Hasil untuk "Medical emergencies. Critical care. Intensive care. First aid"

Fatih Cemal Tekin, Mehmet Gül

Charles W. LeNeave, Brian Meier, Heather Liffert et al.

Max Sunog, Colin Magdamo, Marie-Laure Charpignon et al.

Missing data, inaccuracies in medication lists, and recording delays in electronic health records (EHR) are major limitations for target trial emulation (TTE), the process by which EHR data are used to retrospectively emulate a randomized control trial. EHR TTE relies on recorded data that proxy true drug exposures and outcomes. We investigate the under-utilized criterion that a patient has indications of primary care provider (PCP) encounters within the EHR. Such patients tend to have more records overall and a greater proportion of the types of encounters that materialize comprehensive and up-to-date records. We examine the impact of including a PCP feature in the TTE model or as an eligibility criterion for cohort selection, contrasted with ignoring it altogether. To that end, we compare the estimated effects of two first line antidiabetic drug classes on the onset of Alzheimer's Disease and Related Dementias (ADRD). We find that the estimated treatment effect is sensitive to the consideration of a PCP feature, particularly when used as an eligibility criterion. Our work suggests that this PCP feature should be further researched.

Artem Goncharov, Rajesh Ghosh, Hyou-Arm Joung et al.

Computational point-of-care (POC) sensors enable rapid, low-cost, and accessible diagnostics in emergency, remote and resource-limited areas that lack access to centralized medical facilities. These systems can utilize neural network-based algorithms to accurately infer a diagnosis from the signals generated by rapid diagnostic tests or sensors. However, neural network-based diagnostic models are subject to hallucinations and can produce erroneous predictions, posing a risk of misdiagnosis and inaccurate clinical decisions. To address this challenge, here we present an autonomous uncertainty quantification technique developed for POC diagnostics. As our testbed, we used a paper-based, computational vertical flow assay (xVFA) platform developed for rapid POC diagnosis of Lyme disease, the most prevalent tick-borne disease globally. The xVFA platform integrates a disposable paper-based assay, a handheld optical reader and a neural network-based inference algorithm, providing rapid and cost-effective Lyme disease diagnostics in under 20 min using only 20 uL of patient serum. By incorporating a Monte Carlo dropout (MCDO)-based uncertainty quantification approach into the diagnostics pipeline, we identified and excluded erroneous predictions with high uncertainty, significantly improving the sensitivity and reliability of the xVFA in an autonomous manner, without access to the ground truth diagnostic information of patients. Blinded testing using new patient samples demonstrated an increase in diagnostic sensitivity from 88.2% to 95.7%, indicating the effectiveness of MCDO-based uncertainty quantification in enhancing the robustness of neural network-driven computational POC sensing systems.

Yue Wu, Xiaolan Chen, Weiyi Zhang et al.

Large language models (LLMs) show promise for tailored healthcare communication but face challenges in interpretability and multi-task integration particularly for domain-specific needs like myopia, and their real-world effectiveness as patient education tools has yet to be demonstrated. Here, we introduce ChatMyopia, an LLM-based AI agent designed to address text and image-based inquiries related to myopia. To achieve this, ChatMyopia integrates an image classification tool and a retrieval-augmented knowledge base built from literature, expert consensus, and clinical guidelines. Myopic maculopathy grading task, single question examination and human evaluations validated its ability to deliver personalized, accurate, and safe responses to myopia-related inquiries with high scalability and interpretability. In a randomized controlled trial (n=70, NCT06607822), ChatMyopia significantly improved patient satisfaction compared to traditional leaflets, enhancing patient education in accuracy, empathy, disease awareness, and patient-eyecare practitioner communication. These findings highlight ChatMyopia's potential as a valuable supplement to enhance patient education and improve satisfaction with medical services in primary eye care settings.

Yuto Yokoi, Kazuhiro Hotta

We propose two novel loss functions, Multiplicative Loss and Confidence-Adaptive Multiplicative Loss, for semantic segmentation in medical and cellular images. Although Cross Entropy and Dice Loss are widely used, their additive combination is sensitive to hyperparameters and often performs suboptimally, especially with limited data. Medical images suffer from data scarcity due to privacy, ethics, and costly annotations, requiring robust and efficient training objectives. Our Multiplicative Loss combines Cross Entropy and Dice losses multiplicatively, dynamically modulating gradients based on prediction confidence. This reduces penalties for confident correct predictions and amplifies gradients for incorrect overconfident ones, stabilizing optimization. Building on this, Confidence-Adaptive Multiplicative Loss applies a confidence-driven exponential scaling inspired by Focal Loss, integrating predicted probabilities and Dice coefficients to emphasize difficult samples. This enhances learning under extreme data scarcity by strengthening gradients when confidence is low. Experiments on cellular and medical segmentation benchmarks show our framework consistently outperforms tuned additive and existing loss functions, offering a simple, effective, and hyperparameter-free mechanism for robust segmentation under challenging data limitations.

M. Cesari, Marco Proietti

TheWorld Health Organization declared the COVID-19 situation as a pandemic onMarch 11, 2020.1 To date, Italy is the country after China that has beenmost severely hit by this humanitarian and public health tsunami. Projections are even suggesting that the number of deaths due to SARS-CoV-2 in Italy will continue to increase in the near future, leaving us the sad world record of casualties. What has happened in Italy during these last few weeks? On February 22, a “red zone” was defined by the government to quarantine a group of several towns in the Lombardy region, just a few hours after the diagnosis of the first case in Italy. This area, where about 50,000 persons live, included Codogno (where patient 1 was identified), Castiglione D’Adda, and Casalpusterlengo. On March 8, the red zone was extended to the entire region of Lombardy (about 10 million people) and several surrounding provinces in a new attempt to prevent the uncontrolled diffusion of the virus to the rest of the country. The following day, the entire country was transformed into a “red zone.” OnMarch 21, a complete lockdown of Italy was ordered by the government as a drastic and unprecedented countermeasure against the coronavirus. Behind this story of the Italian crisis is the drama of a health care system close to collapse. The exponential increase of patients admitted to emergency departments with fever and/or respiratory symptoms resembled themountingwave of a tsunami. It soon became evident how inadequate the availability of beds was to face the continuous flow of patients. The situationwas aggravated by the need to isolate patients with COVID-19, given the high contagiousness of the virus. At the same time, intensive care units started to saturate, and the number of devices for ventilating patients suddenly appeared insufficient to address the growing demand. Furthermore, health care professionals started falling sick (sometimes even dying) as consequence of their untiringwillingness to serve the community, as well as the infrastructural unpreparedness for the enormity of the outbreak. Our world was completely subverted by the emergency. No plans or protocols had the time to be tested and verified, at least on a large scale. The rapidity of the evolving scenario made it necessary to adopt easy and pragmatic solutions even for critical and delicate matters. Not surprisingly, the usual, despicable age criterion started to be

A. D. Bocharnikov, E. A. Boeva, M. A. Milovanova et al.

The aim of the study was to compare the effect of sevoflurane and chloral hydrate on the neurological status and volume of brain damage after trauma and ischemia in experimental models of traumatic brain injury (TBI) and focal ischemic stroke (IS) induced by photothrombosis (PT).Materials and methods. The experiments were performed on mongrel Wistar rats weighing 250–300 g (N=43). There were 4 groups: the Ischemia + Sevoflurane group (ISSEV) (N=10), the Ischemia + Chloral hydrate group (ISCH) (N=10), TBI + Sevoflurane group (TBISEV) (N=13), and TBI+Chloral hydrate group (TBICH) (N=10). Ischemic brain damage was modelled using Rose Bengal (RB) dye-induced PT, and TBI was modelled using mechanical force-induced concussion.Results. MRI findings indicate lower volumes of brain damage (mm³) in rats from TBISEV group compared with the TBICH group (19±5 vs. 60±5, P<0.0001), and in the ISSEV group compared with the ISCH group (9.8±1.5 vs. 21.5±2, P=0.0016). Moreover, there was a significant difference between ISSEV and ISCH groups based on the protocol assessment of neurological status on day 14 with higher scores in ISSEV (11.4±1.8 vs. 4.9±2.6, P<0.0001).Conclusion. Taking into account the data obtained, we recommend a careful choice of anesthesia when modeling ischemic stroke and traumatic brain injury in animals. In particular, the neuroprotective effect of sevoflurane should be taken into account in the PT and TBI models.

Ahmad, A.I.1*,Suleiman, A.I.1, Dauda, E.S.1, Ogara, H.1, Obadaki, I.A.1, Salihu, O.A.1, Obansa U.O.2

Garlic (Allium sativum), Ginger (Zingiber officinale) and Turmeric (Curcuma longa) have acquired a reputation in different traditions as prophylactic as well as therapeutic medicinal plants. The aim of the study was to unravel the effects of ethanol extracts of each of the spices on selected haematological parameters in Wistar Rats. Standard methods for analysis were used for this study. A total of 45 male Wistar rats were used in this study with 15 Wistar rats in three groups. Group I served as the control and the rest as test groups. The rats in Group II received 100 mg/kg BW and Group III received 200 mg/kg BW) of the sample extract for 21 days. Results obtained revealed that rats fed with ethanol extracts (100 mg/kg BW and 200 mg/kg BW) of garlic, ginger, and turmeric had a significantly (p<0.05) increased PCV, Hb and WBC as well as a significant (p < 0.05) reduction in the platelet levels in the test groups when compared to the control respectively. The significant increase in PCV, Hb, and WBC levels confirmed the anti-anaemic and anti-infection properties of garlic, ginger, and turmeric, while the significant decrease in the platelet levels indicated their anti-coagulating potentials.

Birger Moell

Background: Rapid advancements in natural language processing have led to the development of large language models with the potential to revolutionize mental health care. These models have shown promise in assisting clinicians and providing support to individuals experiencing various psychological challenges. Objective: This study aims to compare the performance of two large language models, GPT-4 and Chat-GPT, in responding to a set of 18 psychological prompts, to assess their potential applicability in mental health care settings. Methods: A blind methodology was employed, with a clinical psychologist evaluating the models' responses without knowledge of their origins. The prompts encompassed a diverse range of mental health topics, including depression, anxiety, and trauma, to ensure a comprehensive assessment. Results: The results demonstrated a significant difference in performance between the two models (p > 0.05). GPT-4 achieved an average rating of 8.29 out of 10, while Chat-GPT received an average rating of 6.52. The clinical psychologist's evaluation suggested that GPT-4 was more effective at generating clinically relevant and empathetic responses, thereby providing better support and guidance to potential users. Conclusions: This study contributes to the growing body of literature on the applicability of large language models in mental health care settings. The findings underscore the importance of continued research and development in the field to optimize these models for clinical use. Further investigation is necessary to understand the specific factors underlying the performance differences between the two models and to explore their generalizability across various populations and mental health conditions.

Xichen Xu, Wentao Chen, Weimin Zhou

Medical imaging systems that are designed for producing diagnostically informative images should be objectively assessed via task-based measures of image quality (IQ). Ideally, computation of task-based measures of IQ needs to account for all sources of randomness in the measurement data, including the variability in the ensemble of objects to be imaged. To address this need, stochastic object models (SOMs) that can generate an ensemble of synthesized objects or phantoms can be employed. Various mathematical SOMs or phantoms were developed that can interpretably synthesize objects, such as lumpy object models and parameterized torso phantoms. However, such SOMs that are purely mathematically defined may not be able to comprehensively capture realistic object variations. To establish realistic SOMs, it is desirable to use experimental data. An augmented generative adversarial network (GAN), AmbientGAN, was recently proposed for establishing SOMs from medical imaging measurements. However, it remains unclear to which extent the AmbientGAN-produced objects can be interpretably controlled. This work introduces a novel approach called AmbientCycleGAN that translates mathematical SOMs to realistic SOMs by use of noisy measurement data. Numerical studies that consider clustered lumpy background (CLB) models and real mammograms are conducted. It is demonstrated that our proposed method can stably establish SOMs based on mathematical models and noisy measurement data. Moreover, the ability of the proposed AmbientCycleGAN to interpretably control image features in the synthesized objects is investigated.

Adrit Rao, Andrea Fisher, Ken Chang et al.

Data augmentations are widely used in training medical image deep learning models to increase the diversity and size of sparse datasets. However, commonly used augmentation techniques can result in loss of clinically relevant information from medical images, leading to incorrect predictions at inference time. We propose the Interactive Medical Image Learning (IMIL) framework, a novel approach for improving the training of medical image analysis algorithms that enables clinician-guided intermediate training data augmentations on misprediction outliers, focusing the algorithm on relevant visual information. To prevent the model from using irrelevant features during training, IMIL will 'blackout' clinician-designated irrelevant regions and replace the original images with the augmented samples. This ensures that for originally mispredicted samples, the algorithm subsequently attends only to relevant regions and correctly correlates them with the respective diagnosis. We validate the efficacy of IMIL using radiology residents and compare its performance to state-of-the-art data augmentations. A 4.2% improvement in accuracy over ResNet-50 was observed when using IMIL on only 4% of the training set. Our study demonstrates the utility of clinician-guided interactive training to achieve meaningful data augmentations for medical image analysis algorithms.

Yoshie Noji, Satoki Inoue, Kazuhiro Watanabe

Gülçin Hilal Alay, Derful Gülen, Alev Öztaş et al.

Objective:Due to the anatomical, physiological, and immunological changes associated with pregnancy, pregnant women are a population at risk of coronavirus disease-2019 (COVID-19) disease-related morbidity and mortality. There aren’t enough studies on the conditions of pregnant and puerperal women who are being followed up in intensive care. The goal of this study was to determine if there was a link between variant status, vaccination status, and mortality in pregnant and puerperal women who were monitored in the intensive care unit during the transition from the alpha to the delta variation.Materials and Methods:The study was designed as a 6-month prospective observational study that occurred between August 1, 2021, and February 1, 2022. Age, present comorbidities, vaccination status, gravida, parity, gestational age (for pregnant women), variant status, birth style (cesarean section or normal delivery), and COVID-19 medical therapies in the critical care unit were all recorded.Results:During the observation period, forty patients were enrolled in the study. The patients average age was 30.9±5.2. The pregnant patients’ median gestational week was 32 weeks and 2 days. While 30 of the patients had no concomitant conditions, two had gestational diabetes, four had hypothyroidism, three had chronic hypertension, and one had Wilson’s disease. In 37.5% of the patients, intubation was required. During the follow-up in intensive care, ten individuals died. The patients in the intensive care unit spent an average of 12.1±11.8 days there. While 7 (19.4%) of the 36 patients with alpha variants died, 3 (75%) of the 4 patients with delta variants died, a statistically significant difference (p=0.042).Conclusion:In the pregnant population admitted to the intensive care unit, the delta variant was associated with a greater mortality rate. In our research, we discovered that the vaccination rate among pregnant women admitted to the intensive care unit was quite low.

Jin Zhu, Guang Yang, Pietro Lio

Super-resolution plays an essential role in medical imaging because it provides an alternative way to achieve high spatial resolutions and image quality with no extra acquisition costs. In the past few decades, the rapid development of deep neural networks has promoted super-resolution performance with novel network architectures, loss functions and evaluation metrics. Specifically, vision transformers dominate a broad range of computer vision tasks, but challenges still exist when applying them to low-level medical image processing tasks. This paper proposes an efficient vision transformer with residual dense connections and local feature fusion to achieve efficient single-image super-resolution (SISR) of medical modalities. Moreover, we implement a general-purpose perceptual loss with manual control for image quality improvements of desired aspects by incorporating prior knowledge of medical image segmentation. Compared with state-of-the-art methods on four public medical image datasets, the proposed method achieves the best PSNR scores of 6 modalities among seven modalities. It leads to an average improvement of $+0.09$ dB PSNR with only 38\% parameters of SwinIR. On the other hand, the segmentation-based perceptual loss increases $+0.14$ dB PSNR on average for SOTA methods, including CNNs and vision transformers. Additionally, we conduct comprehensive ablation studies to discuss potential factors for the superior performance of vision transformers over CNNs and the impacts of network and loss function components. The code will be released on GitHub with the paper published.

Jannatul Nayem, Sayed Sahriar Hasan, Noshin Amina et al.

Deep learning becomes an elevated context regarding disposing of many machine learning tasks and has shown a breakthrough upliftment to extract features from unstructured data. Though this flourishing context is developing in the medical image processing sector, scarcity of problem-dependent training data has become a larger issue in the way of easy application of deep learning in the medical sector. To unravel the confined data source, researchers have developed a model that can solve machine learning problems with fewer data called ``Few shot learning". Few hot learning algorithms determine to solve the data limitation problems by extracting the characteristics from a small dataset through classification and segmentation methods. In the medical sector, there is frequently a shortage of available datasets in respect of some confidential diseases. Therefore, Few shot learning gets the limelight in this data scarcity sector. In this chapter, the background and basic overview of a few shots of learning is represented. Henceforth, the classification of few-shot learning is described also. Even the paper shows a comparison of methodological approaches that are applied in medical image analysis over time. The current advancement in the implementation of few-shot learning concerning medical imaging is illustrated. The future scope of this domain in the medical imaging sector is further described.

Weipeng Zhou, Danielle Bitterman, Majid Afshar et al.

Large language models (LLMs) like ChatGPT have excited scientists across fields; in medicine, one source of excitement is the potential applications of LLMs trained on electronic health record (EHR) data. But there are tough questions we must first answer if health care institutions are interested in having LLMs trained on their own data; should they train an LLM from scratch or fine-tune it from an open-source model? For healthcare institutions with a predefined budget, what are the biggest LLMs they can afford? In this study, we take steps towards answering these questions with an analysis on dataset sizes, model sizes, and costs for LLM training using EHR data. This analysis provides a framework for thinking about these questions in terms of data scale, compute scale, and training budgets.

Robinson Onyemechi Oturugbum

Daily, massive volume of data are produced due to the internet of things' rapid development, which has now permeated the healthcare industry. Recent advances in data mining have spawned a new field of a study dubbed privacy-preserving data mining (PPDM). PPDM technique or approach enables the extraction of actionable insight from enormous volume of data while safeguarding the privacy of individual information and benefiting the entire society Medical research has taken a new course as a result of data mining with healthcare data to detect diseases earlier and improve patient care. Data integration necessitates the sharing of sensitive patient information. However, substantial privacy issues are raised in connection with the storage and transmission of potentially sensitive information. Disclosing sensitive information infringes on patients' privacy. This paper aims to conduct a review of related work on privacy-preserving mechanisms, data protection regulations, and mitigating tactics. The review concluded that no single strategy outperforms all others. Hence, future research should focus on adequate techniques for privacy solutions in the age of massive medical data and the standardization of evaluation standards.

Robert Hahn, Rui He, Yuhong Li

Maria Loreto, Massimo Pisanti, Marco Celentani et al.

Abstract Background We carry out a retrospective observational analysis of clinical records of patients with major placenta praevia who underwent cesarean section surgery over a period of 20 months in our hospital. Out of a total of 40 patients, 20 were subjected to Goal-Directed Therapy (GDT) implemented with non-invasive hemodynamic monitoring using the EV1000 ClearSight system (Group I) and 20 to standard hemodynamic monitoring (Group II). Given the risk of conspicuous blood loss, this study evaluate the impact on maternal and fetal health of GDT relative to standard hemodynamic monitoring. Results Average total infusion of fluids was 1600 +/− 350 ml. Use of blood products occurred in 29 patients (72,5%), of which 11 had a hysterectomy and 8 were treated with Bakri Balloons. For 2 patients > 1000 mL of concentrated red blood cells were used. When stroke volume index SVI dropped below 35 mL/m2/beat, it responded well to the infusion of at least 2 crystalloid boluses (5 ml/kg) in 7 patients. Cardiac index (CI) increased in 8 patients in concomitance with a reduction in medium arterial pressure (MAP), but the use of ephedrine (10 mg iv) re-established acceptable baseline values. Group I means are higher than Group II means for MAP, lower for RBC usage, end-of-surgery maternal lactates and fetal pH, and for LOS. Statistical analysis determines that the null hypotheses of equalities between Groups I and II can be rejected for all measures apart from MAP at baseline and induction. Proportions of serious complications in Groups I and II are respectively 10% and 32% and Boschloo’s test rejects the null of equality of proportions against the alternative hypothesis of lower proportion of occurrence in Group I than in Group II. Conclusions Hypovolemia can lead to vasoconstriction and inadequate perfusion with decreased oxygen delivery to organs and peripheral tissues and ultimately cause organ dysfunction. Despite the small sample size due to the rarity of the pathology, our statistical analysis finds evidence in favor of more favorable clinical outcomes for patients who received GDT implemented with non-invasive hemodynamic monitoring infusion relative to patients who received standard hemodynamic monitoring.