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.

OBJECTIVE: The development of predictive models for patients treated by emergency medical services (EMS) is on the rise in the emergency field. However, how these models evolve over time has not been studied. The objective of the present work is to compare the characteristics of patients who present mortality in the short, medium and long term, and to derive and validate a predictive model for each mortality time.
METHODS: A prospective multicenter study was conducted, which included adult patients with unselected acute illness who were treated by EMS. The primary outcome was noncumulative mortality from all causes by time windows including 30-day mortality, 31- to 180-day mortality, and 181- to 365-day mortality. Prehospital predictors included demographic variables, standard vital signs, prehospital laboratory tests, and comorbidities.
RESULTS: A total of 4830 patients were enrolled. The noncumulative mortalities at 30, 180, and 365 days were 10.8%, 6.6%, and 3.5%, respectively. The best predictive value was shown for 30-day mortality (AUC = 0.930; 95% CI: 0.919-0.940), followed by 180-day (AUC = 0.852; 95% CI: 0.832-0.871) and 365-day (AUC = 0.806; 95% CI: 0.778-0.833) mortality.
CONCLUSIONS: Rapid characterization of patients at risk of short-, medium-, or long-term mortality could help EMS to improve the treatment of patients suffering from acute illnesses.

Gestational diabetes mellitus (GDM) is a hyperglycemic state that is typically diagnosed by an oral glucose tolerance test (OGTT), which is unpleasant, time-consuming, has low reproducibility, and results are tardy. The machine learning (ML) predictive models that have been proposed to improve GDM diagnosis are usually based on instrumental methods that take hours to produce a result. Near-infrared (NIR) spectroscopy is a simple, fast, and low-cost analytical technique that has never been assessed for the prediction of GDM. This study aims to develop ML predictive models for GDM based on NIR spectroscopy, and to evaluate their potential as early detection or alternative screening tools according to their predictive power and duration of analysis. Serum samples from the first trimester (before GDM diagnosis) and the second trimester (at the time of GDM diagnosis) of pregnancy were analyzed by NIR spectroscopy. Four spectral ranges were considered, and 80 mathematical pretreatments were tested for each. NIR data-based models were built with single- and multi-block ML techniques. Every model was subjected to double cross-validation. The best models for first and second trimester achieved areas under the receiver operating characteristic curve of 0.5768 ± 0.0635 and 0.8836 ± 0.0259, respectively. This is the first study reporting NIR-spectroscopy-based methods for the prediction of GDM. The developed methods allow for prediction of GDM from 10 µL of serum in only 32 min. They are simple, fast, and have a great potential for application in clinical practice, especially as alternative screening tools to the OGTT for GDM diagnosis.

Using mathematical models of physiological systems in medicine has allowed for the development of diagnostic, treatment, and medical educational tools. However, their complexity restricts, in most cases, their application for predictive, preventive, and personalized purposes. Although there are strategies that reduce the complexity of applying models based on fitting techniques, most of them are focused on a single instant of time, neglecting the effect of the system\'s temporal evolution. The objective of this research was to introduce a dynamic fitting strategy for physiological models with an extensive array of parameters and a constrained amount of experimental data. The proposed strategy focused on obtaining better predictions based on the temporal trends in the system\'s parameters and being capable of predicting future states. The study utilized a cardiorespiratory model as a case study. Experimental data from a longitudinal study of healthy adult subjects undergoing aerobic exercise were used for fitting and validation. The model predictions obtained in a steady state using the proposed strategy and the traditional single-fit approach were compared. The most successful outcomes were primarily linked to the proposed strategy, exhibiting better overall results regarding accuracy and behavior than the traditional population fitting approach at a single instant in time. The results evidenced the usefulness of the dynamic fitting strategy, highlighting its use for predictive, preventive, and personalized applications.

BACKGROUND: The growth in the capabilities of telehealth have made it possible to identify individuals with a higher risk of uncontrolled diabetes and provide them with targeted support and resources to help them manage their condition. Thus, predictive modeling has emerged as a valuable tool for the advancement of diabetes management.
OBJECTIVE: This study aimed to conceptualize and develop a novel machine learning (ML) approach to proactively identify participants enrolled in a remote diabetes monitoring program (RDMP) who were at risk of uncontrolled diabetes at 12 months in the program.
METHODS: Registry data from the Livongo for Diabetes RDMP were used to design separate dynamic predictive ML models to predict participant outcomes at each monthly checkpoint of the participants\' program journey (month-n models) from the first day of onboarding (month-0 model) up to the 11th month (month-11 model). A participant\'s program journey began upon onboarding into the RDMP and monitoring their own blood glucose (BG) levels through the RDMP-provided BG meter. Each participant passed through 12 predicative models through their first year enrolled in the RDMP. Four categories of participant attributes (ie, survey data, BG data, medication fills, and health signals) were used for feature construction. The models were trained using the light gradient boosting machine and underwent hyperparameter tuning. The performance of the models was evaluated using standard metrics, including precision, recall, specificity, the area under the curve, the F1-score, and accuracy.
RESULTS: The ML models exhibited strong performance, accurately identifying observable at-risk participants, with recall ranging from 70% to 94% and precision from 40% to 88% across the 12-month program journey. Unobservable at-risk participants also showed promising performance, with recall ranging from 61% to 82% and precision from 42% to 61%. Overall, model performance improved as participants progressed through their program journey, demonstrating the importance of engagement data in predicting long-term clinical outcomes.
CONCLUSIONS: This study explored the Livongo for Diabetes RDMP participants\' temporal and static attributes, identification of diabetes management patterns and characteristics, and their relationship to predict diabetes management outcomes. Proactive targeting ML models accurately identified participants at risk of uncontrolled diabetes with a high level of precision that was generalizable through future years within the RDMP. The ability to identify participants who are at risk at various time points throughout the program journey allows for personalized interventions to improve outcomes. This approach offers significant advancements in the feasibility of large-scale implementation in remote monitoring programs and can help prevent uncontrolled glycemic levels and diabetes-related complications. Future research should include the impact of significant changes that can affect a participant\'s diabetes management.

Background The COVID-19 disease continues to cause severe mortality and morbidity. Biochemical parameters are being used to predict the severity of the infection. This study aims to predict disease severity and mortality to help reduce mortality through timely intervention in a cost-effective way. Methods A total of 324 COVID-19 cases admitted at our hospital (All India Institute of Medical Sciences, Patna, BR, India) between June 2020 to December 2020 (phase 1: 190 patients) and April 2021 to May 2021 (phase 2: 134 patients) were recruited for this study. Statistical analysis was done using SPSS Statistics version 23 (IBM Corp., Armonk, NY, USA) and model prediction using Python (The Python Software Foundation, Wilmington, DE, USA). Results There were significant differences in biochemical parameters at the time of admission among COVID-19 patients between phases 1 and 2, ICU and non-ICU admissions, and expired and discharged patients. The receiver operating characteristic (ROC) curves predicted mortality solely based on biochemical parameters. Using multiple logistic regression in Python, a total of four models (two each) were developed to predict ICU admission and mortality. A total of 92 out of 96 patients were placed into the correct management category by our model. This model would have allowed us to preserve 17 of the 21 patients we lost. Conclusions We developed predictive models for admission (ICU or non-ICU) and mortality based on biochemical parameters at the time of admission. A predictive model with a significant predictive capability for IL-6 and procalcitonin values using normal biochemical parameters was proposed. Both can be used as machine learning tools to prognosticate the severity of COVID-19 infections. This study is probably the first of its kind to propose triage for admission in the ICU or non-ICU at the medical emergency department during the first presentation for the necessary optimal treatment of COVID-19 based on a predictive model.

BACKGROUND: Large language models (LLMs) hold potential for mental health applications. However, their opaque alignment processes may embed biases that shape problematic perspectives. Evaluating the values embedded within LLMs that guide their decision-making have ethical importance. Schwartz\'s theory of basic values (STBV) provides a framework for quantifying cultural value orientations and has shown utility for examining values in mental health contexts, including cultural, diagnostic, and therapist-client dynamics.
OBJECTIVE: This study aimed to (1) evaluate whether the STBV can measure value-like constructs within leading LLMs and (2) determine whether LLMs exhibit distinct value-like patterns from humans and each other.
METHODS: In total, 4 LLMs (Bard, Claude 2, Generative Pretrained Transformer [GPT]-3.5, GPT-4) were anthropomorphized and instructed to complete the Portrait Values Questionnaire-Revised (PVQ-RR) to assess value-like constructs. Their responses over 10 trials were analyzed for reliability and validity. To benchmark the LLMs\' value profiles, their results were compared to published data from a diverse sample of 53,472 individuals across 49 nations who had completed the PVQ-RR. This allowed us to assess whether the LLMs diverged from established human value patterns across cultural groups. Value profiles were also compared between models via statistical tests.
RESULTS: The PVQ-RR showed good reliability and validity for quantifying value-like infrastructure within the LLMs. However, substantial divergence emerged between the LLMs\' value profiles and population data. The models lacked consensus and exhibited distinct motivational biases, reflecting opaque alignment processes. For example, all models prioritized universalism and self-direction, while de-emphasizing achievement, power, and security relative to humans. Successful discriminant analysis differentiated the 4 LLMs\' distinct value profiles. Further examination found the biased value profiles strongly predicted the LLMs\' responses when presented with mental health dilemmas requiring choosing between opposing values. This provided further validation for the models embedding distinct motivational value-like constructs that shape their decision-making.
CONCLUSIONS: This study leveraged the STBV to map the motivational value-like infrastructure underpinning leading LLMs. Although the study demonstrated the STBV can effectively characterize value-like infrastructure within LLMs, substantial divergence from human values raises ethical concerns about aligning these models with mental health applications. The biases toward certain cultural value sets pose risks if integrated without proper safeguards. For example, prioritizing universalism could promote unconditional acceptance even when clinically unwise. Furthermore, the differences between the LLMs underscore the need to standardize alignment processes to capture true cultural diversity. Thus, any responsible integration of LLMs into mental health care must account for their embedded biases and motivation mismatches to ensure equitable delivery across diverse populations. Achieving this will require transparency and refinement of alignment techniques to instill comprehensive human values.

BACKGROUND: Prognostic models have been developed using data from a multicentre noncomparative study to forecast the likelihood of a 50% reduction in prostate-specific antigen (PSA50), longer prostate-specific antigen (PSA) progression-free survival (PFS), and longer overall survival (OS) in patients with metastatic castration-resistant prostate cancer receiving [177Lu]Lu-PSMA radioligand therapy. The predictive utility of the models to identify patients likely to benefit most from [177Lu]Lu-PSMA compared with standard chemotherapy has not been established.
OBJECTIVE: To determine the predictive value of the models using data from the randomised, open-label, phase 2, TheraP trial (primary objective) and to evaluate the clinical net benefit of the PSA50 model (secondary objective).
METHODS: All 200 patients were randomised in the TheraP trial to receive [177Lu]Lu-PSMA-617 (n = 99) or cabazitaxel (n = 101) between February 2018 and September 2019.
METHODS: Predictive performance was investigated by testing whether the association between the modelled outcome classifications (favourable vs unfavourable outcome) was different for patients randomised to [177Lu]Lu-PSMA versus cabazitaxel. The clinical benefit of the PSA50 model was evaluated using a decision curve analysis.
CONCLUSIONS: The probability of PSA50 in patients classified as having a favourable outcome was greater in the [177Lu]Lu-PSMA-617 group than in the cabazitaxel group (odds ratio 6.36 [95% confidence interval {CI} 1.69-30.80] vs 0.96 [95% CI 0.32-3.05]; p = 0.038 for treatment-by-model interaction). The PSA50 rate in patients with a favourable outcome for [177Lu]Lu-PSMA-617 versus cabazitaxel was 62/88 (70%) versus 31/85 (36%). The decision curve analysis indicated that the use of the PSA50 model had a clinical net benefit when the probability of a PSA response was ≥30%. The predictive performance of the models for PSA PFS and OS was not established (treatment-by-model interaction: p = 0.36 and p = 0.41, respectively).
CONCLUSIONS: A previously developed outcome classification model for PSA50 was demonstrated to be both predictive and prognostic for the outcome after [177Lu]Lu-PSMA-617 versus cabazitaxel, while the PSA PFS and OS models had purely prognostic value. The models may aid clinicians in defining strategies for patients with metastatic castration-resistant prostate cancer who failed first-line chemotherapy and are eligible for [177Lu]Lu-PSMA-617 and cabazitaxel.
RESULTS: In this report, we validated previously developed statistical models that can predict a response to Lu-PSMA radioligand therapy in patients with advanced prostate cancer. We found that the statistical models can predict patient survival, and aid in determining whether Lu-PSMA therapy or cabazitaxel yields a higher probability to achieve a serum prostate-specific antigen response.

Soil erodibility (K) is an essential component in estimating soil loss indicating the soil\'s susceptibility to detach and transport. Data Computing and processing methods, such as artificial neural networks (ANNs) and multiple linear regression (MLR), have proven to be helpful in the development of predictive models for natural hazards. The present case study aims to assess the efficiency of MLR and ANN models to forecast soil erodibility in Peninsular Malaysia. A total of 103 samples were collected from various sites and K values were calculated using the Tew equation developed for Malaysian soil. From several extracted parameters, the outcomes of correlation and principal component analysis (PCA) revealed the influencing factors to be used in the development of ANN and MLR models. Based on the correlation and PCA results, two sets of influencing factors were employed to develop predictive models. Two MLR (MLR-1 and MLR-2) models and four neural networks (NN-1, NN-2, NN-3, and NN-4) optimized using Levenberg-Marquardt (LM) and scaled conjugate gradient (SCG) were developed and evaluated. The model performance validation was conducted using the coefficient of determination (R2), mean squared error (MSE), root mean squared error (RMSE), and Nash-Sutcliffe efficiency coefficient (NSE). The analysis showed that ANN models outperformed MLR models. The R2 values of 0.446 (MLR-1), 0.430 (MLR-2), 0.894 (NN-1), 0.855 (NN-2), 0.940 (NN-3), and 0.826 (NN-4); MSE values of 0.0000306 (MLR-1), 0.0000315 (MLR-2), 0.0000158 (NN-1), 0.0000261 (NN-2), 0.0000318 (NN-3), and 0.0000216 (NN-4) suggested the higher accuracy and lower modelling error of ANN models as compared with MLR. This study could provide an empirical basis and methodological support for K factor estimation in the region.

OBJECTIVE: To investigate postoperative surgical and non-surgical complications that occur within 30 days following myomectomy procedures, whether laparoscopic or via open surgery.
METHODS: Prospective cohort study SETTING: Del Ponte Women\'s and Children\'s Hospital, Varese, Italy.
METHODS: Women undergoing myomectomy either with laparoscopic or open surgery from July 2020 to June 2023 INTERVENTIONS: Data of consecutive patients who underwent abdominal myomectomy procedures, either via laparoscopy or open abdominal surgery were collected. The study examined patient characteristics, size and location of fibroids, surgical data, and complications. Univariate and multivariable analyses were employed to identify factors contributing to postoperative Clavien-Dindo grade ≥ II complications.
RESULTS: Overall 383 patients were included in the study. The univariate analysis showed intramural fibroid type (p = .0009), large fibroid size (p = .03), and extended operative times (p = .05) were associated with postoperative complications. Open surgical approach (p <.001) and uterine cavity opening (p = .02) also contributed to complications. Postoperative anemia emerged as the most prevalent complication. In the multivariable analysis, the open surgical approach emerged as the only independent factor associated with an increased risk of grade ≥ II complications (odds ratio 7.37; p <.0001).
CONCLUSIONS: In this study we found an increased likelihood of complications in case of open myomectomy. While the presence of potential selection bias may have impacted this finding, it could provide valuable insights for clinicians and surgical teams in the strategic planning of myomectomy procedures.