (63%) invasive breast cancer patients had pre and post Ki-67% checked while on aromatase inhibitors (AI);21/26 (81%) had a decrease in Ki-67%, 2/26 (7.7%) patients had no change, and 3/26 (11.5%) had an increase. Of those 21 patients, the percent change of Ki-67% from baseline was mean 69.15% ± 22.58 and median 71.83%. No significant associations with changes (pre to post) in Ki-67%, T stage, ER% and PR% in NET for ≤4 weeks and >4 weeks (Table 2). Median duration of NET in invasive breast cancer was 6.85 weeks. 1 patient had a complete pathological response after NET and 2 patients were upstaged from DCIS to invasive carcinoma at the time of surgery. Conclusion: While the sample sizes are small, this is a unique cohort of early stage surgically resectable breast cancer patients who were treated with NET during the COVID-19 pandemic. This real-world data confirms pathological changes, especially decrease in Ki-67% even with short duration use of NET that has been reported in trials of neoadjuvant AI. Long term follow-up for survival outcome is planned.
ABSTRACT
The arrival of COVID-19 has ushered in a new era of distance learning. Since schools and universities have closed, learning has transferred to apps like Google Meet, Microsoft Teams, Zoom, and others. Almost all colleges have changed their curricula to reflect the current reality. Students' practical knowledge deteriorated as a result of the virtual form of learning, and they began attending lectures only for the purpose of attending them. With all of this, their grades and scores should ideally be declining, but the findings came as a shock. It was a fantastic turnaround. Many students outperformed their average score. This is due to the fact that there has never been a way to perform an organized evaluation without using unequal means in the online-mode of education. To address the existing problem, a system that can assist in analysing unfair tactics used by students is required. The employment of proctoring procedures is a big difficulty for the research community when it comes to online examinations. In this paper, we present how to create a complete multi-model system utilising computer vision to prevent the presence of humans throughout the examination. We propose a system that includes a variety of features that students may exploit throughout the test, such as eye gaze tracking, mouth open or close detection, object identification, and head posture estimate using facial landmarks and face detection. Our system can also transform the student's voice into a text format, which might be useful for keeping track of the words said by the student. This might aid the examiner in determining whether or not the student is speaking with someone close. In summary, this research reveals how to prevent cheating in online tests using semi-automated proctoring based on vision and audio capabilities and monitor multiple students at a time. © 2021 IEEE.
ABSTRACT
Background: In high-risk estrogen-receptor positive, HER2 positive, or triple negative breast cancer (BC), chemotherapy can increase cure rates in early-stage disease and prolong survival in setting of advanced disease. Real world data specific to BC is needed to counsel patients (pts) with BC on their risk for SARS-CoV-2 infection and mortality in the context of the SARS-CoV-2 pandemic. Methods: In this retrospective study, we abstracted clinical data including demographics, tumor histology, cancer treatment, and COVID-19 testing results status from the electronic medical record of 3778 BC patients who received cancer care from 02/01/2020 - 05/01/2020 in New York City at our cancer center. The primary endpoint of the study was incidence of SARS-CoV-2 infection by treatment type (cytotoxic chemotherapy (CT) vs non-cytotoxic therapies (endocrine and/or HER2 directed therapy (E/H)) diagnosed by either serology, RT-PCR, or documented clinical diagnosis. Probability of Treatment Weighting (IPTW) and Mann-Whitney Test were used to assess risk of SARS-CoV-2 infection by treatment and assess outcomes based on oncologic and non-oncologic risk factors respectively. Results: 3062 patients met inclusion criteria with 379 pts in CT, 2343 pts in E/H and 340 in NT groups. During study period 641 patients (20.9%) were tested by either PCR or serology with 64 patients (2.1%) diagnosed with COVID-19. All pts who tested positive by PCR and subsequently had serology testing were positive for IgG. The weighted risk of SARS-COV-2 infection was 3.5% in CT vs. 2.7% in E/H (p=0.523). 27 patients (0.9%) expired over follow up, with 10 deaths attributed to SARS-CoV-2 infection. The weighted risk for death was 0.7% with CT vs. 0.1% with E/H, p=0.24 (Table A). Age, BMI,CCI and advanced cancer stage were associated with increased mortality following SARS-CoV-2 infection (Table). Conclusions: CT was not associated with increased risk of infection with SARS-CoV-2 infection or death following infection. BC cancer treatment, including CT, can be safely administered with enhanced infectious precautions and should not be withheld particularly when given for curative intent.
ABSTRACT
The Present Study analyzed research output for a period of 5 years between 2015 to and 2019. Web of Science database a service from Clarivate Analytics has been used to download citation and source data. Histcite application software have been used to present the datasets. Analysis part focuses on the parameters like citation impact at local and global level, influential authors and their total output, ranking of contributing institutions and countries. In addition to this scientographical mapping of data is presented through graphs using VOSviewer software mapping technique. © 2020, Library Philosophy and Practice. All Rights Reserved