Can ChatGPT provide appropriate meal plans for NCD patients?

OBJECTIVES

Dietary habits significantly affect health conditions and are closely related to the onset and progression of non-communicable diseases (NCDs). Consequently, a well-balanced diet plays an important role in lessening the effects of various disorders, including NCDs. Several artificial intelligence recommendation systems have been developed to propose healthy and nutritious diets. Most of these systems use expert knowledge and guidelines to provide tailored diets and encourage healthier eating habits. However, new advances in large language models such as ChatGPT, with their ability to produce human-like responses, have led individuals to search for advice in several tasks, including diet recommendations. This study aimed to determine the ability of ChatGPT models to generate appropriate personalized meal plans for patients with obesity, cardiovascular diseases, and type 2 diabetes.

METHODS

Using a state-of-the-art knowledge-based recommendation system as a reference, we assessed the meal plans generated by two large language models in terms of energy intake, nutrient accuracy, and meal variability.

RESULTS

Experimental results with different user profiles revealed the potential of ChatGPT models to provide personalized nutritional advice.

CONCLUSION

Additional supervision and guidance by nutrition experts or knowledge-based systems are required to ensure meal appropriateness for users with NCDs.

What is the effectiveness of surgical and non-surgical therapies in the treatment of ischemic priapism in patients with sickle cell disease? A systematic review by the EAU Sexual and Reproductive Health Guidelines Panel

Sickle cell disease (SCD) is an inherited hemoglobin disorder characterized by the occlusion of small blood vessels by sickle-shaped red blood cells. SCD is associated with a number of complications, including ischemic priapism. While SCD accounts for at least one-third of all priapism cases, no definitive treatment strategy has been established to specifically treat patients with SC priapism. The aim of this systematic review was to assess the efficacy and safety of contemporary treatment modalities for acute and stuttering ischemic priapism associated with SCD. The primary outcome measures were defined as resolution of acute priapism (detumescence) and complete response of stuttering priapism, while the primary harm outcome was as sexual dysfunction. The protocol for the review has been registered (PROSPERO Nr: CRD42020182001), and a systematic search of Medline, Embase, and Cochrane controlled trials databases was performed. Three trials with 41 observational studies met the criteria for inclusion in this review. None of the trials assessed detumescence, as a primary outcome. All of the trials reported a complete response of stuttering priapism; however, the certainty of the evidence was low. It is clear that assessing the effectiveness of specific interventions for priapism in SCD, well-designed, adequately-powered, multicenter trials are strongly required.

Surgical and minimally invasive treatment of ischaemic and non-ischaemic priapism: a systematic review by the EAU Sexual and Reproductive Health Guidelines panel

Surgical treatments for ischemic priapism (IP) include shunts or penile implants. Non-ischemic priapism (NIP) is usually the result of penile/perineal trauma causing an arterial fistula and embolisation may be required. We conducted a systematic review on behalf of the EAU Sexual and Reproductive health Guidelines panel to analyse the available evidence on efficacy and safety of surgical modalities for IP and NIP. Outcomes were priapism resolution, sexual function and adverse events following surgery. Overall, 63 studies (n = 923) met inclusion criteria up to September 2021. For IP (n = 702), surgery comprised distal (n = 274), proximal shunts (n = 209) and penile prostheses (n = 194). Resolution occurred in 18.7-100% for distal, 5.7-100% for proximal shunts and 100% for penile prostheses. Potency rate was 20-100% for distal, 11.1-77.2% for proximal shunts, and 26.3-100% for penile prostheses, respectively. Patient satisfaction was 60-100% following penile prostheses implantation. Complications were 0-42.5% for shunts and 0-13.6% for IPP. For NIP (n = 221), embolisation success was 85.7-100% and potency 80-100%. The majority of studies were retrospective cohort studies. Risk of bias was high. Overall, surgical shunts have acceptable success rates in IP. Proximal/venous shunts should be abandoned due to morbidity/ED rates. In IP > 48 h, best outcomes are seen with penile prostheses implantation. Embolisation is the mainstay technique for NIP with high resolution rates and adequate erectile function.

Automatic Ergonomic Risk Assessment Using a Variational Deep Network Architecture

Ergonomic risk assessment is vital for identifying work-related human postures that can be detrimental to the health of a worker. Traditionally, ergonomic risks are reported by human experts through time-consuming and error-prone procedures; however, automatic algorithmic methods have recently started to emerge. To further facilitate the automatic ergonomic risk assessment, this paper proposes a novel variational deep learning architecture to estimate the ergonomic risk of any work-related task by utilizing the Rapid Entire Body Assessment (REBA) framework. The proposed method relies on the processing of RGB images and the extraction of 3D skeletal information that is then fed to a novel deep network for accurate and robust estimation of REBA scores for both individual body parts and the entire body. Through a variational approach, the proposed method processes the skeletal information to construct a descriptive skeletal latent space that can accurately model human postures. Moreover, the proposed method distills knowledge from ground truth ergonomic risk scores and leverages it to further enhance the discrimination ability of the skeletal latent space, leading to improved accuracy. Experiments on two well-known datasets (i.e., University of Washington Indoor Object Manipulation (UW-IOM) and Technische Universität München (TUM) Kitchen) validate the ability of the proposed method to achieve accurate results, overcoming current state-of-the-art methods.

Users' Perspective on the AI-Based Smartphone PROTEIN App for Personalized Nutrition and Healthy Living: A Modified Technology Acceptance Model (mTAM) Approach

The ubiquitous nature of smartphone ownership, its broad application and usage, along with its interactive delivery of timely feedback are appealing for health-related behavior change interventions via mobile apps. However, users' perspectives about such apps are vital in better bridging the gap between their design intention and effective practical usage. In this vein, a modified technology acceptance model (mTAM) is proposed here, to explain the relationship between users' perspectives when using an AI-based smartphone app for personalized nutrition and healthy living, namely, PROTEIN, and the mTAM constructs toward behavior change in their nutrition and physical activity habits. In particular, online survey data from 85 users of the PROTEIN app within a period of 2 months were subjected to confirmatory factor analysis (CFA) and regression analysis (RA) to reveal the relationship of the mTAM constructs, i.e., perceived usefulness (PU), perceived ease of use (PEoU), perceived novelty (PN), perceived personalization (PP), usage attitude (UA), and usage intention (UI) with the users' behavior change (BC), as expressed via the acceptance/rejection of six related hypotheses (H1-H6), respectively. The resulted CFA-related parameters, i.e., factor loading (FL) with the related p-value, average variance extracted (AVE), and composite reliability (CR), along with the RA results, have shown that all hypotheses H1-H6 can be accepted (p < 0.001). In particular, it was found that, in all cases, FL > 0.5, CR > 0.7, AVE > 0.5, indicating that the items/constructs within the mTAM framework have good convergent validity. Moreover, the adjusted coefficient of determination (R 2) was found within the range of 0.224-0.732, justifying the positive effect of PU, PEoU, PN, and PP on the UA, that in turn positively affects the UI, leading to the BC. Additionally, using a hierarchical RA, a significant change in the prediction of BC from UA when the UI is used as a mediating variable was identified. The explored mTAM framework provides the means for explaining the role of each construct in the functionality of the PROTEIN app as a supportive tool for the users to improve their healthy living by adopting behavior change in their dietary and physical activity habits. The findings herein offer insights and references for formulating new strategies and policies to improve the collaboration among app designers, developers, behavior scientists, nutritionists, physical activity/exercise physiology experts, and marketing experts for app design/development toward behavior change.

Artificial Intelligence Technologies for Sign Language

AI technologies can play an important role in breaking down the communication barriers of deaf or hearing-impaired people with other communities, contributing significantly to their social inclusion. Recent advances in both sensing technologies and AI algorithms have paved the way for the development of various applications aiming at fulfilling the needs of deaf and hearing-impaired communities. To this end, this survey aims to provide a comprehensive review of state-of-the-art methods in sign language capturing, recognition, translation and representation, pinpointing their advantages and limitations. In addition, the survey presents a number of applications, while it discusses the main challenges in the field of sign language technologies. Future research direction are also proposed in order to assist prospective researchers towards further advancing the field.

Recurrent neural network pruning using dynamical systems and iterative fine-tuning

Network pruning techniques are widely employed to reduce the memory requirements and increase the inference speed of neural networks. This work proposes a novel RNN pruning method that considers the RNN weight matrices as collections of time-evolving signals. Such signals that represent weight vectors can be modelled using Linear Dynamical Systems (LDSs). In this way, weight vectors with similar temporal dynamics can be pruned as they have limited effect on the performance of the model. Additionally, during the fine-tuning of the pruned model, a novel discrimination-aware variation of the L2 regularization is introduced to penalize network weights (i.e., reduce the magnitude), whose impact on the output of an RNN network is minimal. Finally, an iterative fine-tuning approach is proposed that employs a bigger model to guide an increasingly smaller pruned one, as a steep decrease of the network parameters can irreversibly harm the performance of the pruned model. Extensive experimentation with different network architectures demonstrates the potential of the proposed method to create pruned models with significantly improved perplexity by at least 0.62% on the PTB dataset and improved F1-score by 1.39% on the SQuAD dataset, contrary to other state-of-the-art approaches that slightly improve or even deteriorate models' performance.

Assistive HCI-Serious Games Co-design Insights: The Case Study of i-PROGNOSIS Personalized Game Suite for Parkinson's Disease

Human-Computer Interaction (HCI) and games set a new domain in understanding people's motivations in gaming, behavioral implications of game play, game adaptation to player preferences and needs for increased engaging experiences in the context of HCI serious games (HCI-SGs). When the latter relate with people's health status, they can become a part of their daily life as assistive health status monitoring/enhancement systems. Co-designing HCI-SGs can be seen as a combination of art and science that involves a meticulous collaborative process. The design elements in assistive HCI-SGs for Parkinson's Disease (PD) patients, in particular, are explored in the present work. Within this context, the Game-Based Learning (GBL) design framework is adopted here and its main game-design parameters are explored for the Exergames, Dietarygames, Emotional games, Handwriting games, and Voice games design, drawn from the PD-related i-PROGNOSIS Personalized Game Suite (PGS) (www.i-prognosis.eu) holistic approach. Two main data sources were involved in the study. In particular, the first one includes qualitative data from semi-structured interviews, involving 10 PD patients and four clinicians in the co-creation process of the game design, whereas the second one relates with data from an online questionnaire addressed by 104 participants spanning the whole related spectrum, i.e., PD patients, physicians, software/game developers. Linear regression analysis was employed to identify an adapted GBL framework with the most significant game-design parameters, which efficiently predict the transferability of the PGS beneficial effect to real-life, addressing functional PD symptoms. The findings of this work can assist HCI-SG designers for designing PD-related HCI-SGs, as the most significant game-design factors were identified, in terms of adding value to the role of HCI-SGs in increasing PD patients' quality of life, optimizing the interaction with personalized HCI-SGs and, hence, fostering a collaborative human-computer symbiosis.

A Review on Early Forest Fire Detection Systems Using Optical Remote Sensing

The environmental challenges the world faces nowadays have never been greater or more complex. Global areas covered by forests and urban woodlands are threatened by natural disasters that have increased dramatically during the last decades, in terms of both frequency and magnitude. Large-scale forest fires are one of the most harmful natural hazards affecting climate change and life around the world. Thus, to minimize their impacts on people and nature, the adoption of well-planned and closely coordinated effective prevention, early warning, and response approaches are necessary. This paper presents an overview of the optical remote sensing technologies used in early fire warning systems and provides an extensive survey on both flame and smoke detection algorithms employed by each technology. Three types of systems are identified, namely terrestrial, airborne, and spaceborne-based systems, while various models aiming to detect fire occurrences with high accuracy in challenging environments are studied. Finally, the strengths and weaknesses of fire detection systems based on optical remote sensing are discussed aiming to contribute to future research projects for the development of early warning fire systems.

Validation of a Deep Learning System for the Full Automation of Bite and Meal Duration Analysis of Experimental Meal Videos

Eating behavior can have an important effect on, and be correlated with, obesity and eating disorders. Eating behavior is usually estimated through self-reporting measures, despite their limitations in reliability, based on ease of collection and analysis. A better and widely used alternative is the objective analysis of eating during meals based on human annotations of in-meal behavioral events (e.g., bites). However, this methodology is time-consuming and often affected by human error, limiting its scalability and cost-effectiveness for large-scale research. To remedy the latter, a novel "Rapid Automatic Bite Detection" (RABiD) algorithm that extracts and processes skeletal features from videos was trained in a video meal dataset (59 individuals; 85 meals; three different foods) to automatically measure meal duration and bites. In these settings, RABiD achieved near perfect agreement between algorithmic and human annotations (Cohen's kappa κ = 0.894; F1-score: 0.948). Moreover, RABiD was used to analyze an independent eating behavior experiment (18 female participants; 45 meals; three different foods) and results showed excellent correlation between algorithmic and human annotations. The analyses revealed that, despite the changes in food (hash vs. meatballs), the total meal duration remained the same, while the number of bites were significantly reduced. Finally, a descriptive meal-progress analysis revealed that different types of food affect bite frequency, although overall bite patterns remain similar (the outcomes were the same for RABiD and manual). Subjects took bites more frequently at the beginning and the end of meals but were slower in-between. On a methodological level, RABiD offers a valid, fully automatic alternative to human meal-video annotations for the experimental analysis of human eating behavior, at a fraction of the cost and the required time, without any loss of information and data fidelity.

EAU-ESMO consensus statements on the management of advanced and variant bladder cancer-an international collaborative multi-stakeholder effort: under the auspices of the EAU and ESMO Guidelines Committees†

BACKGROUND

Although guidelines exist for advanced and variant bladder cancer management, evidence is limited/conflicting in some areas and the optimal approach remains controversial.

OBJECTIVE

To bring together a large multidisciplinary group of experts to develop consensus statements on controversial topics in bladder cancer management.

DESIGN

A steering committee compiled proposed statements regarding advanced and variant bladder cancer management which were assessed by 113 experts in a Delphi survey. Statements not reaching consensus were reviewed; those prioritised were revised by a panel of 45 experts before voting during a consensus conference.

SETTING

Online Delphi survey and consensus conference.

PARTICIPANTS

The European Association of Urology (EAU), the European Society for Medical Oncology (ESMO), experts in bladder cancer management.

OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS

Statements were ranked by experts according to their level of agreement: 1-3 (disagree), 4-6 (equivocal), 7-9 (agree). A priori (level 1) consensus was defined as ≥70% agreement and ≤15% disagreement, or vice versa. In the Delphi survey, a second analysis was restricted to stakeholder group(s) considered to have adequate expertise relating to each statement (to achieve level 2 consensus).

RESULTS AND LIMITATIONS

Overall, 116 statements were included in the Delphi survey. Of these, 33 (28%) statements achieved level 1 consensus and 49 (42%) statements achieved level 1 or 2 consensus. At the consensus conference, 22 of 27 (81%) statements achieved consensus. These consensus statements provide further guidance across a broad range of topics, including the management of variant histologies, the role/limitations of prognostic biomarkers in clinical decision making, bladder preservation strategies, modern radiotherapy techniques, the management of oligometastatic disease and the evolving role of checkpoint inhibitor therapy in metastatic disease.

CONCLUSIONS

These consensus statements provide further guidance on controversial topics in advanced and variant bladder cancer management until a time where further evidence is available to guide our approach.

Intrauterine device migration to the urinary bladder causing sexual dysfunction: a case report

BACKGROUND

Intravesical migration represents an uncommon complication of intrauterine device (IUD) insertion. We present the case of an IUD that migrated to the urinary bladder, causing significant sexual complaints.

CASE REPORT

A 38-year-old woman presented with complaints of gradually evolving dyspareunia and recurrent urinary tract infections during the past 12 months. She reported an IUD insertion 18 months before. Further detailed evaluation revealed disorders in all sexual domains. Imaging and cystoscopy detected the presence of IUD in the urinary bladder. Under anesthesia, the IUD was removed out of the bladder without any complications. In her follow-up evaluation after six months, her sexual function was significantly improved and she had no urinary symptoms.

CONCLUSION

Sexual difficulties in a woman with an IUD should raise the suspicion of device dislodgement or dislocation. Hippokratia 2016, 20(1): 70-72.

Morphological and textural analysis of centroblasts in low-thickness sliced tissue biopsies of follicular lymphoma

This paper presents a new method for discriminating centroblast (CB) from non-centroblast cells in microscopic images acquired from tissue biopsies of follicular lymphoma. In the proposed method tissue sections are sliced at a low thickness level, around 1-1.5 μm, which provides a more detailed depiction of the nuclei and other textural information of cells usually not distinguishable in thicker specimens, such as 4-5 μm, that have been used in the past by other researchers. To identify CBs, a morphological and textural analysis is applied in order to extract various features related to their nuclei, nucleoli and cytoplasm. The generated feature vector is then used as input in a two-class SVM classifier with ε-Support Vector Regression and radial basis kernel function. Experimental results with an annotated dataset consisting of 300 images of centroblasts and non-centroblasts, derived from high-power field images of follicular lymphoma stained with Hematoxylin and Eosin, have shown the great potential of the proposed method with an average detection rate of 97.44%.

Pre-pregnancy obesity: maternal, neonatal and childhood outcomes

Nowadays, obesity rates have an increasing tendency, since the incidence of obesity in both developed and developing countries is still rising over the years. Maternal pre-pregnancy obesity seems to have an influence on both obstetrical and neonatal outcomes. Many researchers have focused on pregnancies of obese nulliparous, non diabetic women as well as on the medical profile of their neonates, with conflicting conclusions. Additionally, several studies have followed these neonates through their childhood and adult life in order to observe them for any occurrence towards specific diseases. In our study, literature was reviewed and results are presented, into two groups. The first group summarizes the correlation of high maternal prepregnancy Body Mass Index (BMI) with the rates of hypertensive disorders, fertility, cesarean section and maternal mortality, while the second group correlates maternal BMI to neonatal Apgar score, neonatal admission to NICU, preterm delivery, congenital defects, birthweight, and weight status after birth, child morbidity, respiratory problems as asthma and children's mortality. Maternal pre-pregnancy obesity tends to have an important negative impact on the above mentioned outcomes. However, further research, in certain fields, needs to be carried out in order to gain a clear image.

Dual inhibition of aromatase and epidermal growth factor receptor in non-small cell lung cancer

e22189

Background: Recent evidence suggests that estrogen signaling is important in the progression of cancers expressing estrogen receptors (ERs) and may also be involved in the pathogenesis of non-small cell lung cancer (NSCLC). Aromatase is an enzyme complex that catalyses the final step in estrogen synthesis and is present in several tissues, including the lung. In view of a possible functional interaction between the ER and the epidermal growth factor receptor (EGFR) pathways in NSCLC, we investigated the dual inhibition of aromatase and EGFR in NSCLC cell lines. Methods: In the current study we used exemestane, an irreversible steroidal aromatase inactivator, and erlotinib, an EGFR tyrosine kinase inhibitor. The in vitroexperiments were performed using H23 and A549, two NSCLC cell lines with low and high levels of aromatase, respectively. Cell proliferation was measured by MTT assay. Metalloproteinase (MMP) levels were detected by zymography and cell migration was determined by boyden chamber assay. EGFR protein levels detection was performed by immunofluorescense assay. Results: Exemestane and erlotinib inhibited H23 and A549 cell proliferation either alone or in combination, 48 hours after their application. However, the combination of exemestane and erlotinib was more effective than each agent alone, in H23 cells. Furthermore, exemestane decreased MMP-2 and MMP- 9 levels in H23 cells, whereas erlotinib did not. The combination of exemestane and erlotinib had the same effect on MMPs, as exemestane alone. The effect on cell migration was in line with the results in MMPs levels. In A549 cells, no changes in MMPs levels or cell migration were demonstrated. In addition, exemestane altered the location of EGFR protein in H23 cells, but not in A549 cells. Conclusions: Our findings suggest an antiproliferative effect of exemestane and erlotinib in both cell lines, as well as synergy for the combination in H23 cells. The activity of the combination in these cells with low levels of aromatase might involve an additional effect of exemestane on EGFR protein location. Erlotinib did not enhance the effect of exemestane on MMPs secretion and migration in H23 cells.

No significant financial relationships to disclose.

Global initiative for chronic obstructive lung disease for chronic obstructive pulmonary disease: GOLD opportunity for lung disorders

BACKGROUND

The purpose of this study was to assess the agreement of asthma and chronic obstructive pulmonary disease (COPD) treatment prescribed by physicians and pulmonologists in comparison to asthma and COPD guidelines and the need of the implementation of COPD guidelines in primary health care physicians.

METHODS

Eighty-three asthma patients and 100 COPD patients were chosen and classified in relation to the agreement of their treatment prescribed by a health care physician and that mentioned by global initiative for chronic obstructive lung disease (GOLD) The COPD patients were classified according to their stage of the disease too.

RESULTS

Both pulmonologists and primary health care physicians manage asthma patients following asthma guidelines, while great proportion of COPD patients are undertreated by primary health care physicians. The proportion of undertreated COPD patients is decreased as the stage of disease is progressing.

CONCLUSIONS

COPD patients mainly are undertreated by primary health care physicians when they are in the primary stages of the disease. The overtreatment of some patients consists of high doses of inhaled steroids prescribed by both pulmonologists, and mainly, primary health care physicians. Therefore, it can be concluded that there is the need of the implementation of COPD guideline by primary health care physicians and the need of COPD patients to be diagnosed in early stages by performing spirometry.

Synthesis, molecular structure determination, and antitumor activity of platinum(II) and palladium(II) complexes of 2-substituted benzimidazole

The complexes of 2-aminomethyl benzimidazole, 2-(beta-aminoethyl)benzimidazole, and 2-(alpha-aminoethy-l)benzimidazole with Pt(II) and Pd(II) have been prepared. The molecular structure of the free ligands and their complexes were studied by IR and 1H NMR. It was concluded that the substituted benzimidazole derivatives behave as bidentate ligands, being bound to the metal atoms via the nitrogen of the -N = group and the amino group of the side chain of the benzimidazole ring. The metal complexes were tested for antineoplastic activity both in cultures of neoplastic cells (MEL-745, K-562, Colon 205, IMP-32, SK-N-SH) and in vivo in rodents bearing L-1210 leukemia. The antiproliferative activity of these agents was compared to that of cis-platin.

Analysis of early lymphocyte activation events by fluorescence polarization flow cytometry

After short-term (up to 4 h) stimulation with mitogen or antigen, lymphocytes were incubated with fluorescein diacetate and the polarization of fluorescence from intracellular fluorescein was measured on a specially adapted FACS II. This flow cytofluorimetric method to assay early changes in activated lymphocytes gave a reproducible response to the mitogens phytohaemagglutinin (PHA), concanavalin-A and the monoclonal antibody OKT3, recognized at 1 h by decreased polarization. A response by immune spleen cells to the antigen dinitrophenyl-ovalbumin was revealed at 4 h. The calcium ionophore A23187 induced an increase in polarization after only 10 min. The PHA polarization response was shown to be dependent on PHA binding, PHA dose, T cells, calcium ions and an intact cytoskeleton. The cellular events monitored by the polarization change are presumably altered fluidity of the probe's microenvironment due to conformational change in macromolecules to which the probe has bound or to dissociation of the probe into the aqueous phase. The fluorescein fluorescence polarization assay is a reliable and sensitive monitor of early lymphocyte activation events and, coupled with the use of a flow cytometer, permits study of particular subpopulations of responding cells.

Flow cytofluorimetry of fluorescein fluorescence polarization to assay lymphocyte activation

Change in fluorescence polarization of intracellular fluorescein measured with a specially adapted flow cytometer reliably reflected subtle biophysical changes in cells, such as those accompanying increased temperature or osmolality of the suspending medium. This system was developed to monitor changes in lymphocytes one hour after stimulation with the mitogen phytohaemagglutinin, and provided a sensitive and rapid assay of lymphocyte activation.

Fluorescence polarization assay by flow cytometry

Fluorescence polarization measurement on cell suspensions provides a highly sensitive means for detecting subtle changes in the cells, such as occur early after lymphocyte activation or on malignant transformation. We review here the principles of fluorescence polarization, its measurement by a commercially available flow cytometer and application of such assays especially in cellular immunology.