Evaluation of four chatbots in autoimmune liver disease: A comparative analysis.

INTRODUCTION AND OBJECTIVES: Autoimmune liver diseases (AILDs) are rare and require precise evaluation, which is often challenging for medical providers. Chatbots are innovative solutions to assist healthcare professionals in clinical management. In our study, ten liver specialists systematically evaluated four chatbots to determine their utility as clinical decision support tools in the field of AILDs. MATERIALS AND METHODS: We constructed a 56-question questionnaire focusing on AILD evaluation, diagnosis, and management of Autoimmune Hepatitis (AIH), Primary Biliary Cholangitis (PBC), and Primary Sclerosing Cholangitis (PSC). Four chatbots -ChatGPT 3.5, Claude, Microsoft Copilot, and Google Bard- were presented with the questions in their free tiers in December 2023. Responses underwent critical evaluation by ten liver specialists using a standardized 1 to 10 Likert scale. The analysis included mean scores, the number of highest-rated replies, and the identification of common shortcomings in chatbots performance. RESULTS: Among the assessed chatbots, specialists rated Claude highest with a mean score of 7.37 (SD = 1.91), followed by ChatGPT (7.17, SD = 1.89), Microsoft Copilot (6.63, SD = 2.10), and Google Bard (6.52, SD = 2.27). Claude also excelled with 27 best-rated replies, outperforming ChatGPT (20), while Microsoft Copilot and Google Bard lagged with only 6 and 9, respectively. Common deficiencies included listing details over specific advice, limited dosing options, inaccuracies for pregnant patients, insufficient recent data, over-reliance on CT and MRI imaging, and inadequate discussion regarding off-label use and fibrates in PBC treatment. Notably, internet access for Microsoft Copilot and Google Bard did not enhance precision compared to pre-trained models. CONCLUSIONS: Chatbots hold promise in AILD support, but our study underscores key areas for improvement. Refinement is needed in providing specific advice, accuracy, and focused up-to-date information. Addressing these shortcomings is essential for enhancing the utility of chatbots in AILD management, guiding future development, and ensuring their effectiveness as clinical decision-support tools.

Weakly-supervised deep learning models enable HER2-low prediction from H &E stained slides.

BACKGROUND: Human epidermal growth factor receptor 2 (HER2)-low breast cancer has emerged as a new subtype of tumor, for which novel antibody-drug conjugates have shown beneficial effects. Assessment of HER2 requires several immunohistochemistry tests with an additional in situ hybridization test if a case is classified as HER2 2+. Therefore, novel cost-effective methods to speed up the HER2 assessment are highly desirable. METHODS: We used a self-supervised attention-based weakly supervised method to predict HER2-low directly from 1437 histopathological images from 1351 breast cancer patients. We built six distinct models to explore the ability of classifiers to distinguish between the HER2-negative, HER2-low, and HER2-high classes in different scenarios. The attention-based model was used to comprehend the decision-making process aimed at relevant tissue regions. RESULTS: Our results indicate that the effectiveness of classification models hinges on the consistency and dependability of assay-based tests for HER2, as the outcomes from these tests are utilized as the baseline truth for training our models. Through the use of explainable AI, we reveal histologic patterns associated with the HER2 subtypes. CONCLUSION: Our findings offer a demonstration of how deep learning technologies can be applied to identify HER2 subgroup statuses, potentially enriching the toolkit available for clinical decision-making in oncology.

The Evolution of Active Learning in Response to the Pandemic: The Role of Technology.

Active learning has consistently played a significant role in education. Through interactive tasks, group projects, and a variety of engaging activities, students are encouraged to forge connections with the subject matter. However, the pandemic has necessitated that educators adapt and refine their active learning techniques to accommodate the online environment. This has resulted in stimulating innovations in the field, encompassing virtual simulations, online collaboration tools, and interactive multimedia. The COVID-19 pandemic has rapidly transformed the landscape of teaching and learning, particularly in higher education. One of the most prominent shifts has been the widespread adoption of active learning techniques, which have increased student engagement and fostered deeper learning experiences. In this chapter, we examine the evolution of active learning during the pandemic, emphasizing its advantages and challenges. Furthermore, we delve into the role of advances in artificial intelligence and their potential to enhance the effectiveness of active learning approaches. As we once focused on leveraging the opportunities of remote teaching, we must now shift our attention to harnessing the power of AI responsibly and ethically to benefit our students. Drawing from our expertise in educational innovation, we provide insights and recommendations for educators aiming to maximize the benefits of active learning in the post-pandemic era.

Machine Learning Meets Physics-based Modeling: A Mass-spring System to Predict Protein-ligand Binding Affinity.

BACKGROUND: Computational assessment of the energetics of protein-ligand complexes is a challenge in the early stages of drug discovery. Previous comparative studies on computational methods to calculate the binding affinity showed that targeted scoring functions outperform universal models. OBJECTIVE: The goal here is to review the application of a simple physics-based model to estimate the binding. The focus is on a mass-spring system developed to predict binding affinity against cyclin-dependent kinase. METHOD: Publications in PubMed were searched to find mass-spring models to predict binding affinity. Crystal structures of cyclin-dependent kinases found in the protein data bank and two web servers to calculate affinity based on the atomic coordinates were employed. RESULTS: One recent study showed how a simple physics-based scoring function (named Taba) could contribute to the analysis of protein-ligand interactions. Taba methodology outperforms robust physics-based models implemented in docking programs such as AutoDock4 and Molegro Virtual Docker. Predictive metrics of 27 scoring functions and energy terms highlight the superior performance of the Taba scoring function for cyclin- dependent kinase. CONCLUSION: The recent progress of machine learning methods and the availability of these techniques through free libraries boosted the development of more accurate models to address protein-ligand interactions. Combining a naïve mass-spring system with machine-learning techniques generated a targeted scoring function with superior predictive performance to estimate pKi.

Interpretation and explanation of computer vision classification of carambola (Averrhoa carambola L.) according to maturity stage.

The classification of carambola, also known as starfruit, according to quality parameters is usually conducted by trained human evaluators through visual inspections. This is a costly and subjective method that can generate high variability in results. As an alternative, computer vision systems (CVS) combined with deep learning (DCVS) techniques have been introduced in the industry as a powerful and an innovative tool for the rapid and non-invasive classification of fruits. However, validating the learning capability and trustworthiness of a DL model, aka black box, to obtain insights can be challenging. To reduce this gap, we propose an integrated eXplainable Artificial Intelligence (XAI) method for the classification of carambolas at different maturity stages. We compared two Residual Neural Networks (ResNet) and Visual Transformers (ViT) to identify the image regions that are enhanced by a Random Forest (RF) model, with the aim of providing more detailed information at the feature level for classifying the maturity stage. Changes in fruit colour and physicochemical data throughout the maturity stages were analysed, and the influence of these parameters on the maturity stages was evaluated using the Gradient-weighted Class Activation Mapping (Grad-CAM), the Attention Maps using RF importance. The proposed approach provides a visualization and description of the most important regions that led to the model decision, in wide visualization follows the models an importance features from RF. Our approach has promising potential for standardized and rapid carambolas classification, achieving 91 % accuracy with ResNet and 95 % with ViT, with potential application for other fruits.

Performance of ChatGPT in Solving Questions From the Progress Test (Brazilian National Medical Exam): A Potential Artificial Intelligence Tool in Medical Practice.

Background The use of artificial intelligence (AI) is not a recent phenomenon, but the latest advancements in this technology are making a significant impact across various fields of human knowledge. In medicine, this trend is no different, although it has developed at a slower pace. ChatGPT is an example of an AI-based algorithm capable of answering questions, interpreting phrases, and synthesizing complex information, potentially aiding and even replacing humans in various areas of social interest. Some studies have compared its performance in solving medical knowledge exams with medical students and professionals to verify AI accuracy. This study aimed to measure the performance of ChatGPT in answering questions from the Progress Test from 2021 to 2023. Methodology An observational study was conducted in which questions from the 2021 Progress Test and the regional tests (Southern Institutional Pedagogical Support Center II) of 2022 and 2023 were presented to ChatGPT 3.5. The results obtained were compared with the scores of first- to sixth-year medical students from over 120 Brazilian universities. All questions were presented sequentially, without any modification to their structure. After each question was presented, the platform's history was cleared, and the site was restarted. Results The platform achieved an average accuracy rate in 2021, 2022, and 2023 of 69.7%, 68.3%, and 67.2%, respectively, surpassing students from all medical years in the three tests evaluated, reinforcing findings in the current literature. The subject with the best score for the AI was Public Health, with a mean grade of 77.8%. Conclusions ChatGPT demonstrated the ability to answer medical questions with higher accuracy than humans, including students from the last year of medical school.

Understanding Health Care Students' Perceptions, Beliefs, and Attitudes Toward AI-Powered Language Models: Cross-Sectional Study.

BACKGROUND: ChatGPT was not intended for use in health care, but it has potential benefits that depend on end-user understanding and acceptability, which is where health care students become crucial. There is still a limited amount of research in this area. OBJECTIVE: The primary aim of our study was to assess the frequency of ChatGPT use, the perceived level of knowledge, the perceived risks associated with its use, and the ethical issues, as well as attitudes toward the use of ChatGPT in the context of education in the field of health. In addition, we aimed to examine whether there were differences across groups based on demographic variables. The second part of the study aimed to assess the association between the frequency of use, the level of perceived knowledge, the level of risk perception, and the level of perception of ethics as predictive factors for participants' attitudes toward the use of ChatGPT. METHODS: A cross-sectional survey was conducted from May to June 2023 encompassing students of medicine, nursing, dentistry, nutrition, and laboratory science across the Americas. The study used descriptive analysis, chi-square tests, and ANOVA to assess statistical significance across different categories. The study used several ordinal logistic regression models to analyze the impact of predictive factors (frequency of use, perception of knowledge, perception of risk, and ethics perception scores) on attitude as the dependent variable. The models were adjusted for gender, institution type, major, and country. Stata was used to conduct all the analyses. RESULTS: Of 2661 health care students, 42.99% (n=1144) were unaware of ChatGPT. The median score of knowledge was "minimal" (median 2.00, IQR 1.00-3.00). Most respondents (median 2.61, IQR 2.11-3.11) regarded ChatGPT as neither ethical nor unethical. Most participants (median 3.89, IQR 3.44-4.34) "somewhat agreed" that ChatGPT (1) benefits health care settings, (2) provides trustworthy data, (3) is a helpful tool for clinical and educational medical information access, and (4) makes the work easier. In total, 70% (7/10) of people used it for homework. As the perceived knowledge of ChatGPT increased, there was a stronger tendency with regard to having a favorable attitude toward ChatGPT. Higher ethical consideration perception ratings increased the likelihood of considering ChatGPT as a source of trustworthy health care information (odds ratio [OR] 1.620, 95% CI 1.498-1.752), beneficial in medical issues (OR 1.495, 95% CI 1.452-1.539), and useful for medical literature (OR 1.494, 95% CI 1.426-1.564; P<.001 for all results). CONCLUSIONS: Over 40% of American health care students (1144/2661, 42.99%) were unaware of ChatGPT despite its extensive use in the health field. Our data revealed the positive attitudes toward ChatGPT and the desire to learn more about it. Medical educators must explore how chatbots may be included in undergraduate health care education programs.

Artificial neural networks as a tool for seasonal forecast of attack intensity of Spodoptera spp. in Bt soybean.

Soybean (Glycine max) is the world's most cultivated legume; currently, most of its varieties are Bt. Spodoptera spp. (Lepidoptera: Noctuidae) are important pests of soybean. An artificial neural network (ANN) is an artificial intelligence tool that can be used in the study of spatiotemporal dynamics of pest populations. Thus, this work aims to determine ANN to identify population regulation factors of Spodoptera spp. and predict its density in Bt soybean. For two years, the density of Spodoptera spp. caterpillars, predators, and parasitoids, climate data, and plant age was evaluated in commercial soybean fields. The selected ANN was the one with the weather data from 25 days before the pest's density evaluation. ANN forecasting and pest densities in soybean fields presented a correlation of 0.863. It was found that higher densities of the pest occurred in dry seasons, with less wind, higher atmospheric pressure and with increasing plant age. Pest density increased with the increase in temperature until this curve reached its maximum value. ANN forecasting and pest densities in soybean fields in different years, seasons, and stages of plant development were similar. Therefore, this ANN is promising to be implemented into integrated pest management programs in soybean fields.

Artificial Intelligence-Based Diagnosis of Obstructive Sleep Apnea Syndrome: A Scoping Review / Diagnóstico Basado en Inteligencia Artificial para el Síndrome Obstructivo de Apnea del Sueño: Una Revisión de Alcance

SUMMARY: To diagnose obstructive sleep apnea syndrome (OSAS), polysomnography is used, an expensive and extensive study requiring the patient to sleep in a laboratory. OSAS has been associated with features of facial morphology, and a preliminary diagnosis could be made using an artificial intelligence (AI) predictive model. This study aimed to analyze, using a scoping review, the AI-based technological options applied to diagnosing OSAS and the parameters evaluated in such analyses on craniofacial structures. A systematic search of the literature was carried out up to February 2024, and, using inclusion and exclusion criteria, the studies to be analyzed were determined. Titles and abstracts were independently selected by two researchers. Fourteen studies were selected, including a total of 13,293 subjects analyzed. The age of the sample ranged from 18 to 90 years. 9,912 (74.56 %) subjects were male, and 3,381 (25.43 %) were female. The included studies presented a diagnosis of OSAS by polysomnography; seven presented a control group of subjects without OSAS and another group with OSAS. The remaining studies presented OSAS groups in relation to their severity. All studies had a mean accuracy of 80 % in predicting OSAS using variables such as age, gender, measurements, and/or imaging measurements. There are no tests before diagnosis by polysomnography to guide the user in the likely presence of OSAS. In this sense, there are risk factors for developing OSA linked to facial shape, obesity, age, and other conditions, which, together with the advances in AI for diagnosis and guidance in OSAS, could be used for early detection.

Para diagnosticar el Síndrome Apnea Obstructiva del Sueño (SAOS) se utiliza la polisomnografía, el cual es un costoso y extenso estudio que exige que el paciente duerma en un laboratorio. El SAOS ha sido asociado con características de la morfología facial y mediante un modelo predictivo de la Inteligencia Artificial (IA), se podría realizar un diagnóstico preliminar. El objetivo de este estudio fue analizar por medio de una revisión de alcance, las opciones tecnológicas basadas en IA aplicadas al diagnóstico del SAOS, y los parámetros evaluados en dichos análisis en las estructuras craneofaciales. Se realizó una búsqueda sistemática de la literatura hasta febrero del 2024 y mediante criterios de inclusión y exclusión se determino los estudios a analizar. Los títulos y resúmenes fueron seleccionados de forma independiente por dos investigadores. Se seleccionaron 14 estudios, incluyeron un total de 13.293 sujetos analizados. El rango edad de la muestra oscilo entre 18 y 90 años. 9.912 (74.56 %) sujetos eran de sexo masculino y 3.381 (25,43 %) eran de sexo femenino. Los estudios incluidos presentaron diagnóstico de SAOS mediante polisomnografía, siete estudios presentaron un grupo control de sujetos con ausencia de SAOS y otro grupo con presencia de SAOS. Mientras que los demás estudios, presentaron grupos de SAOS en relación con su severidad. Todos los estudios tuvieron una precisión media del 80 % en la predicción de SAOS utilizando variables como la edad, el género, mediciones y/o mediciones imagenológicas. no existen exámenes previos al diagnóstico por polisomnografía que permitan orientar al usuario en la probable presencia de SAOS. En este sentido, existen factores de riesgo para desarrollar SAOS vinculados a la forma facial, la obesidad, la edad y otras condiciones, que sumados a los avances con IA para diagnóstico y orientación en SAOS podrían ser utilizados para la detección precoz del mismo.

O uso de sistemas de inteligência artificial para a personalização da experiência do paciente: a percepção de gestores de tecnologia e inovação de hospitais associados à ANAHP / The use of artificial intelligence systems for patient experience personalization: the perception of technology and innovation managers at hospitals associated with ANAHP

Objetivo: O presente trabalho explora a percepção de gestores das áreas de Tecnologia e Inovação de hospitais privados brasileiros acerca do uso da inteligência artificial (IA) na saúde, com foco específico na personalização da experiência do paciente nesses hospitais. Métodos: Este trabalho se caracteriza como uma pesquisa descritiva transversal quantitativa. Foi desenvolvido um questionário com 14 questões que foi distribuído a uma amostra de gestores de tecnologia e inovação em hospitais, com o apoio da Associação Nacional de Hospitais Privados (ANAHP). O questionário foi disponibilizado em versão online à base de 122 hospitais associados à ANAHP. Resultados: Foram obtidas 30 respostas completas (aproximadamente 25% da base total), conquistando percepções sobre as vantagens, desvantagens e desafios éticos e técnicos relacionados ao emprego da IA na área clínica, particularmente em ambientes hospitalares. As respostas coletadas ratificaram o otimismo e a reserva dos profissionais de tecnologia e inovação em hospitais privados quanto ao poder e aos impactos da IA na personalização da experiência do paciente, bem como indicaram a necessidade de treinamento adequado para os funcionários desses hospitais, a fim de maximizar os benefícios da IA como ferramenta de apoio à tomada de decisão. Conclusões: Este trabalho é uma fonte de consulta para instituições de saúde que considerem utilizar a IA na personalização da experiência do paciente e queiram estabelecer treinamentos de pessoal baseados nesses princípios. Desse modo, os resultados aqui obtidos oferecem orientações valiosas para a adoção plena de IA no setor de saúde.

Objective: This study explores the perception of managers in the Technology and Innovation areas of Brazilian private hospitals regarding the use of artificial intelligence (AI) in healthcare, specifically focusing on patient experience personalization in these hospitals. Methods: This study is characterized as a quantitative cross-sectional descriptive research. A questionnaire with 14 questions was developed and distributed to a sample of technology and innovation managers in hospitals, with the support of the National Association of Private Hospitals (NAPH). The questionnaire was made available online to a base of 122 hospitals associated with NAPH. Results: 30 complete responses were obtained (nearly 25% of the total base), capturing perceptions on the advantages, disadvantages, and ethical and technical challenges related to the use of AI in clinical settings, particularly in hospital environments. The collected responses affirmed the optimism and caution of technology and innovation professionals in private hospitals regarding the power and impacts of AI on patient experience personalization, and indicated the need for adequate training for employees in these hospitals to maximize the benefits of AI as a decision support tool. Conclusions: This study serves as a reference for healthcare institutions considering the use of AI in patient experience personalization and aiming to establish personnel training based on these principles. Thus, the results obtained here offer valuable guidance for the full adoption of AI in the healthcare sector.

Accurate prediction of all-cause mortality in patients with metabolic dysfunction-associated steatotic liver disease using electronic health records.

INTRODUCTION AND OBJECTIVES: Despite the huge clinical burden of MASLD, validated tools for early risk stratification are lacking, and heterogeneous disease expression and a highly variable rate of progression to clinical outcomes result in prognostic uncertainty. We aimed to investigate longitudinal electronic health record-based outcome prediction in MASLD using a state-of-the-art machine learning model. PATIENTS AND METHODS: n = 940 patients with histologically-defined MASLD were used to develop a deep-learning model for all-cause mortality prediction. Patient timelines, spanning 12 years, were fully-annotated with demographic/clinical characteristics, ICD-9 and -10 codes, blood test results, prescribing data, and secondary care activity. A Transformer neural network (TNN) was trained to output concomitant probabilities of 12-, 24-, and 36-month all-cause mortality. In-sample performance was assessed using 5-fold cross-validation. Out-of-sample performance was assessed in an independent set of n = 528 MASLD patients. RESULTS: In-sample model performance achieved AUROC curve 0.74-0.90 (95 % CI: 0.72-0.94), sensitivity 64 %-82 %, specificity 75 %-92 % and Positive Predictive Value (PPV) 94 %-98 %. Out-of-sample model validation had AUROC 0.70-0.86 (95 % CI: 0.67-0.90), sensitivity 69 %-70 %, specificity 96 %-97 % and PPV 75 %-77 %. Key predictive factors, identified using coefficients of determination, were age, presence of type 2 diabetes, and history of hospital admissions with length of stay >14 days. CONCLUSIONS: A TNN, applied to routinely-collected longitudinal electronic health records, achieved good performance in prediction of 12-, 24-, and 36-month all-cause mortality in patients with MASLD. Extrapolation of our technique to population-level data will enable scalable and accurate risk stratification to identify people most likely to benefit from anticipatory health care and personalized interventions.

Optimizing trigger timing in minimal ovarian stimulation for In Vitro fertilization using machine learning models with random search hyperparameter tuning.

Various studies have emphasized the importance of identifying the optimal Trigger Timing (TT) for the trigger shot in In Vitro Fertilization (IVF), which is crucial for the successful maturation and release of oocytes, especially in minimal ovarian stimulation treatments. Despite its significance for the ultimate success of IVF, determining the precise TT remains a complex challenge for physicians due to the involvement of multiple variables. This study aims to enhance TT by developing a machine learning multi-output model that predicts the expected number of retrieved oocytes, mature oocytes (MII), fertilized oocytes (2 PN), and useable blastocysts within a 48-h window after the trigger shot in minimal stimulation cycles. By utilizing this model, physicians can identify patients with possible early, late, or on-time trigger shots. The study found that approximately 27 % of treatments administered the trigger shot on a suboptimal day, but optimizing the TT using the developed Artificial Intelligence (AI) model can potentially increase useable blastocyst production by 46 %. These findings highlight the potential of predictive models as a supplementary tool for optimizing trigger shot timing and improving IVF outcomes, particularly in minimal ovarian stimulation. The experimental results underwent statistical validation, demonstrating the accuracy and performance of the model. Overall, this study emphasizes the value of AI prediction models in enhancing TT and making the IVF process safer and more efficient.

A 2.5D Self-Training Strategy for Carotid Artery Segmentation in T1-Weighted Brain Magnetic Resonance Images.

Precise annotations for large medical image datasets can be time-consuming. Additionally, when dealing with volumetric regions of interest, it is typical to apply segmentation techniques on 2D slices, compromising important information for accurately segmenting 3D structures. This study presents a deep learning pipeline that simultaneously tackles both challenges. Firstly, to streamline the annotation process, we employ a semi-automatic segmentation approach using bounding boxes as masks, which is less time-consuming than pixel-level delineation. Subsequently, recursive self-training is utilized to enhance annotation quality. Finally, a 2.5D segmentation technique is adopted, wherein a slice of a volumetric image is segmented using a pseudo-RGB image. The pipeline was applied to segment the carotid artery tree in T1-weighted brain magnetic resonance images. Utilizing 42 volumetric non-contrast T1-weighted brain scans from four datasets, we delineated bounding boxes around the carotid arteries in the axial slices. Pseudo-RGB images were generated from these slices, and recursive segmentation was conducted using a Res-Unet-based neural network architecture. The model's performance was tested on a separate dataset, with ground truth annotations provided by a radiologist. After recursive training, we achieved an Intersection over Union (IoU) score of (0.68 ± 0.08) on the unseen dataset, demonstrating commendable qualitative results.

Identifying and training deep learning neural networks on biomedical-related datasets.

This manuscript describes the development of a resources module that is part of a learning platform named 'NIGMS Sandbox for Cloud-based Learning' https://github.com/NIGMS/NIGMS-Sandbox. The overall genesis of the Sandbox is described in the editorial NIGMS Sandbox at the beginning of this Supplement. This module delivers learning materials on implementing deep learning algorithms for biomedical image data in an interactive format that uses appropriate cloud resources for data access and analyses. Biomedical-related datasets are widely used in both research and clinical settings, but the ability for professionally trained clinicians and researchers to interpret datasets becomes difficult as the size and breadth of these datasets increases. Artificial intelligence, and specifically deep learning neural networks, have recently become an important tool in novel biomedical research. However, use is limited due to their computational requirements and confusion regarding different neural network architectures. The goal of this learning module is to introduce types of deep learning neural networks and cover practices that are commonly used in biomedical research. This module is subdivided into four submodules that cover classification, augmentation, segmentation and regression. Each complementary submodule was written on the Google Cloud Platform and contains detailed code and explanations, as well as quizzes and challenges to facilitate user training. Overall, the goal of this learning module is to enable users to identify and integrate the correct type of neural network with their data while highlighting the ease-of-use of cloud computing for implementing neural networks. This manuscript describes the development of a resource module that is part of a learning platform named ``NIGMS Sandbox for Cloud-based Learning'' https://github.com/NIGMS/NIGMS-Sandbox. The overall genesis of the Sandbox is described in the editorial NIGMS Sandbox [1] at the beginning of this Supplement. This module delivers learning materials on the analysis of bulk and single-cell ATAC-seq data in an interactive format that uses appropriate cloud resources for data access and analyses.

Machine learning for the adsorptive removal of ciprofloxacin using sugarcane bagasse as a low-cost biosorbent: comparison of analytic, mechanistic, and neural network modeling.

Contamination with traces of pharmaceutical compounds, such as ciprofloxacin, has prompted interest in their removal via low-cost, efficient biomass-based adsorption. In this study, classical models, a mechanistic model, and a neural network model were evaluated for predicting ciprofloxacin breakthrough curves in both laboratory- and pilot scales. For the laboratory-scale (d = 2.2 cm, Co = 5 mg/L, Q = 7 mL/min, T = 18 °C) and pilot-scale (D = 4.4 cm, Co = 5 mg/L, Q = 28 mL/min, T = 18 °C) setups, the experimental adsorption capacities were 2.19 and 2.53 mg/g, respectively. The mechanistic model reproduced the breakthrough data with high accuracy on both scales (R2 > 0.4 and X2 < 0.15), and its fit was higher than conventional analytical models, namely the Clark, Modified Dose-Response, and Bohart-Adams models. The neural network model showed the highest level of agreement between predicted and experimental data with values of R2 = 0.993, X2 = 0.0032 (pilot-scale) and R2 = 0.986, X2 = 0.0022 (laboratory-scale). This study demonstrates that machine learning algorithms exhibit great potential for predicting the liquid adsorption of emerging pollutants in fixed bed.

Bayesian Networks for Prescreening in Depression: Algorithm Development and Validation.

BACKGROUND: Identifying individuals with depressive symptomatology (DS) promptly and effectively is of paramount importance for providing timely treatment. Machine learning models have shown promise in this area; however, studies often fall short in demonstrating the practical benefits of using these models and fail to provide tangible real-world applications. OBJECTIVE: This study aims to establish a novel methodology for identifying individuals likely to exhibit DS, identify the most influential features in a more explainable way via probabilistic measures, and propose tools that can be used in real-world applications. METHODS: The study used 3 data sets: PROACTIVE, the Brazilian National Health Survey (Pesquisa Nacional de Saúde [PNS]) 2013, and PNS 2019, comprising sociodemographic and health-related features. A Bayesian network was used for feature selection. Selected features were then used to train machine learning models to predict DS, operationalized as a score of ≥10 on the 9-item Patient Health Questionnaire. The study also analyzed the impact of varying sensitivity rates on the reduction of screening interviews compared to a random approach. RESULTS: The methodology allows the users to make an informed trade-off among sensitivity, specificity, and a reduction in the number of interviews. At the thresholds of 0.444, 0.412, and 0.472, determined by maximizing the Youden index, the models achieved sensitivities of 0.717, 0.741, and 0.718, and specificities of 0.644, 0.737, and 0.766 for PROACTIVE, PNS 2013, and PNS 2019, respectively. The area under the receiver operating characteristic curve was 0.736, 0.801, and 0.809 for these 3 data sets, respectively. For the PROACTIVE data set, the most influential features identified were postural balance, shortness of breath, and how old people feel they are. In the PNS 2013 data set, the features were the ability to do usual activities, chest pain, sleep problems, and chronic back problems. The PNS 2019 data set shared 3 of the most influential features with the PNS 2013 data set. However, the difference was the replacement of chronic back problems with verbal abuse. It is important to note that the features contained in the PNS data sets differ from those found in the PROACTIVE data set. An empirical analysis demonstrated that using the proposed model led to a potential reduction in screening interviews of up to 52% while maintaining a sensitivity of 0.80. CONCLUSIONS: This study developed a novel methodology for identifying individuals with DS, demonstrating the utility of using Bayesian networks to identify the most significant features. Moreover, this approach has the potential to substantially reduce the number of screening interviews while maintaining high sensitivity, thereby facilitating improved early identification and intervention strategies for individuals experiencing DS.

Performance Assessment of Universal Machine Learning Interatomic Potentials: Challenges and Directions for Materials' Surfaces.

Machine learning interatomic potentials (MLIPs) are one of the main techniques in the materials science toolbox, able to bridge ab initio accuracy with the computational efficiency of classical force fields. This allows simulations ranging from atoms, molecules, and biosystems, to solid and bulk materials, surfaces, nanomaterials, and their interfaces and complex interactions. A recent class of advanced MLIPs, which use equivariant representations and deep graph neural networks, is known as universal models. These models are proposed as foundation models suitable for any system, covering most elements from the periodic table. Current universal MLIPs (UIPs) have been trained with the largest consistent data set available nowadays. However, these are composed mostly of bulk materials' DFT calculations. In this article, we assess the universality of all openly available UIPs, namely MACE, CHGNet, and M3GNet, in a representative task of generalization: calculation of surface energies. We find that the out-of-the-box foundation models have significant shortcomings in this task, with errors correlated to the total energy of surface simulations, having an out-of-domain distance from the training data set. Our results show that while UIPs are an efficient starting point for fine-tuning specialized models, we envision the potential of increasing the coverage of the materials space toward universal training data sets for MLIPs.

Assessing the Relevance of Non-molecular Prognostic Systems for Myelodysplastic Syndrome in the Era of Next-Generation Sequencing.

Background: The Molecular International Prognostic Scoring System (IPSS-M) has improved the prediction of clinical outcomes for myelodysplastic syndromes (MDS). The Artificial Intelligence Prognostic Scoring System for MDS (AIPSS-MDS), based on classical clinical parameters, has outperformed the IPSS, revised version (IPSS-R). For the first time, we validated the IPSS-M and other molecular prognostic models and compared them with the established IPSS-R and AIPSS-MDS models using data from South American patients. Methods: Molecular and clinical data from 145 patients with MDS and 37 patients with MDS/myeloproliferative neoplasms were retrospectively analyzed. Results: Prognostic power evaluation revealed that the IPSS-M (Harrell's concordance [C]-index: 0.75, area under the receiver operating characteristic curve [AUC]: 0.68) predicted overall survival better than the European MDS (EuroMDS; C-index: 0.72, AUC: 0.68) and Munich Leukemia Laboratory (MLL) (C-index: 0.70, AUC: 0.64) models. The IPSS-M prognostic discrimination was similar to that of the AIPSS-MDS model (C-index: 0.74, AUC: 0.66) and outperformed the IPSS-R model (C-index: 0.70, AUC: 0.61). Considering simplified low- and high-risk groups for clinical management, after restratifying from IPSS-R (57% and 32%, respectively, hazard ratio [HR]: 2.8; P=0.002) to IPSS-M, 12.6% of patients were upstaged, and 5% were downstaged (HR: 2.9; P=0.001). The AIPSS-MDS recategorized 51% of the low-risk cohort as high-risk, with no patients being downstaged (HR: 5.6; P<0.001), consistent with most patients requiring disease-modifying therapy. Conclusions: The IPSS-M and AIPSS-MDS models provide more accurate survival prognoses than the IPSS-R, EuroMDS, and MLL models. The AIPSS-MDS model is a valid option for assessing risks for all patients with MDS, especially in resource-limited centers where molecular testing is not currently a standard clinical practice.

The Advent of Artificial Intelligence into Cardiac Surgery: A Systematic Review of Our Understanding.

When faced with questions about artificial intelligence (AI), many surgeons respond with scepticism and rejection. However, in the realm of cardiac surgery, it is imperative that we embrace the potential of AI and adopt a proactive mindset. This systematic review utilizes PubMed® to explore the intersection of AI and cardiac surgery since 2017. AI has found applications in various aspects of cardiac surgery, including teaching aids, diagnostics, predictive outcomes, surgical assistance, and expertise. Nevertheless, challenges such as data computation errors, vulnerabilities to malware, and privacy concerns persist. While AI has limitations, its restricted capabilities without cognitive and emotional intelligence should lead us to cautiously and partially embrace this advancing technology to enhance patient care.