Categories
Nevin Manimala Statistics

A Multilabel Text Classifier of Cancer Literature at the Publication Level: Methods Study of Medical Text Classification

JMIR Med Inform. 2023 Oct 5;11:e44892. doi: 10.2196/44892.

ABSTRACT

BACKGROUND: Given the threat posed by cancer to human health, there is a rapid growth in the volume of data in the cancer field and interdisciplinary and collaborative research is becoming increasingly important for fine-grained classification. The low-resolution classifier of reported studies at the journal level fails to satisfy advanced searching demands, and a single label does not adequately characterize the literature originated from interdisciplinary research results. There is thus a need to establish a multilabel classifier with higher resolution to support literature retrieval for cancer research and reduce the burden of screening papers for clinical relevance.

OBJECTIVE: The primary objective of this research was to address the low-resolution issue of cancer literature classification due to the ambiguity of the existing journal-level classifier in order to support gaining high-relevance evidence for clinical consideration and all-sided results for literature retrieval.

METHODS: We trained a multilabel classifier with scalability for classifying the literature on cancer research directly at the publication level to assign proper content-derived labels based on the “Bidirectional Encoder Representation from Transformers (BERT) + X” model and obtain the best option for X. First, a corpus of 70,599 cancer publications retrieved from the Dimensions database was divided into a training and a testing set in a ratio of 7:3. Second, using the classification terminology of International Cancer Research Partnership cancer types, we compared the performance of classifiers developed using BERT and 5 classical deep learning models, such as the text recurrent neural network (TextRNN) and FastText, followed by metrics analysis.

RESULTS: After comparing various combined deep learning models, we obtained a classifier based on the optimal combination “BERT + TextRNN,” with a precision of 93.09%, a recall of 87.75%, and an F1-score of 90.34%. Moreover, we quantified the distinctive characteristics in the text structure and multilabel distribution in order to generalize the model to other fields with similar characteristics.

CONCLUSIONS: The “BERT + TextRNN” model was trained for high-resolution classification of cancer literature at the publication level to support accurate retrieval and academic statistics. The model automatically assigns 1 or more labels to each cancer paper, as required. Quantitative comparison verified that the “BERT + TextRNN” model is the best fit for multilabel classification of cancer literature compared to other models. More data from diverse fields will be collected to testify the scalability and extensibility of the proposed model in the future.

PMID:37796584 | DOI:10.2196/44892

Categories
Nevin Manimala Statistics

Visual statistical learning of naturalistic textures

J Exp Psychol Hum Percept Perform. 2023 Oct 5. doi: 10.1037/xhp0001152. Online ahead of print.

ABSTRACT

The visual system continuously adapts to the statistical properties of the environment. In this study, we demonstrated that training significantly enhanced subjects’ perceptual sensitivity to co-occurrence statistics in naturalistic textures. The learning effect was specific to the statistical component and spatial location. By examining the time course of learning, we found that learning was accelerated at an untrained location. Our findings establish a link between statistical learning and visual perception, indicating multistage plasticity beyond V1 in the visual hierarchy. (PsycInfo Database Record (c) 2023 APA, all rights reserved).

PMID:37796580 | DOI:10.1037/xhp0001152

Categories
Nevin Manimala Statistics

Older Persons’ and Health Care Professionals’ Design Choices When Co-Designing a Medication Plan Aiming to Promote Patient Safety: Case Study

JMIR Aging. 2023 Oct 5;6:e49154. doi: 10.2196/49154.

ABSTRACT

BACKGROUND: Harm from medications is a major patient safety challenge among older persons. Adverse drug events tend to arise when prescribing or evaluating medications; therefore, interventions targeting these may promote patient safety. Guidelines highlight the value of a joint plan for continued treatment. If such a plan includes medications, a medication plan promoting patient safety is advised. There is growing evidence for the benefits of including patients and health care professionals in initiatives for improving health care products and services through co-design.

OBJECTIVE: This study aimed to identify participants’ needs and requirements for a medication plan and explore their reasoning for different design choices.

METHODS: Using a case study design, we collected and analyzed qualitative and quantitative data and compared them side by side. We explored the needs and requirements for a medication plan expressed by 14 participants (older persons, nurses, and physicians) during a co-design initiative in a regional health system in Sweden. We performed a directed content analysis of qualitative data gathered from co-design sessions and interviews. Descriptive statistics were used to analyze the quantitative data from survey answers.

RESULTS: A medication plan must provide an added everyday value related to safety, effort, and engagement. The physicians addressed challenges in setting aside time to apply a medication plan, whereas the older persons raised the potential for increased patient involvement. According to the participants, a medication plan needs to support communication, continuity, and interaction. The nurses specifically addressed the need for a plan that was easy to gain an overview of. Important function requirements included providing instant access, automation, and attention. Content requirements included providing detailed information about the medication treatment. Having the plan linked to the medication list and instantly obtainable information was also requested.

CONCLUSIONS: After discussing the needs and requirements for a medication plan, the participants agreed on an iteratively developed medication plan prototype linked to the medication list within the existing electronic health record. According to the participants, the medication plan prototype may promote patient safety and enable patient engagement, but concerns were raised about its use in daily clinical practice. The last step in the co-design framework is testing the intervention to explore how it works and connects with users. Therefore, testing the medication plan prototype in clinical practice would be a future step.

PMID:37796569 | DOI:10.2196/49154

Categories
Nevin Manimala Statistics

Team-Based Surgical Approach to Head and Neck Microvascular Free Flap Reconstruction

JAMA Otolaryngol Head Neck Surg. 2023 Oct 5. doi: 10.1001/jamaoto.2023.3028. Online ahead of print.

ABSTRACT

IMPORTANCE: Because microvascular free flap reconstruction is increasingly used to restore function in patients with head and neck cancer, there is a growing need for evidence-based perioperative care.

OBJECTIVE: To assess the association of different team-based surgical approaches with intraoperative and postoperative outcomes for patients undergoing head and neck free flap reconstruction.

DESIGN, SETTING, AND PARTICIPANTS: This retrospective cohort study of 733 patients was conducted at an academic tertiary care medical center. Head and neck oncologic procedures involving microvascular free flap reconstruction with available intraoperative data collected from January 1, 2000, to December 31, 2021, were included.

MAIN OUTCOMES AND MEASURES: Patient characteristics including demographic characteristics and comorbid conditions, operative variables, length of stay, and postoperative outcomes were measured. Descriptive statistics and effect size measures were performed to compare the 3 intraoperative surgical team approaches, specifically single surgeon, separate 2-team approach, and integrated 2-team approach; 1:1 nearest neighbor matching without caliper was performed to compare single- vs 2-team and separate and integrated 2-team approaches. Effect size measures including Cramer V for dichotomous variables, the Kendall W coefficient of concordance for ordinal variables, and η2 for continuous variables were reported with 95% CIs to describe precision.

RESULTS: Among 733 cases, there were no clinically significant differences in patient demographic characteristics, clinicopathologic characteristics, and choice of free flap reconstruction based on intraoperative surgical team approach. The mean (SD) age was 58.7 (12.4) years, and 514 were male (70.1%). In terms of operative and postoperative variables, there was a difference in operative times and intraoperative fluid requirements among the 3 different techniques, with the integrated 2-team approach demonstrating a mean reduction in operative time of approximately 2 hours (η2 = 0.871; 95% CI, 0.852-0.887; mean [SD] operative time = 541 [191] minutes for the single-surgeon approach, 399 [175] minutes for the integrated 2-team approach, and 537 [200] minutes for the separate 2-team approach) and lower fluid requirements of greater than 1 L (η2 = 0.790; 95% CI, 0.762-0.817). In both unadjusted analyses and propensity score matching, there were no clinically significant differences in terms of ischemia time, use of pressors, postoperative complications (including free flap failure, number of return trips to the operating room, length of stay, or 30-day readmission) based on intraoperative team approach.

CONCLUSIONS AND RELEVANCE: Findings suggest that the integrated 2-team surgical approach for complex head and neck microvascular reconstruction can be used to safely decrease operative time, with no difference in postoperative outcomes.

PMID:37796525 | DOI:10.1001/jamaoto.2023.3028

Categories
Nevin Manimala Statistics

Limited English Proficiency Is Associated With Diabetic Retinopathy in Patients Presenting for Cataract Surgery

Transl Vis Sci Technol. 2023 Oct 3;12(10):4. doi: 10.1167/tvst.12.10.4.

ABSTRACT

PURPOSE: To investigate the relationship between limited English proficiency (LEP) and diabetic retinopathy (DR) in patients presenting for cataract surgery.

METHODS: This is a retrospective observational study of patients who underwent cataract surgery between January 2014 and February 2020. Patients who self-identified as needing or preferring an interpreter were defined as having LEP. Differences in demographics, characteristics, and outcomes including history of type 2 diabetes (T2DM), DR, preoperative best corrected visual acuity (BCVA), macular edema, and anti-vascular endothelial growth factor injections were analyzed. Statistical comparisons were assessed using logistic regression with generalized estimating equations.

RESULTS: We included 13,590 eyes. Of these, 868 (6.4%) were from LEP patients. Patients with LEP were more likely to be Hispanic (P < 0.001), female sex (P = 0.008), or older age (P = 0.003) and have worse mean BCVA at presentation (P < 0.001). Patients with LEP had a significantly higher rate of T2DM (P < 0.001), macular edema (P = 0.033), and DR (18.1% vs. 5.8%, P < 0.001). Findings remained significant when controlling for age, sex, race/ethnicity, and type of health insurance. Patients with LEP and DR were more likely to have had later stages of DR (P = 0.023).

CONCLUSIONS: Patients with LEP presenting for cataract surgery had a higher rate of DR and associated complications compared to patients with English proficiency. Further studies are needed to understand how language disparities influence health and what measures could be taken to improve healthcare in this vulnerable population.

TRANSLATIONAL RELEVANCE: Our study highlights healthcare disparities within ophthalmology and emphasizes the importance of advocating for improved healthcare delivery for patients with LEP.

PMID:37796496 | DOI:10.1167/tvst.12.10.4

Categories
Nevin Manimala Statistics

On Enhancing Clinical Trial Data Sharing

JAMA Oncol. 2023 Oct 5. doi: 10.1001/jamaoncol.2023.3859. Online ahead of print.

NO ABSTRACT

PMID:37796491 | DOI:10.1001/jamaoncol.2023.3859

Categories
Nevin Manimala Statistics

Cardiovascular Risk in Prostate Cancer Patients Using Luteinizing Hormone-Releasing Hormone Agonists or a Gonadotropin-Releasing Hormone Antagonist

J Urol. 2023 Oct 5:101097JU0000000000003721. doi: 10.1097/JU.0000000000003721. Online ahead of print.

ABSTRACT

PURPOSE: LHRH agonists are believed to have higher cardiovascular risk relative to GnRH antagonists. However, previous studies have not consistently demonstrated this. We used real-world clinical practice data to evaluate differences in MACE risk between LHRH agonists compared to a GnRH antagonist following androgen deprivation therapy (ADT) initiation.

MATERIALS AND METHODS: We performed a retrospective analysis of data in the Decision Resources Group (now Clarivate) Real World Evidence repository, which represents >300 million US patients from 1991-2020 across all US regions. Patients with prostate cancer (PCa) who received at least 1 injection of ADT were included. The risks of MACE and all-cause mortality as independent endpoints were evaluated, Kaplan-Meier curves were constructed, and associations between MACE and all available confounding risk factors were evaluated by Cox regression analysis using Statistical Package for the Social Sciences (SPSS).

RESULTS: A total of 45,059 men with PCa treated with ADT were analyzed. Overall, the risks of MACE and all-cause mortality were slightly lower in the first year after ADT initiation compared to subsequent years. MACE risk was higher for the GnRH antagonist compared to LHRH agonists (HR = 1.62; 95% CI 1.21-2.18, P = .001). The risk of all-cause mortality was also higher for the GnRH antagonist vs LHRH agonists (HR = 1.87; 95% CI 1.39-2.52, P < .001).

CONCLUSIONS: The adjusted incidence of MACE was higher for men treated with the GnRH antagonist compared to the LHRH agonists. The demographic and risk factors with the greatest impact on MACE risk were higher age, baseline metastasis, oncology (vs urology) setting, personal MACE history, antagonist (vs agonist), tobacco history, White (vs Black) race, and lower BMI.

PMID:37796473 | DOI:10.1097/JU.0000000000003721

Categories
Nevin Manimala Statistics

Drug utilization and medical expenses in psoriasis treatment at a dermatology hospital in Vietnam, 2019-2021

Ann Ig. 2023 Nov-Dec;35(6):670-682. doi: 10.7416/ai.2023.2572.

ABSTRACT

INTRODUCTION: Psoriasis is a persistent, chronic, inflammatory cutaneous disorder that recurs frequently and has negative impacts on the living quality of sufferers.

METHODS: Data from the Inpatient and Outpatient Department medical records at Can Tho dermatology hospital were used to generate a descriptive statistics report on medicines and medical costs for psoriasis therapy in 2019-2021.

RESULTS: The average number of prescription medications varied annually, averaging roughly 0.62±85.4% per prescription. Corticosteroids and calcipotriol were the most commonly recommended drugs for psoriasis. Antihistamines were the most often used medication, with over 12,000 instances among the 28,397 individuals studied. The peak in average per-treatment expenses occurred in 2021 when they fluctuated between US $120 and US $160. In contrast, examination expenses were the most costly, ranging from US $93-$107.

CONCLUSION: The bulk of psoriasis therapy treatments were topical agents, whose quantities rose progressively. Direct examination expenses accounted for the greatest proportion.

PMID:37796471 | DOI:10.7416/ai.2023.2572

Categories
Nevin Manimala Statistics

A comparison of COVID-19 incidence rates across six European countries in 2021

Euro Surveill. 2023 Oct;28(40). doi: 10.2807/1560-7917.ES.2023.28.40.2300088.

ABSTRACT

International comparisons of COVID-19 incidence rates have helped gain insights into the characteristics of the disease, benchmark disease impact, shape public health measures and inform potential travel restrictions and border control measures. However, these comparisons may be biased by differences in COVID-19 surveillance systems and approaches to reporting in each country. To better understand these differences and their impact on incidence comparisons, we collected data on surveillance systems from six European countries: Belgium, England, France, Italy, Romania and Sweden. Data collected included: target testing populations, access to testing, case definitions, data entry and management and statistical approaches to incidence calculation. Average testing, incidence and contextual data were also collected. Data represented the surveillance systems as they were in mid-May 2021. Overall, important differences between surveillance systems were detected. Results showed wide variations in testing rates, access to free testing and the types of tests recorded in national databases, which may substantially limit incidence comparability. By systematically including testing information when comparing incidence rates, these comparisons may be greatly improved. New indicators incorporating testing or existing indicators such as death or hospitalisation will be important to improving international comparisons.

PMID:37796443 | DOI:10.2807/1560-7917.ES.2023.28.40.2300088

Categories
Nevin Manimala Statistics

Race and Intention to Breastfeed are the Strongest Predictors of Exclusive Breastfeeding: a Retrospective Study

J Racial Ethn Health Disparities. 2023 Oct 5. doi: 10.1007/s40615-023-01819-8. Online ahead of print.

ABSTRACT

INTRODUCTION: Racial disparities exist in maternal and neonatal care including breastfeeding (BF). The purpose of this study is to assess factors associated with BF success by race with a specific focus on pre-birth BF plan and time duration from birth until initiation of skin-to-skin contact and from birth to the first feed or breastfeed.

METHODS: A database query of our electronic medical records was performed for all patients who had a vaginal delivery that met our study criteria. Demographic information, pre-delivery feeding plan (exclusive BF, exclusive formula, or mixed), time to first feed and first breastfeed, and time to skin-to-skin were compared among different postpartum feeding practices (exclusive BF, exclusive formula, mixed), and compared across race/ethnic groups using ANOVA, Chi-square, and Fisher’s exact statistical tests as appropriate. Logistic regression was used to investigate the independent effect of each variable on exclusive BF.

RESULTS: The study analyzed 12,578 deliveries. There was a significant difference in intended feeding plans among the different racial groups. Approximately 61% of Black patients intended to exclusively BF as compared to 79% of the other groups. Overall, 3994 (32%) patients breastfed exclusively, 872 (7%) exclusively used formula, and 7712 (61%) used a mix of breast and formula. White patients were most likely to exclusively BF (35%) and Black patients were least likely (21%), p < 0.001. Our model found that self-identified race and pre-delivery feeding plan were the strongest predictors of exclusive BF.

CONCLUSIONS: The main findings of this study are that self-identified race and intention to BF are the strongest predictors of exclusive BF. Black patients intend to BF at a significantly lower rate than other racial groups, for reasons not determined by this study, and this affects feeding practice. Our findings are notable because prehospital intention to BF can be modified by outreach, education, and changes to in-hospital practices.

PMID:37796430 | DOI:10.1007/s40615-023-01819-8