BACKGROUND: The escalating global prevalence of obesity has necessitated the exploration of novel diagnostic approaches. Recent scientific inquiries have indicated potential alterations in voice characteristics associated with obesity, suggesting the feasibility of using voice as a noninvasive biomarker for obesity detection.
OBJECTIVE: This study aims to use deep neural networks to predict obesity status through the analysis of short audio recordings, investigating the relationship between vocal characteristics and obesity.
METHODS: A pilot study was conducted with 696 participants, using self-reported BMI to classify individuals into obesity and nonobesity groups. Audio recordings of participants reading a short script were transformed into spectrograms and analyzed using an adapted YOLOv8 model (Ultralytics). The model performance was evaluated using accuracy, recall, precision, and F1-scores.
RESULTS: The adapted YOLOv8 model demonstrated a global accuracy of 0.70 and a macro F1-score of 0.65. It was more effective in identifying nonobesity (F1-score of 0.77) than obesity (F1-score of 0.53). This moderate level of accuracy highlights the potential and challenges in using vocal biomarkers for obesity detection.
CONCLUSIONS: While the study shows promise in the field of voice-based medical diagnostics for obesity, it faces limitations such as reliance on self-reported BMI data and a small, homogenous sample size. These factors, coupled with variability in recording quality, necessitate further research with more robust methodologies and diverse samples to enhance the validity of this novel approach. The findings lay a foundational step for future investigations in using voice as a noninvasive biomarker for obesity detection.

BACKGROUND: Early warning score systems are widely used for identifying patients who are at the highest risk of deterioration to assist clinical decision-making. This could facilitate early intervention and consequently improve patient outcomes; for example, the National Early Warning Score (NEWS) system, which is recommended by the Royal College of Physicians in the United Kingdom, uses predefined alerting thresholds to assign scores to patients based on their vital signs. However, there is limited evidence of the reliability of such scores across patient cohorts in the United Arab Emirates.
OBJECTIVE: Our aim in this study was to propose a data-driven model that accurately predicts in-hospital deterioration in an inpatient cohort in the United Arab Emirates.
METHODS: We conducted a retrospective cohort study using a real-world data set that consisted of 16,901 unique patients associated with 26,073 inpatient emergency encounters and 951,591 observation sets collected between April 2015 and August 2021 at a large multispecialty hospital in Abu Dhabi, United Arab Emirates. The observation sets included routine measurements of heart rate, respiratory rate, systolic blood pressure, level of consciousness, temperature, and oxygen saturation, as well as whether the patient was receiving supplementary oxygen. We divided the data set of 16,901 unique patients into training, validation, and test sets consisting of 11,830 (70%; 18,319/26,073, 70.26% emergency encounters), 3397 (20.1%; 5206/26,073, 19.97% emergency encounters), and 1674 (9.9%; 2548/26,073, 9.77% emergency encounters) patients, respectively. We defined an adverse event as the occurrence of admission to the intensive care unit, mortality, or both if the patient was admitted to the intensive care unit first. On the basis of 7 routine vital signs measurements, we assessed the performance of the NEWS system in detecting deterioration within 24 hours using the area under the receiver operating characteristic curve (AUROC). We also developed and evaluated several machine learning models, including logistic regression, a gradient-boosting model, and a feed-forward neural network.
RESULTS: In a holdout test set of 2548 encounters with 95,755 observation sets, the NEWS system achieved an overall AUROC value of 0.682 (95% CI 0.673-0.690). In comparison, the best-performing machine learning models, which were the gradient-boosting model and the neural network, achieved AUROC values of 0.778 (95% CI 0.770-0.785) and 0.756 (95% CI 0.749-0.764), respectively. Our interpretability results highlight the importance of temperature and respiratory rate in predicting patient deterioration.
CONCLUSIONS: Although traditional early warning score systems are the dominant form of deterioration prediction models in clinical practice today, we strongly recommend the development and use of cohort-specific machine learning models as an alternative. This is especially important in external patient cohorts that were unseen during model development.

UNASSIGNED: Benign prostatic hyperplasia (BPH) is the most common benign disease causing voiding dysfunction in middle-aged and elderly men. the current \"gold standard\" for surgical treatment is transurethral resection of the prostate (TURP). Continuous bladder irrigation (CBI) is routinely given for 3 to 5 days after operation. However, this may induce bladder spasm. Bladder spasm not only brings physical and mental pain to patients, delaying the postoperative recovery process, but it also increases the medical economic burden. Therefore, it is important to take active measures to effectively warn and deal with bladder spasm. The color of the drainage fluid is an important indicator and requires close observation during CBI, as it can reflect real-time postoperative bleeding. When the color of drainage fluid is abnormal, effective measures should be undertaken. Grading nursing intervention divides patients into different conditions according to their possible changes, and then recommends targeted nursing intervention. Existing studies have formulated CBI programs from the perspective of quantifying the relationship between drainage fluid color and irrigation speed, but have yet to incorporate bladder spasm prevention and control levels or design corresponding grading nursing intervention programs according to different drainage fluid colors. This study aimed to construct the risk warning classification and intervention plan of bladder spasm under the guidance of CBI speed adjusting card after TURP.
UNASSIGNED: Based on the rate adjustment card of CBI after TURP, we formulated the first draft of an early warning classification of risk in bladder spasm and its intervention plans by combining methods suggested from a literature search with semi-structured interviews and results from 2 rounds of correspondence inquiries with 28 experts by the Delphi method. We further screened and revised grading standards and measures.
UNASSIGNED: The positive coefficients of experts in 2 rounds of correspondence inquiries were both 100%, the authority coefficients were both 0.952, and the Kendall harmony coefficients were 0.238 and 0.326, respectively (P<0.01). In the second round of correspondence inquiries, the coefficient of variation of expert opinions was 0.000-0.154, and the coefficient of variation of all items was <0.25. Finally, a 3-level risk warning classification standard and 23 nursing measures for CBI complicated by bladder spasm was constructed.
UNASSIGNED: The early warning classification of risk in bladder spasm and its intervention plans guided by rate adjustment card of CBI after TURP are scientific and feasible, and can provide a basis and guidance for effective and standardized CBI in patients after TURP.

BACKGROUND: Mentalization, which is integral to human cognitive processes, pertains to the interpretation of one\'s own and others\' mental states, including emotions, beliefs, and intentions. With the advent of artificial intelligence (AI) and the prominence of large language models in mental health applications, questions persist about their aptitude in emotional comprehension. The prior iteration of the large language model from OpenAI, ChatGPT-3.5, demonstrated an advanced capacity to interpret emotions from textual data, surpassing human benchmarks. Given the introduction of ChatGPT-4, with its enhanced visual processing capabilities, and considering Google Bard\'s existing visual functionalities, a rigorous assessment of their proficiency in visual mentalizing is warranted.
OBJECTIVE: The aim of the research was to critically evaluate the capabilities of ChatGPT-4 and Google Bard with regard to their competence in discerning visual mentalizing indicators as contrasted with their textual-based mentalizing abilities.
METHODS: The Reading the Mind in the Eyes Test developed by Baron-Cohen and colleagues was used to assess the models\' proficiency in interpreting visual emotional indicators. Simultaneously, the Levels of Emotional Awareness Scale was used to evaluate the large language models\' aptitude in textual mentalizing. Collating data from both tests provided a holistic view of the mentalizing capabilities of ChatGPT-4 and Bard.
RESULTS: ChatGPT-4, displaying a pronounced ability in emotion recognition, secured scores of 26 and 27 in 2 distinct evaluations, significantly deviating from a random response paradigm (P<.001). These scores align with established benchmarks from the broader human demographic. Notably, ChatGPT-4 exhibited consistent responses, with no discernible biases pertaining to the sex of the model or the nature of the emotion. In contrast, Google Bard\'s performance aligned with random response patterns, securing scores of 10 and 12 and rendering further detailed analysis redundant. In the domain of textual analysis, both ChatGPT and Bard surpassed established benchmarks from the general population, with their performances being remarkably congruent.
CONCLUSIONS: ChatGPT-4 proved its efficacy in the domain of visual mentalizing, aligning closely with human performance standards. Although both models displayed commendable acumen in textual emotion interpretation, Bard\'s capabilities in visual emotion interpretation necessitate further scrutiny and potential refinement. This study stresses the criticality of ethical AI development for emotional recognition, highlighting the need for inclusive data, collaboration with patients and mental health experts, and stringent governmental oversight to ensure transparency and protect patient privacy.

BACKGROUND: This study evaluated an early warning, alert and response system for a crisis-affected population in Doolo zone, Somali Region, Ethiopia, in 2019-2021, with a history of epidemics of outbreak-prone diseases. To adequately cover an area populated by a semi-nomadic pastoralist, or livestock herding, population with sparse access to healthcare facilities, the surveillance system included four components: health facility indicator-based surveillance, community indicator- and event-based surveillance, and alerts from other actors in the area. This evaluation described the usefulness, acceptability, completeness, timeliness, positive predictive value, and representativeness of these components.
METHODS: We carried out a mixed-methods study retrospectively analysing data from the surveillance system February 2019-January 2021 along with key informant interviews with system implementers, and focus group discussions with local communities. Transcripts were analyzed using a mixed deductive and inductive approach. Surveillance quality indicators assessed included completeness, timeliness, and positive predictive value, among others.
RESULTS: 1010 signals were analysed; these resulted in 168 verified events, 58 alerts, and 29 responses. Most of the alerts (46/58) and responses (22/29) were initiated through the community event-based branch of the surveillance system. In comparison, one alert and one response was initiated via the community indicator-based branch. Positive predictive value of signals received was about 6%. About 80% of signals were verified within 24 h of reports, and 40% were risk assessed within 48 h. System responses included new mobile clinic sites, measles vaccination catch-ups, and water and sanitation-related interventions. Focus group discussions emphasized that responses generated were an expected return by participant communities for their role in data collection and reporting. Participant communities found the system acceptable when it led to the responses they expected. Some event types, such as those around animal health, led to the community\'s response expectations not being met.
CONCLUSIONS: Event-based surveillance can produce useful data for localized public health action for pastoralist populations. Improvements could include greater community involvement in the system design and potentially incorporating One Health approaches.

The high Arctic is considered a pristine environment compared with many other regions in the northern hemisphere. It is becoming increasingly vulnerable to invasion by invasive alien species (IAS), however, as climate change leads to rapid loss of sea ice, changes in ocean temperature and salinity, and enhanced human activities. These changes are likely to increase the incidence of arrival and the potential for establishment of IAS in the region. To predict the impact of IAS, a group of experts in taxonomy, invasion biology and Arctic ecology carried out a horizon scanning exercise using the Svalbard archipelago as a case study, to identify the species that present the highest risk to biodiversity, human health and the economy within the next 10 years. A total of 114 species, currently absent from Svalbard, recorded once and/or identified only from environmental DNA samples, were initially identified as relevant for review. Seven species were found to present a high invasion risk and to potentially cause a significant negative impact on biodiversity and five species had the potential to have an economic impact on Svalbard. Decapod crabs, ascidians and barnacles dominated the list of highest risk marine IAS. Potential pathways of invasion were also researched, the most common were found associated with vessel traffic. We recommend (i) use of this approach as a key tool within the application of biosecurity measures in the wider high Arctic, (ii) the addition of this tool to early warning systems for strengthening existing surveillance measures; and (iii) that this approach is used to identify high-risk terrestrial and freshwater IAS to understand the overall threat facing the high Arctic. Without the application of biosecurity measures, including horizon scanning, there is a greater risk that marine IAS invasions will increase, leading to unforeseen changes in the environment and economy of the high Arctic.

Influenza outbreaks pose a significant threat to global public health. Traditional surveillance systems and simple algorithms often struggle to predict influenza outbreaks in an accurate and timely manner. Big data and modern technology have offered new modalities for disease surveillance and prediction. Influenza-like illness can serve as a valuable surveillance tool for emerging respiratory infectious diseases like influenza and COVID-19, especially when reported case data may not fully reflect the actual epidemic curve.
This study aimed to develop a predictive model for influenza outbreaks by combining Baidu search query data with traditional virological surveillance data. The goal was to improve early detection and preparedness for influenza outbreaks in both northern and southern China, providing evidence for supplementing modern intelligence epidemic surveillance methods.
We collected virological data from the National Influenza Surveillance Network and Baidu search query data from January 2011 to July 2018, totaling 3,691,865 and 1,563,361 respective samples. Relevant search terms related to influenza were identified and analyzed for their correlation with influenza-positive rates using Pearson correlation analysis. A distributed lag nonlinear model was used to assess the lag correlation of the search terms with influenza activity. Subsequently, a predictive model based on the gated recurrent unit and multiple attention mechanisms was developed to forecast the influenza-positive trend.
This study revealed a high correlation between specific Baidu search terms and influenza-positive rates in both northern and southern China, except for 1 term. The search terms were categorized into 4 groups: essential facts on influenza, influenza symptoms, influenza treatment and medicine, and influenza prevention, all of which showed correlation with the influenza-positive rate. The influenza prevention and influenza symptom groups had a lag correlation of 1.4-3.2 and 5.0-8.0 days, respectively. The Baidu search terms could help predict the influenza-positive rate 14-22 days in advance in southern China but interfered with influenza surveillance in northern China.
Complementing traditional disease surveillance systems with information from web-based data sources can aid in detecting warning signs of influenza outbreaks earlier. However, supplementation of modern surveillance with search engine information should be approached cautiously. This approach provides valuable insights for digital epidemiology and has the potential for broader application in respiratory infectious disease surveillance. Further research should explore the optimization and customization of search terms for different regions and languages to improve the accuracy of influenza prediction models.

OBJECTIVE: The world is experiencing increasing threats from infectious diseases and environmental hazards. Integration of disease surveillance systems has been put forth as one way to ensure more timely analysis of data and response. This study sought to explore the current context and state of integration of disease surveillance in England, including the barriers and facilitators to integration, as well as opportunities for improvement.
METHODS: Qualitative study with focus groups and key informant interviews.
METHODS: Focus group discussions (FGDs) and key informant interviews (KIIs) were conducted with key national, regional, and local stakeholders involved in surveillance activities in August and September 2022. These discussions and interviews were recorded, transcribed, and coded using a within-case content and thematic analysis.
RESULTS: In total, five FGDs and 10 KIIs were conducted with 27 participants. Participants had different views on what integration is, though mostly agreed that surveillance systems in England are not integrated. Lack of standardisation, governance and oversight, and structural and financial barriers were hindering the current system from being more integrated. The additional benefits of integration above and beyond the \'status quo\' during response activities were questioned by some.
CONCLUSIONS: England does not have a single integrated disease surveillance system but has a range of disease-specific surveillance systems that have evolved largely independently to meet operational needs. Greater integration may be desired and to a certain extent is important, but it is essential that it is understood as a means to an end and the overall purpose of surveillance is kept in mind.

UNASSIGNED: Human mobility and climate conditions are recognised key drivers of dengue transmission, but their combined and individual role in the local spatiotemporal clustering of dengue cases is not well understood. This study investigated the effects of human mobility and weather conditions on dengue risk in an urban area in Yogyakarta, Indonesia.
UNASSIGNED: We established a Bayesian spatiotemporal model for neighbourhood outbreak prediction and evaluated the performances of two different approaches for constructing an adjacency matrix: one based on geographical proximity and the other based on human mobility patterns. We used population, weather conditions, and past dengue cases as predictors using a flexible distributed lag approach. The human mobility data were estimated based on proxies from social media. Unseen data from February 2017 to January 2020 were used to estimate the one-month ahead prediction accuracy of the model.
UNASSIGNED: When human mobility proxies were included in the spatial covariance structure, the model fit improved in terms of the log score (from 1.748 to 1.561) and the mean absolute error (from 0.676 to 0.522) based on the validation data. Additionally, showed only few observations outside the credible interval of predictions (1.48%) and weather conditions were not found to contribute additionally to the clustering of cases at this scale.
UNASSIGNED: The study shows that it is possible to make highly accurate predictions of the within-city cluster dynamics of dengue using mobility proxies from social media combined with disease surveillance data. These insights are important for proactive and timely outbreak management of dengue.
UNASSIGNED: Swedish Research Council Formas, Umeå Centre for Global Health Research, Swedish Council for Working Life and Social Research, Swedish research council VINNOVA and Alexander von Humboldt Foundation (Germany).

UNASSIGNED: When sepsis is detected, organ damage may have progressed to irreversible stages, leading to poor prognosis. The use of machine learning for predicting sepsis early has shown promise, however international validations are missing.
UNASSIGNED: This was a retrospective, observational, multi-centre cohort study. We developed and externally validated a deep learning system for the prediction of sepsis in the intensive care unit (ICU). Our analysis represents the first international, multi-centre in-ICU cohort study for sepsis prediction using deep learning to our knowledge. Our dataset contains 136,478 unique ICU admissions, representing a refined and harmonised subset of four large ICU databases comprising data collected from ICUs in the US, the Netherlands, and Switzerland between 2001 and 2016. Using the international consensus definition Sepsis-3, we derived hourly-resolved sepsis annotations, amounting to 25,694 (18.8%) patient stays with sepsis. We compared our approach to clinical baselines as well as machine learning baselines and performed an extensive internal and external statistical validation within and across databases, reporting area under the receiver-operating-characteristic curve (AUC).
UNASSIGNED: Averaged over sites, our model was able to predict sepsis with an AUC of 0.846 (95% confidence interval [CI], 0.841-0.852) on a held-out validation cohort internal to each site, and an AUC of 0.761 (95% CI, 0.746-0.770) when validating externally across sites. Given access to a small fine-tuning set (10% per site), the transfer to target sites was improved to an AUC of 0.807 (95% CI, 0.801-0.813). Our model raised 1.4 false alerts per true alert and detected 80% of the septic patients 3.7 h (95% CI, 3.0-4.3) prior to the onset of sepsis, opening a vital window for intervention.
UNASSIGNED: By monitoring clinical and laboratory measurements in a retrospective simulation of a real-time prediction scenario, a deep learning system for the detection of sepsis generalised to previously unseen ICU cohorts, internationally.
UNASSIGNED: This study was funded by the Personalized Health and Related Technologies (PHRT) strategic focus area of the ETH domain.