RESUMEN
MOTIVATION: Deep graph learning (DGL) has been widely employed in the realm of ligand-based virtual screening. Within this field, a key hurdle is the existence of activity cliffs (ACs), where minor chemical alterations can lead to significant changes in bioactivity. In response, several DGL models have been developed to enhance ligand bioactivity prediction in the presence of ACs. Yet, there remains a largely unexplored opportunity within ACs for optimizing ligand bioactivity, making it an area ripe for further investigation. RESULTS: We present a novel approach to simultaneously predict and optimize ligand bioactivities through DGL and ACs (OLB-AC). OLB-AC possesses the capability to optimize ligand molecules located near ACs, providing a direct reference for optimizing ligand bioactivities with the matching of original ligands. To accomplish this, a novel attentive graph reconstruction neural network and ligand optimization scheme are proposed. Attentive graph reconstruction neural network reconstructs original ligands and optimizes them through adversarial representations derived from their bioactivity prediction process. Experimental results on nine drug targets reveal that out of the 667 molecules generated through OLB-AC optimization on datasets comprising 974 low-activity, noninhibitor, or highly toxic ligands, 49 are recognized as known highly active, inhibitor, or nontoxic ligands beyond the datasets' scope. The 27 out of 49 matched molecular pairs generated by OLB-AC reveal novel transformations not present in their training sets. The adversarial representations employed for ligand optimization originate from the gradients of bioactivity predictions. Therefore, we also assess OLB-AC's prediction accuracy across 33 different bioactivity datasets. Results show that OLB-AC achieves the best Pearson correlation coefficient (r2) on 27/33 datasets, with an average improvement of 7.2%-22.9% against the state-of-the-art bioactivity prediction methods. AVAILABILITY AND IMPLEMENTATION: The code and dataset developed in this work are available at github.com/Yueming-Yin/OLB-AC.
Asunto(s)
Aprendizaje Profundo , Ligandos , Redes Neurales de la Computación , Descubrimiento de Drogas/métodosRESUMEN
Providing family updates is a common clinical task for medical trainees and practitioners working in hospital settings. Good clinical communication skills are essential in clinical care as it is associated with improved patient satisfaction, understanding of condition, treatment adherence, and better overall clinical outcomes. Moreover, poor communications are often the source of medical complaints. However, while patient-centred communication skills training has generally been incorporated into clinical education, there hitherto remains inadequate training on clinical communications with patients' families, which carry different nuances. In recent years, it is increasingly recognized that familial involvement in the care of hospitalized patients leads to better clinical and psychological outcomes. In fact, in Asian populations with more collectivistic cultures, families are generally highly involved in patient care and decision-making. Therefore, effective clinical communications and regular provision of family updates are essential to build therapeutic rapport, facilitate familial involvement in patient care, and also provide a more holistic understanding of the patient's background and psychosocial set-up. In this article, we herein describe a seven-step understand the clinical context, gather perspectives, deliver medical information, address questions, concerns and expectations, provide tentative plans, demonstrate empathy, postcommunication reflections model as a practical guide for medical trainees and practitioners in provision of structured and effective family updates in their clinical practice.
Asunto(s)
Comunicación , Relaciones Profesional-Familia , Humanos , Competencia Clínica , Empatía , Familia/psicología , Relaciones Médico-PacienteRESUMEN
Clinical reasoning is a crucial skill and defining characteristic of the medical profession, which relates to intricate cognitive and decision-making processes that are needed to solve real-world clinical problems. However, much of our current competency-based medical education systems have focused on imparting swathes of content knowledge and skills to our medical trainees, without an adequate emphasis on strengthening the cognitive schema and psychological processes that govern actual decision-making in clinical environments. Nonetheless, flawed clinical reasoning has serious repercussions on patient care, as it is associated with diagnostic errors, inappropriate investigations, and incongruent or suboptimal management plans that can result in significant morbidity and even mortality. In this article, we discuss the psychological constructs of clinical reasoning in the form of cognitive 'thought processing' models and real-world contextual or emotional influences on clinical decision-making. In addition, we propose practical strategies, including pedagogical development of a personal cognitive schema, mitigating strategies to combat cognitive bias and flawed reasoning, and emotional regulation and self-care techniques, which can be adopted in medical training to optimize physicians' clinical reasoning in real-world practice that effectively translates learnt knowledge and skill sets into good decisions and outcomes.
RESUMEN
Identification of differentially expressed proteins in a proteomics workflow typically encompasses five key steps: raw data quantification, expression matrix construction, matrix normalization, missing value imputation (MVI), and differential expression analysis. The plethora of options in each step makes it challenging to identify optimal workflows that maximize the identification of differentially expressed proteins. To identify optimal workflows and their common properties, we conduct an extensive study involving 34,576 combinatoric experiments on 24 gold standard spike-in datasets. Applying frequent pattern mining techniques to top-ranked workflows, we uncover high-performing rules that demonstrate optimality has conserved properties. Via machine learning, we confirm optimal workflows are indeed predictable, with average cross-validation F1 scores and Matthew's correlation coefficients surpassing 0.84. We introduce an ensemble inference to integrate results from individual top-performing workflows for expanding differential proteome coverage and resolve inconsistencies. Ensemble inference provides gains in pAUC (up to 4.61%) and G-mean (up to 11.14%) and facilitates effective aggregation of information across varied quantification approaches such as topN, directLFQ, MaxLFQ intensities, and spectral counts. However, further development and evaluation are needed to establish acceptable frameworks for conducting ensemble inference on multiple proteomics workflows.
Asunto(s)
Proteómica , Proteómica/métodos , Flujo de Trabajo , Aprendizaje Automático , Proteoma/metabolismo , Humanos , Algoritmos , Bases de Datos de ProteínasRESUMEN
INTRODUCTION: Early in the coronavirus disease 2019 (COVID-19) pandemic, a low incidence of cardiovascular complications was reported in Singapore. Little was known about the trend of cardiovascular complications as the pandemic progressed. In this study, we examined the evolving trends in electrocardiographic and cardiovascular manifestations in patients hospitalised with COVID-19. METHODS: We examined the first 1781 consecutive hospitalised patients with polymerase chain reaction-confirmed COVID-19. We divided the population based on whether they had abnormal heart rate (HR) or electrocardiography (ECG) or normal HR and ECG, comparing the baseline characteristics and outcomes. Cardiovascular complications were defined as acute myocardial infarction, stroke, pulmonary embolism, myocarditis and mortality. RESULTS: The 253 (14.2%) patients who had abnormal HR/ECG at presentation were more likely to be symptomatic. Sinus tachycardia was commonly observed. Troponin I levels (97.0 ± 482.9 vs. 19.7 ± 68.4 ng/L, P = 0.047) and C-reactive protein levels (20.1 ± 50.7 vs. 13.9 ± 24.1 µmol/L, P = 0.003) were significantly higher among those with abnormal HR/ECGs, with a higher prevalence of myocarditis (2.0% vs. 0.5%, P = 0.019), pulmonary embolism (2.0% vs. 0.3%, P = 0.008) and acute myocardial infarction (1.2% vs. 0.1%, P = 0.023). After adjusting for age and comorbidities, abnormal HR/ECG (adjusted odds ratio 4.41, 95% confidence interval 2.21-8.77; P < 0.001) remained independently associated with adverse cardiovascular complications. Over time, there was a trend towards a higher proportion of hospitalised patients with cardiovascular complications. CONCLUSION: Cardiovascular complications appear to be increasing in proportion over time among hospitalised patients with COVID-19. A baseline ECG and HR measurement may be helpful for predicting these complications.
RESUMEN
BACKGROUND: The use of artificial intelligence (AI) can revolutionize health care, but this raises risk concerns. It is therefore crucial to understand how clinicians trust and accept AI technology. Gastroenterology, by its nature of being an image-based and intervention-heavy specialty, is an area where AI-assisted diagnosis and management can be applied extensively. OBJECTIVE: This study aimed to study how gastroenterologists or gastrointestinal surgeons accept and trust the use of AI in computer-aided detection (CADe), computer-aided characterization (CADx), and computer-aided intervention (CADi) of colorectal polyps in colonoscopy. METHODS: We conducted a web-based questionnaire from November 2022 to January 2023, involving 5 countries or areas in the Asia-Pacific region. The questionnaire included variables such as background and demography of users; intention to use AI, perceived risk; acceptance; and trust in AI-assisted detection, characterization, and intervention. We presented participants with 3 AI scenarios related to colonoscopy and the management of colorectal polyps. These scenarios reflect existing AI applications in colonoscopy, namely the detection of polyps (CADe), characterization of polyps (CADx), and AI-assisted polypectomy (CADi). RESULTS: In total, 165 gastroenterologists and gastrointestinal surgeons responded to a web-based survey using the structured questionnaire designed by experts in medical communications. Participants had a mean age of 44 (SD 9.65) years, were mostly male (n=116, 70.3%), and mostly worked in publicly funded hospitals (n=110, 66.67%). Participants reported relatively high exposure to AI, with 111 (67.27%) reporting having used AI for clinical diagnosis or treatment of digestive diseases. Gastroenterologists are highly interested to use AI in diagnosis but show different levels of reservations in risk prediction and acceptance of AI. Most participants (n=112, 72.72%) also expressed interest to use AI in their future practice. CADe was accepted by 83.03% (n=137) of respondents, CADx was accepted by 78.79% (n=130), and CADi was accepted by 72.12% (n=119). CADe and CADx were trusted by 85.45% (n=141) of respondents and CADi was trusted by 72.12% (n=119). There were no application-specific differences in risk perceptions, but more experienced clinicians gave lesser risk ratings. CONCLUSIONS: Gastroenterologists reported overall high acceptance and trust levels of using AI-assisted colonoscopy in the management of colorectal polyps. However, this level of trust depends on the application scenario. Moreover, the relationship among risk perception, acceptance, and trust in using AI in gastroenterology practice is not straightforward.