An official website of the United States government
Abstract Continuous monitoring of blood glucose (BG) levels is a key aspect of diabetes management. Patients with Type-1 diabetes (T1D) require an effective tool to monitor these levels in order to make appropriate decisions regarding insulin administration and food intake to keep BG levels in target range. Effectively and accurately predicting future BG levels at multi-time steps ahead benefits a patient with diabetes by helping them decrease the risks of extremes in BG including hypo- and hyperglycemia. In this study, we present a novel multi-component deep learning model that predicts the BG levels in a multi-step look ahead fashion. The model is evaluated both quantitatively and qualitatively on actual blood glucose data for 97 patients. For the prediction horizon (PH) of 30 mins, the average values forroot mean squared error(RMSE),mean absolute error(MAE),mean absolute percentage error(MAPE), andnormalized mean squared error(NRMSE) are$$23.22 \pm 6.39$$ mg/dL, 16.77 ± 4.87 mg/dL,$$12.84 \pm 3.68$$ and$$0.08 \pm 0.01$$ respectively. When Clarke and Parkes error grid analyses were performed comparing predicted BG with actual BG, the results showed average percentage of points in Zone A of$$80.17 \pm 9.20$$ and$$84.81 \pm 6.11,$$ respectively. We offer this tool as a mechanism to enhance the predictive capabilities of algorithms for patients with T1D.
more »
« less
This content will become publicly available on December 1, 2026
Deep learning unlocks the true potential of organ donation after circulatory death with accurate prediction of time-to-death
Abstract Increasing the number of organ donations after circulatory death (DCD) has been identified as one of the most important ways of addressing the ongoing organ shortage. While recent technological advances in organ transplantation have increased their success rate, a substantial challenge in increasing the number of DCD donations resides in the uncertainty regarding the timing of cardiac death after terminal extubation, impacting the risk of prolonged ischemic organ injury, and negatively affecting post-transplant outcomes. In this study, we trained and externally validated an ODE-RNN model, which combines recurrent neural network with neural ordinary equations and excels in processing irregularly-sampled time series data. The model is designed to predict time-to-death following terminal extubation in the intensive care unit (ICU) using the history of clinical observations. Our model was trained on a cohort of 3,238 patients from Yale New Haven Hospital, and validated on an external cohort of 1,908 patients from six hospitals across Connecticut. The model achieved accuracies of$$95.3~\pm ~1.0\%$$and$$95.4~\pm ~0.7\%$$for predicting whether death would occur in the first 30 and 60 minutes, respectively, with a calibration error of$$0.024~\pm ~0.009$$. Heart rate, respiratory rate, mean arterial blood pressure (MAP), oxygen saturation (SpO2), and Glasgow Coma Scale (GCS) scores were identified as the most important predictors. Surpassing existing clinical scores, our model sets the stage for reduced organ acquisition costs and improved post-transplant outcomes.
more »
« less
- Award ID(s):
- 2047856
- PAR ID:
- 10617982
- Publisher / Repository:
- Springer Nature
- Date Published:
- Journal Name:
- Scientific Reports
- Volume:
- 15
- Issue:
- 1
- ISSN:
- 2045-2322
- Subject(s) / Keyword(s):
- Machine learning, AI, Time-to-death prediction
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
BACKGROUND: Lung transplantation is the gold standard for a carefully selected patient population with end-stage lung disease. We sought to create a unique risk stratification model using only preoperative recipient data to predict one-year postoperative mortality during our pre-transplant assessment. METHODS: Data of lung transplant recipients at Houston Methodist Hospital (HMH) from 1/2009 to 12/2014 were extracted from the United Network for Organ Sharing (UNOS) database. Patients were randomly divided into development and validation cohorts. Cox proportional-hazards models were conducted. Variables associated with 1-year mortality post-transplant were assigned weights based on the beta coefficients, and risk scores were derived. Patients were stratified into low-, medium- and high-risk categories. Our model was validated using the validation dataset and data from other US transplant centers in the UNOS database RESULTS: We randomized 633 lung recipients from HMH into the development (n=317 patients) and validation cohort (n=316). One-year survival after transplant was significantly different among risk groups: 95% (low-risk), 84% (medium-risk), and 72% (high-risk) (p<0.001) with a C-statistic of 0.74. Patient survival in the validation cohort was also significantly different among risk groups (85%, 77% and 65%, respectively, p<0.001). Validation of the model with the UNOS dataset included 9,920 patients and found 1-year survival to be 91%, 86% and 82%, respectively (p < 0.001). CONCLUSIONS: Using only recipient data collected at the time of pre-listing evaluation, our simple scoring system has good discrimination power and can be a practical tool in the assessment and selection of potential lung transplant recipients.more » « less
-
Abstract Developing prediction models for emerging infectious diseases from relatively small numbers of cases is a critical need for improving pandemic preparedness. Using COVID-19 as an exemplar, we propose a transfer learning methodology for developing predictive models from multi-modal electronic healthcare records by leveraging information from more prevalent diseases with shared clinical characteristics. Our novel hierarchical, multi-modal model ($${\textsc {TransMED}}$$ ) integrates baseline risk factors from the natural language processing of clinical notes at admission, time-series measurements of biomarkers obtained from laboratory tests, and discrete diagnostic, procedure and drug codes. We demonstrate the alignment of$${\textsc {TransMED}}$$ ’s predictions with well-established clinical knowledge about COVID-19 through univariate and multivariate risk factor driven sub-cohort analysis.$${\textsc {TransMED}}$$ ’s superior performance over state-of-the-art methods shows that leveraging patient data across modalities and transferring prior knowledge from similar disorders is critical for accurate prediction of patient outcomes, and this approach may serve as an important tool in the early response to future pandemics.more » « less
-
A<sc>bstract</sc> We report measurements of the absolute branching fractions$$\mathcal{B}\left({B}_{s}^{0}\to {D}_{s}^{\pm }X\right)$$,$$\mathcal{B}\left({B}_{s}^{0}\to {D}^{0}/{\overline{D} }^{0}X\right)$$, and$$\mathcal{B}\left({B}_{s}^{0}\to {D}^{\pm }X\right)$$, where the latter is measured for the first time. The results are based on a 121.4 fb−1data sample collected at the Υ(10860) resonance by the Belle detector at the KEKB asymmetric-energye+e−collider. We reconstruct one$${B}_{s}^{0}$$meson in$${e}^{+}{e}^{-}\to \Upsilon\left(10860\right)\to {B}_{s}^{*}{\overline{B} }_{s}^{*}$$events and measure yields of$${D}_{s}^{+}$$,D0, andD+mesons in the rest of the event. We obtain$$\mathcal{B}\left({B}_{s}^{0}\to {D}_{s}^{\pm }X\right)=\left(68.6\pm 7.2\pm 4.0\right)\%$$,$$\mathcal{B}\left({B}_{s}^{0}\to {D}^{0}/{\overline{D} }^{0}X\right)=\left(21.5\pm 6.1\pm 1.8\right)\%$$, and$$\mathcal{B}\left({B}_{s}^{0}\to {D}^{\pm }X\right)=\left(12.6\pm 4.6\pm 1.3\right)\%$$, where the first uncertainty is statistical and the second is systematic. Averaging with previous Belle measurements gives$$\mathcal{B}\left({B}_{s}^{0}\to {D}_{s}^{\pm }X\right)=\left(63.4\pm 4.5\pm 2.2\right)\%$$and$$\mathcal{B}\left({B}_{s}^{0}\to {D}^{0}/{\overline{D} }^{0}X\right)=\left(23.9\pm 4.1\pm 1.8\right)\%$$. For the$${B}_{s}^{0}$$production fraction at the Υ(10860), we find$${f}_{s}=\left({21.4}_{-1.7}^{+1.5}\right)\%$$.more » « less
-
Abstract We perform path-integral molecular dynamics (PIMD), ring-polymer MD (RPMD), and classical MD simulations of H$$_2$$ O and D$$_2$$ O using the q-TIP4P/F water model over a wide range of temperatures and pressures. The density$$\rho (T)$$ , isothermal compressibility$$\kappa _T(T)$$ , and self-diffusion coefficientsD(T) of H$$_2$$ O and D$$_2$$ O are in excellent agreement with available experimental data; the isobaric heat capacity$$C_P(T)$$ obtained from PIMD and MD simulations agree qualitatively well with the experiments. Some of these thermodynamic properties exhibit anomalous maxima upon isobaric cooling, consistent with recent experiments and with the possibility that H$$_2$$ O and D$$_2$$ O exhibit a liquid-liquid critical point (LLCP) at low temperatures and positive pressures. The data from PIMD/MD for H$$_2$$ O and D$$_2$$ O can be fitted remarkably well using the Two-State-Equation-of-State (TSEOS). Using the TSEOS, we estimate that the LLCP for q-TIP4P/F H$$_2$$ O, from PIMD simulations, is located at$$P_c = 167 \pm 9$$ MPa,$$T_c = 159 \pm 6$$ K, and$$\rho _c = 1.02 \pm 0.01$$ g/cm$$^3$$ . Isotope substitution effects are important; the LLCP location in q-TIP4P/F D$$_2$$ O is estimated to be$$P_c = 176 \pm 4$$ MPa,$$T_c = 177 \pm 2$$ K, and$$\rho _c = 1.13 \pm 0.01$$ g/cm$$^3$$ . Interestingly, for the water model studied, differences in the LLCP location from PIMD and MD simulations suggest that nuclear quantum effects (i.e., atoms delocalization) play an important role in the thermodynamics of water around the LLCP (from the MD simulations of q-TIP4P/F water,$$P_c = 203 \pm 4$$ MPa,$$T_c = 175 \pm 2$$ K, and$$\rho _c = 1.03 \pm 0.01$$ g/cm$$^3$$ ). Overall, our results strongly support the LLPT scenario to explain water anomalous behavior, independently of the fundamental differences between classical MD and PIMD techniques. The reported values of$$T_c$$ for D$$_2$$ O and, particularly, H$$_2$$ O suggest that improved water models are needed for the study of supercooled water.more » « less
