Real Patient Research Articles

Exploring patient perspective: using narrative DIPEx interviews and the ICF model for interprofessional learning.

The International Classification of Functioning, Disability, and Health (ICF) has been widely adopted in academic health profession education and is part of bachelor curricula since its introduction by the WHO in 2001. In this context, interprofessional exchange among health professionals from a biopsychosocial perspective has become increasingly important and is now a key part of bachelor's program curricula to learn with, about, and from each other regarding students' curiosity about interprofessional collaboration (IPC). This pilot study describes initial teaching experiences within an interprofessional elective module for health professions focused on patient-centeredness. It uses the ICF model to exemplify interprofessional exchange based on real patient experiences from the "DIPEx" database, which stands for "Database of Individual Patients' Experiences." Bachelor students from four healthcare professions learned in small interprofessional groups and selected case-related content from excerpts of real patient narratives from qualitative interviews in the DIPEx database. In a peer-to-peer process, students structured, analyzed, and reflected on selected patient experiences and presented their findings using the ICF model. Develop a shared understanding of the case from a biopsychosocial perspective using the ICF model to communicate and reflect on patient-centeredness in interprofessional groups for a common care strategy rooted in patient-centeredness. This study illustrates how the shared analysis of a patient's experience of illness can lead to different perspectives on professional concepts for practice. The ICF model serves as a guiding structure and analysis tool. The core of the IPC, patient-centeredness, becomes the focus of the collaborative actions of the health professions.

“Women's Lives Are on the Line, and Our Hands Are Tied”: How Television Is Reckoning With a Post-Dobbs America

BackgroundSince the 2022 Dobbs v. Jackson Women’s Health Organization Supreme Court decision revoked federal protection for abortion rights, many states have restricted abortion. Although news media covers this shifting landscape through reporting, this article documents how entertainment content is responding to this new reality in its storytelling. MethodsThe sample is from a public database of abortion plotlines on American television (abortiononscreen.org). I separated the sample of 150 plotlines into two groups: plotlines that filmed and/or aired pre-Dobbs (January 2020–August 2022) and those that aired post-Dobbs (September 2022–December 2023). Coding occurred in Microsoft Excel. ResultsPost-Dobbs, there was an increase in procedural abortion depictions compared with pre-Dobbs, but no change in the consistently low number of depictions of medication abortion. The post-Dobbs sample included a 10% increase in teen characters compared with pre-Dobbs. Pre-Dobbs, the vast majority of plotlines (77%) did not portray any barriers to abortion care. Post-Dobbs, 33% depicted barriers. The most common reason for abortion seeking in both samples was age (11%). Pre-Dobbs, the next most common was a mis-timed pregnancy (10%). Post-Dobbs, the next most common was health concerns (11%). ConclusionsSince Dobbs, more television plotlines are portraying obstacles to abortion care, yet they continue to tell stories of white, non-parenting teenagers who make up a small percentage of real abortion patients. Plotlines overrepresent procedural abortion over the more common medication abortion. Depictions of health-related reasons for abortion seeking obscure more commonly provided reasons for abortions, such as mistimed pregnancies, caregiving responsibilities, and financial concerns. Considering the low levels of abortion knowledge nationwide, understanding what (mis)information audiences encounter onscreen is increasingly important.

Development and validation of a novel tool for identification and categorization of non-technical errors associated with surgical mortality.

Up to half of all surgical adverse events are due to non-technical errors, making non-technical skill assessment and improvement a priority. No specific tools are available to retrospectively identify non-technical errors that have occurred in surgical patient care. This original study aimed to develop and provide evidence of validity and inter-rater reliability for the System for Identification and Categorization of Non-technical Error in Surgical Settings (SICNESS). A literature review, modified Delphi process, and two pilot phases were used to develop and test the SICNESS tool. For each pilot, 12 months of surgical mortality data from the Australian and New Zealand Audit of Surgical Mortality were assessed by two independent reviewers using the SICNESS tool. Main outcomes included tool validation through modified Delphi consensus, and inter-rater reliability for: non-technical error identification and non-technical error categorization using Cohen's κ coefficient, and overall agreement using Fleiss' κ coefficient. Version 1 of the SICNESS was used for pilot 1, including 412 mortality cases, and identified and categorized non-technical errors with strong-moderate inter-rater reliability. Non-technical error exemplars were created and validated through Delphi consensus, and a novel mental model was developed. Pilot 2 included an additional 432 mortality cases. Inter-rater reliability was near perfect for leadership (κ 0.92, 95% c.i. 0.82 to 1.00); strong for non-technical error identification (κ 0.89, 0.84 to 0.93), communication and teamwork (κ 0.89, 0.79 to 0.99), and decision-making (κ 0.85, 0.79 to 0.92); and moderate for situational awareness (κ 0.79, 0.71 to 0.87) and overall agreement (κ 0.69, 0.66 to 0.73). The SICNESS is a reliable and valid tool, enabling retrospective identification and categorization of non-technical errors associated with death, occurring in real surgical patient interactions.

S1815 Causes of Death, Mortality Rates, and the Role of Socio-Demographic Risk Factors and Biomarkers in Metabolic Dysfunction-Associated Steatohepatitis Mortality in More Than 18,000 Real World Patients From the United States

S1815 Causes of Death, Mortality Rates, and the Role of Socio-Demographic Risk Factors and Biomarkers in Metabolic Dysfunction-Associated Steatohepatitis Mortality in More Than 18,000 Real World Patients From the United States

PharmiTech: Addressing Polypharmacy Challenges through AI-Driven Solutions

Due to the rising prevalence of polypharmacy, pharmacists face more challenges in ensuring patient safety and optimizing medication management. This paper introduces PharmiTech, a Clinical Decision Support System that leverages Artificial Intelligence (AI) to tackle the growing need for efficient tools to assist pharmacists. The primary focus of the tool is to identify possible herb-drug interactions and instances of prescription drug abuse, combining an expert knowledge base with a supervised classification model and providing user-friendly alerts to pharmacists. To demonstrate the capabilities of the developed tool, this paper presents its functionalities through a case study involving simulated scenarios using de-identified information to maintain the confidentiality of real patients’ personal data. Tested in Portuguese pharmacies, PharmiTech enhances pharmaceutical care, safeguards patient data, and aids pharmacists in informed decision-making, making it a valuable resource for healthcare professionals.

Real world feasibility of patient-based real time quality control (PBRTQC) using five analytes in a South African laboratory

BackgroundPatient-based real-time quality control (PBRTQC) identifies possible bias in methods by utilising shifts in trend of statistical measures in laboratory results. In this study we aimed to compare and optimize various PBRTQC procedures for serum alanine aminotransferase, albumin, calcium, ferritin and sodium. MethodsIn a bias simulation study, we added artificial bias to intervals of patient data and then evaluated the efficiency with which various PBRTQC procedures were able to detect this bias. PBRTQC procedures used included block size, moving statistic calculation, control limits as well as truncation limits. The number of patients till error detection, the false alarm rate as well as validation charts were utilised to select the optimal PBRTQC procedure for each analyte. ResultsThe optimal PBRTQC procedures identified for each analyte were: ALT − MA T0 50 MaxMin; Albumin − MA T5 100 Perc; Calcium − MM T5 50 Perc; Ferritin − MA T0 100 MaxMin; and Sodium − MA T5 75 MaxMin. (T, Truncation limits; Control limits- MA, Moving Average, MM, Moving median; Perc, percentile) ConclusionsThe use of large, real patient datasets allows for the reliable determination of laboratory-specific PBRTQC procedures. This study demonstrates that the moving average calculation excels in both normal and transformed analyte distributions. Whilst, the benefits of PBRTQC procedures are proven, the complex and time-consuming optimisation process may be a barrier to the rapid implementation in under-resourced countries.

MALEXNET-EUNET: MULTI-CLASS LIVER CANCER CLASSIFICATION AND SEGMENTATION USING A HYBRID DEEP LEARNING SYSTEM

Background and objective: One of the most prevalent and significant causes of cancer-related mortality worldwide is considered to be liver cancer. Techniques for automatically segmenting and classifying liver tumors are crucial for supporting medical professionals during the tumor diagnostic process. Classifying liver tumors is challenging due to noise, nonhomogeneity, and the significant appearance diversity observed in tumor tissue. Also, in recent years, most of the research has performed binary classification, but there is still a lack of research on multi-class liver cancer classification. Therefore, we perform a multi-class liver cancer classification and segmentation in this research. Methods: We propose a hybrid deep learning-based multi-class liver cancer classification and segmentation system in this research. The collected CT images are pre-processed in four stages: contrast enhancement, noise filtering, smoothing and sharpening, and liver region segmentation. Next, the binary, texture, histogram, and rotational, scalability, and translational (RST) features are extracted from the pre-processed images. Then, the average correlation (AC) and probability of error (POE) approaches are applied to selecting relevant features and excluding less significant features. After feature selection, a modified AlexNet (MAlexNet) model is used to classify the multi-class classification of liver tumors. Finally, the identified liver tumor regions are segmented using the enhanced U-Net (EUNet) model. Results: Identified liver tumors are accurately classified into three different categories using the proposed classification model: hemangioma (HEM), hepatocellular carcinoma (HCC), and metastatic carcinoma (MET), with an average accuracy of 99.19%. We have collected the multi-class liver cancer CT images from real time patients. The results of the experiments show that proposed hybrid system provides adequate overall accuracy, is less noise-sensitive, and outperforms other state-of-the-art techniques such as SVM, Faster RCNN, Mask RCNN, and SAR-U-Net on a wide range of CT images. Conclusion: Radiologists and doctors can identify liver tumors more accurately using the suggested innovative framework.

Comparative Evaluation of Neural Network Models for Optimizing ECG Signal in Non-Uniform Sampling Domain

Electrocardiographic signals (ECG) are ubiquitous, which justifies the research of their optimal storage and transmission. However, proposals for non-uniform signal sampling must take into account the priority of diagnostic data accuracy and record integrity, as well as robustness to noise and interference. In this study, two novel methods are introduced, each utilizing a distinct neural network architecture for optimizing non-uniform sampling of ECG signal. A transformer model refines each time point selection through an iterative process using gradient descent optimization, with the goal of minimizing the mean squared error between the original and resampled signals. It adaptively modifies time points, which improves the alignment between both signals. In contrast, the Temporal Convolutional Network model trains on the original signal, and gradient descent optimization is utilized to improve the selection of time points. Evaluation of both strategies’ efficacy is performed by calculating signal distances at lower and higher sampling rates. First, a collection of synthetic data points that resembled the P-QRS-T wave was used to train the model. Then, the ECG-ID database for real data analysis was used. Filtering to remove baseline wander followed by evaluation and testing were carried out in the real patient data. The results, in particular MSE = 0.0005, RMSE = 0.0216, and Pearson’s CC = 0.9904 for 120 sps in the case of the transformer patient data model, provide viable paths for maintaining the precision and dependability of ECG-based diagnostic systems at much lower sampling rate. Outcomes indicate that both techniques are effective at improving the fidelity between the original and modified ECG signals.

Numerical Study of the Effect of the Port Angle of the Superior Vena Cava Supplying Cannula on Hemodynamics in the Right Atrium in VV-ECMO.

Objective: To elucidate the pattern of the influence of the port angle of the superior vena cava supplying cannula (SVCS) on hemodynamics within the right atrium in VV-ECMO. Methods: A three-dimensional model of the right atrium was established based on CT images of a real patient. The 3D models of the SVCS and inferior vena cava draining cannula (IVCD) were established based on the Edwards 18Fr and Medos 22Fr real intubation models, respectively. Based on these models, three-dimensional models of the SVCS ports with bending angles of -90°, -60°, -30°, 0°, 30°, 60°, and 90° in the plane formed by the centerline of the SVCS and the center point of the tricuspid valve (TV) were established. Transient-state computational fluid dynamics (CFD) was performed to clarify the right atrium blood flow pattern and hemodynamic states at different SVCS port orientation angles. The velocity clouds, wall pressure, wall shear stress (WSS), relative residence time (RRT), and recirculation fraction (RF) were calculated to assess hemodynamic changes in the right atrium at different angles of the port of the SVCS. Results: As the angle of the port of the superior chamber cannula changed, the location of the high-velocity blood impingement from the SVCS changed, and the pattern of blood flow within the right atrium was dramatically altered. The results for the maximum right atrial wall pressure were 13,472 pa, 13,424 pa, 10,915 pa, 7680.2 pa, 5890.3 pa, 5597.6 pa, and 7883.5 pa (-90° vs. -60° vs. -30° vs. 0° vs. 30° vs. 60° vs. 90°), and the results for the mean right atrial wall pressure were 6788.9 pa, 8615.1 pa, 8684.9 pa, 6717.2 pa, 5429.2 pa, 5455.6 pa, and 7117.8 pa ( -90° vs. -60° vs. -30° vs. 0° vs. 30° vs. 60° vs. 90°). The results of the maximum right atrial wall WSS in the seven cases were 63.572 pa, 55.839 pa, 31.705 pa, 39.531 pa, 40.11 pa, 28.474 pa, and 35.424 (-90° vs. -60° vs. -30° vs. 0° vs. 30° vs. 60° vs. 90°), respectively, and the results of the mean right atrial wall WSS results were 3.8589 pa, 3.6706 pa, 3.3013 pa, 3.2487 pa, 2.3995 pa, 1.3304 pa, and 2.0747 pa (-90° vs. -60° vs. -30° vs. 0° vs. 30° vs. 60° vs. 90°), respectively. The results for the area percentage of high RRT in the seven cases were 3.44%, 2.23%, 4.24%, 1.83%, 3.69%, 7.73%, and 3.68% (-90° vs. -60° vs. -30° vs. 0° vs. 30° vs. 60° vs. 90°), and the results for the RF were 21.57%, 23.24%, 19.78%, 12.57%, 10.24%, 5.07%, and 8.05% (-90° vs. -60° vs. -30° vs. 0° vs. 30° vs. 60° vs. 90°). Conclusions: The more the port of the SVCS is oriented toward the TV, the more favorable it is for reducing RF and the impingement of blood flow in the right atrial wall, but there may be an increased risk of RRT. The opposite orientation of the SVCS port to the TV is not conducive to reducing flow impingement on the right atrial wall and RF.

A computational probabilistic procedure to quantify the time of breast cancer recurrence after chemotherapy administration

We propose a random linear differential equation with jumps to model the dynamics of breast tumor growth using real patients’ data. The model considers the effect of chemotherapy administration and tumor resection. Also, the inherent randomness of the data and the model are taken into account.The model is probabilistically solved by combining two main methods belonging to Uncertainty Quantification: the principle of maximum entropy (PME) and the random variable transformation technique (RVT). The PME is applied to assign proper probability distributions to model parameters. The RVT technique is used to determine the probability density function (PDF) of the solution of the random differential equation, which is a stochastic process.We apply computational optimization techniques to determine the PDF of model parameters so that the PDF of the solution matches the ones assigned to real patients’ data.Once random tumor dynamics has been modeled, we simulate, after surgery, different adjuvant chemotherapy strategies with the aim of delaying tumor recurrence as long as possible. Results are in concordance with medical literature, and tumor relapse is delayed as more cycles of chemotherapy are administered.Although the proposed model has a common general structure, it is shown how it can be customized to patients in order to construct projections about the tumor’s growth. To better illustrate the applicability of the proposed approach, we carefully show how our model can be tailored to two real patients treated at the Hospital Clínico de Valencia (Spain). The obtained results have been overseen by doctors from this hospital.

Implementing Telemedicine into Clinical Training Through Pre-recorded Video Consultations

Although the contribution of real patient encounters to medical education is well known, challenges such as a lack of suitable cases, patients not consenting to student involvement, physical space limitations that prevent every student from participating, the inability to replicate the same patient encounter, and reduced patient admissions to healthcare facilities during extraordinary periods are common obstacles that need to be addressed in clinical education. To overcome these challenges, video consultation (VC) recordings, which were made with the consent of patients having a telemedicine consultation, were collected as an archive of medical interview recordings covering a wide spectrum of pulmonary diseases. These recordings were watched by students in a classroom setting during clinical clerkships, with case discussions interspersed. This article, which also discusses the results of clinical clerkship evaluations, indicates that the use of pre-recorded VC sessions can be an effective tool for teaching good clinical practices through the ideal method of medical interviews, diagnostic approaches, evaluation of test results, communication skills with patients and their relatives, and addressing the socio-psychological aspects and social impacts of diseases. As an innovative attempt, sharing this process at an early stage of development may inspire enthusiasm for implementing this approach and open the field for further development.

Abstract A070: Real world treatment patterns and patient outcomes of neuroendocrine tumors: A single institution study

Abstract Neuroendocrine tumors (NETs) are rare and diverse, with increasing incidence but poorly understood prognostic variables. While African American or Black patients typically have poorer outcomes across various tumor types, this is not well documented for NETs. Our study aimed to investigate racial disparities in NET outcomes. Patients who had a diagnosis of neuroendocrine tumor between 2014 and 2022 were identified and analyzed in this retrospective chart analysis, with race determined as Caucasian (CA) or Black African American (BAA). Histology was stratified as high grade or those without high grade histology. Grade of tumor was identified as well differentiated, moderately or poorly differentiated, and other/unknown. Log-rank test was conducted to compare the survival curves between CA and AA groups. Cox proportional hazards model was built to adjust for potential confounders, including age at diagnosis and gender (if applicable) while comparing racial disparities. The CA vs. AA hazard ratio (HR) and p-values were calculated. Among the 655 patients analyzed, 63.4% were Caucasian (CA) and 36.6% were Black African American (BAA). The average age at diagnosis across the cohort was 61.5 years. The gender distribution was approximately equal, with 50.2% females and 49.8 % males. High-grade histology was identified in 114 patients, of whom 28.1% were BAA and 71.9% were CA. Within this subgroup, males were more prevalent than females (61.4% vs. 38.6%). Overall survival (OS) for CA patients with high-grade histology was 57.4 months, compared to 67.5 months for BAA patients (p=0.7). Additionally, no statistically significant difference in OS was observed between males and females with high-grade histology (60.8 months vs. 68.1 months, respectively; p=0.3). Analysis of tumor grade revealed that well- differentiated tumors were present in 122 patients (18.63%). Among these patients, there was no statistically significant difference in survival between BAA and CA. The primary tumor site was the colon in 89 patients (13.6%), with 77.5% being CA and 22.5% BAA. Pancreatic tumors were present in 119 patients (18.2%), with 72% being CA and 28% BAA. The next most common primary sites were the small intestine (24.9%), rectum (17.6%), and stomach (9.9%). In comparing survival outcomes between racial groups, CA patients had a significantly worse OS (76.9 months) compared to BAA patients (84.6 months) (p=0.05). Regardless of race, females demonstrated better survival (84.2 months) compared to males (75.7 months) (p=0.04). In our retrospective analysis, Caucasian (CA) patients had worse overall survival (OS) than Black African American (BAA) patients, likely due to a higher proportion of CA patients with high- grade histology and primary tumors in the colon. Females showed better OS than males across all subtypes. The reasons for the higher incidence of worse histology in CA patients are unclear. Larger studies are needed to confirm these findings, understand racial disparities, and develop strategies to mitigate them. Citation Format: Radhika Gutta, Wan-Ting su, Ruicond She, Muhammad Shahid, Gazala Khan. Real world treatment patterns and patient outcomes of neuroendocrine tumors: A single institution study [abstract]. In: Proceedings of the 17th AACR Conference on the Science of Cancer Health Disparities in Racial/Ethnic Minorities and the Medically Underserved; 2024 Sep 21-24; Los Angeles, CA. Philadelphia (PA): AACR; Cancer Epidemiol Biomarkers Prev 2024;33(9 Suppl):Abstract nr A070.

Improving electrocardiographic imaging solutions: A comprehensive study on regularization parameter selection in L-curve optimization in the Atria

BackgroundIn electrocardiographic imaging (ECGI), selecting an optimal regularization parameter (λ) is crucial for obtaining accurate inverse electrograms. The effects of signal and geometry uncertainties on the inverse problem regularization have not been thoroughly quantified, and there is no established methodology to identify when λ is sub-optimal due to these uncertainties. This study introduces a novel approach to λ selection using Tikhonov regularization and L-curve optimization, specifically addressing the impact of electrical noise in body surface potential map (BSPM) signals and geometrical inaccuracies in the cardiac mesh. MethodsNineteen atrial simulations (5 of regular rhythms and 14 of atrial fibrillation) ensuring variability in substrate complexity and activation patterns were used for computing the ECGI with added white Gaussian noise from 40 dB to -3dB. Cardiac mesh displacements (1–3 cm) were applied to simulate the uncertainty of atrial positioning and study its impact on the L-curve shape. The regularization parameter, the maximum curvature, and the most horizontal angle of the L-curve (β) were quantified. In addition, BSPM signals from real patients were used to validate our findings. ResultsThe maximum curvature of the L-curve was found to be inversely related to signal-to-noise ratio and atrial positioning errors. In contrast, the β angle is directly related to electrical noise and remains unaffected by geometrical errors. Our proposed adjustment of λ, based on the β angle, provides a more reliable ECGI solution than traditional corner-based methods. Our findings have been validated with simulations and real patient data, demonstrating practical applicability. ConclusionAdjusting λ based on the amount of noise in the data (or on the β angle) allows finding optimal ECGI solutions than a λ purely found at the corner of the L-curve. It was observed that the relevant information in ECGI activation maps is preserved even under the presence of uncertainties when the regularization parameter is correctly selected. The proposed criteria for regularization parameter selection have the potential to enhance the accuracy and reliability of ECGI solutions.

Influence of the use of a tablet-based clinical decision support algorithm by general practitioners on the consultation process: the example of FeverTravelApp

BackgroundDespite the proven positive effects of clinical decision support systems (CDSSs) on general practitioners’ (GPs’) performance and patient management, their adoption remains slow. Several factors have been proposed to explain GPs' reluctance to adopt these tools. This study hypothesizes that the influence of CDSSs on patient-physician interactions could be a determining factor. To explore this hypothesis, we utilized the FeverTravelApp, designed to assist GPs in managing patients presenting with fever after returning from the tropics. A case–control study was conducted, observing and analyzing fourteen consultations between seven physicians and three simulated patients. Each physician conducted consultations both with and without the FeverTravelApp. The consultations were video-recorded and analyzed using a custom analysis grid based on three existing tools. Simulated patients completed the Communication Assessment Tool (CAT) after each consultation, and each physician participated in a semistructured interview following the use of the app.ResultsThe use of the FeverTravelApp influenced multiple aspects of the consultation, particularly communication. Both patient and GP speaking times decreased, while active silence (no one talking while the GP actively performed a task) increased. GPs focused more on the app, which reduced direct patient interaction. However, this influence seemed to bother GPs more than simulated patients, who rated their GPs equally whether the app was used or not. This could be because patients felt better understood when GPs asked fewer but more specific questions related to travel medicine, thus effectively addressing their concerns.ConclusionsThis study supports the hypothesis that CDSSs influence consultation dynamics, which may contribute to their slow adoption. It is essential to involve clinicians early in the development of CDSSs to adapt them to clinical workflows and ensure system interoperability. Additionally, tools that allow clinicians to follow the entire clinical reasoning process, such as decision trees, are needed. Further research is necessary to confirm these findings in real patient settings and to develop CDSSs that meet both patients’ and GPs’ expectations.

Exploring Generative Adversarial Networks for Augmenting Network Intrusion Detection Tasks

The advent of generative networks and their adoption in numerous domains and communities have led to a wave of innovation and breakthroughs in artificial intelligence and machine learning. Generative Adversarial Networks (GANs) have expanded the scope of what is possible with machine learning, allowing for new applications in areas such as computer vision, natural language processing, and creative AI. GANs, in particular, have been used for a wide range of tasks, including image and video generation, data augmentation, style transfer, and anomaly detection. They have also been used for medical imaging and drug discovery, where they can generate synthetic data to augment small datasets, reduce the need for expensive experiments, and lower the number of real patients that must be included in medical trials. Given these developments, we propose using the power of generative adversarial networks to create and augment flow-based network traffic datasets. We evaluate a series of GAN architectures, including Wasserstein, conditional, energy-based, gradient penalty, and LSTM GANs. We evaluate their performance on a set of flow-based network traffic data collected from 16 subjects who used their computers for home, work, and study purposes. The performance of these GAN architectures is described according to metrics that involve networking principles, data distribution among a collection of flows, and temporal data distribution. Given the tendency of network intrusion detection datasets to have a very imbalanced data distribution, i.e., a large number of samples in the “normal traffic” category and a comparatively low number of samples assigned to the “intrusion” categories, we test our GANs by augmenting the intrusion data and checking whether this helps intrusion detection neural networks in their task. We publish the resulting UPBFlow dataset and code on GitHub 1 .

Fractional-Order Modeling of the Depth of Analgesia as Reference Model for Control Purposes

Little research has been carried out in terms of modeling and control of analgesia. However, emerging new technology and recent prototypes paved the way for several ideas on pain modeling for control. Recently, such an idea has been proposed for measuring the Depth of Analgesia (DoA). In this paper, that solution is further exploited towards obtaining a novel fractional-order model and dedicated controller for DoA. First, clinical data from patients undergoing general anesthesia are used to determine a commensurate fractional-order model of the skin impedance at each sampling period. Second, we provide a proof of concept indicating that fractional order changes due to variations in the infused opioid drug (Remifentanil). Third, a fractional-order model for DoA is developed correlating the changes in the pain index (as the output signal) and the Remifentanil infusion rate (as the input signal). Standard optimization routines are used to estimate the parameters. A database of 19 real patients is used. Lastly, a preliminary fractional-order controller is designed and tested in simulation for the 19 patients. The closed-loop simulation results correspond to the expected clinical outcomes.

Unmasking and quantifying racial bias of large language models in medical report generation

BackgroundLarge language models like GPT-3.5-turbo and GPT-4 hold promise for healthcare professionals, but they may inadvertently inherit biases during their training, potentially affecting their utility in medical applications. Despite few attempts in the past, the precise impact and extent of these biases remain uncertain.MethodsWe use LLMs to generate responses that predict hospitalization, cost and mortality based on real patient cases. We manually examine the generated responses to identify biases.ResultsWe find that these models tend to project higher costs and longer hospitalizations for white populations and exhibit optimistic views in challenging medical scenarios with much higher survival rates. These biases, which mirror real-world healthcare disparities, are evident in the generation of patient backgrounds, the association of specific diseases with certain racial and ethnic groups, and disparities in treatment recommendations, etc.ConclusionsOur findings underscore the critical need for future research to address and mitigate biases in language models, especially in critical healthcare applications, to ensure fair and accurate outcomes for all patients.

Revolutionizing Prosthodontics with Artificial Intelligence: A Narrative review

The revolutionary impact of artificial intelligence (Al) on prosthodontics is addressed in this narrative review with focus on how it has changed the way patients are examined. Additionally, machine learning is used which aids in greater accuracy and customization when creating a treatment plan for the patient. Artificial intelligence (AI)-driven technologies are essential in the creation and manufacturing of prostheses and has improved computer-aided design (CAD) systems, making it easier to create customized, anatomically accurate prosthetic limbs. Apart from its practical uses Artificial Intelligence fosters an Ongoing investigation and advancement in the field of prosthodontics, as new materials, techniques, and treatment approaches are developed, Al system continuously incorporate lessons from real patient experiences, pushing the boundaries of what is possible in the field. To address the inherent difficulties in traditional approaches this paper explores a convincing case for using Al in decision making and treatment planning in prosthodontics. Through use of unique patient data to support evidence-based decisions treatment planning can become more precise and personalized by leveraging Al analytical powers. Furthermore, the incorporation of Al-powered technologies including CAD and 3D printing is being investigated as a way to optimize manufacturing process of different of prostheses. Al is playing a crucial role in molding the future of the discipline as highlighted by the ongoing research element. This article highlights the revolutionary potential of artificial intelligence (Al) in prosthodontics, providing a state of and patient-centered approach to dental care.

Apalutamide for non-metastatic castration-resistant prostate cancer (nmCRPC): real world data of a multicenter study

PurposeApalutamide plus androgen-deprivation therapy (ADT) improved outcomes in patients with non-metastatic castration-resistant prostate cancer (nmCRPC). Nevertheless real-world data are limited. The aim of this multicenter study was to generate real-world data from nmCRPC patients treated with ADT plus apalutamide.MethodsIn this observational cohort based investigator initiated trial data of nmCRPC patients receiving apalutamide plus ADT were collected focusing on patient demographic data, prostate-specific antigen (PSA) declines, safety profile including dose modification/discontinuation as well as subsequent therapy and metastasis-free survival (MFS).ResultsData from a total of 31 nmCRPC patients were documented. Compared to the Phase III study Spartan real-world patients are older, showed a higher ECOG-PS and more aggressive tumors. In the cohort PSA decreased about 98.1%, 74% of patients showed a PSA decrease over 90% and 54.8% reached a PSA-level < 0.2ng/ml. Apalutamide was well tolerated in real world patients: adverse events occurred in 67.7% but were in the majority mild (≥ grade 3: 6.5%). Dose reduction was necessary in 38.7% and 32.2% discontinued apalutamide treatment. MFS was 43 months and majority of patients were subsequently treated with abiraterone.ConclusionIn real world more comorbid nmCRPC patients with a higher ECOG-PS and more aggressive tumors are treated with apalutamide plus ADT. Nevertheless efficacy results as well as side effects are similar in real-world compared to Spartan trial showing also a rapid, durable and deep PSA response with a median MFS of 43 months.

Patient Feedback Applied in Undergraduate Dental Education for Individual Student Development and Assessment: A Scoping Review.

Active involvement of patients in healthcare professional education is well established, taking a variety of forms. There is a steer towards patient feedback informing the development of dental students and while there is recognition of its potential value to individual students, challenges exist related to collection and use. What is unclear is, within a dental education setting, the extent and use of patient feedback to individual students. A scoping review was conducted to assess and map the volume and characteristics of the research/literature in this area. Systematic searches of bibliographic databases Ovid MEDLINE(R), Scopus, ERIC and Embase were conducted, and wider literature (Google Scholar) was searched. Screening was conducted based on eligibility criteria and a customised data charting form was used. The electronic and citation tracking searches identified 1021 studies. After duplicates were removed, 778 studies were screened by title and abstract, and 718 studies were found to be irrelevant to the current review. Sixty full-text studies were assessed for eligibility, 46 studies were excluded, and 14 studies were included for data charting. This review has identified that patient feedback has been captured through both simulated and real patient encounters. There was a bias towards feedback generated through simulated patient encounters. Feedback was reported to support the development of a range of skills, most frequently communication and patient management. Challenges that were identified by researchers related to staff/student engagement and available resources.