Development of postoperative delirium prediction models in patients undergoing cardiovascular surgery using machine learning algorithms.

Associations between delirium and postoperative adverse events in cardiovascular surgery have been reported and the preoperative identification of high-risk patients of delirium is needed to implement focused interventions. We aimed to develop and validate machine learning models to predict post-cardiovascular surgery delirium. Patients aged ≥ 40 years who underwent cardiovascular surgery at a single hospital were prospectively enrolled. Preoperative and intraoperative factors were assessed. Each patient was evaluated for postoperative delirium 7 days after surgery. We developed machine learning models using the Bernoulli naive Bayes, Support vector machine, Random forest, Extra-trees, and XGBoost algorithms. Stratified fivefold cross-validation was performed for each developed model. Of the 87 patients, 24 (27.6%) developed postoperative delirium. Age, use of psychotropic drugs, cognitive function (Mini-Cog < 4), index of activities of daily living (Barthel Index < 100), history of stroke or cerebral hemorrhage, and eGFR (estimated glomerular filtration rate) < 60 were selected to develop delirium prediction models. The Extra-trees model had the best area under the receiver operating characteristic curve (0.76 [standard deviation 0.11]; sensitivity: 0.63; specificity: 0.78). XGBoost showed the highest sensitivity (AUROC, 0.75 [0.07]; sensitivity: 0.67; specificity: 0.79). Machine learning algorithms could predict post-cardiovascular delirium using preoperative data.Trial registration: UMIN-CTR (ID; UMIN000049390).

A Deep Learning-Based Model for Classifying Osteoporotic Lumbar Vertebral Fractures on Radiographs: A Retrospective Model Development and Validation Study.

Early diagnosis and initiation of treatment for fresh osteoporotic lumbar vertebral fractures (OLVF) are crucial. Magnetic resonance imaging (MRI) is generally performed to differentiate between fresh and old OLVF. However, MRIs can be intolerable for patients with severe back pain. Furthermore, it is difficult to perform in an emergency. MRI should therefore only be performed in appropriately selected patients with a high suspicion of fresh fractures. As radiography is the first-choice imaging examination for the diagnosis of OLVF, improving screening accuracy with radiographs will optimize the decision of whether an MRI is necessary. This study aimed to develop a method to automatically classify lumbar vertebrae (LV) conditions such as normal, old, or fresh OLVF using deep learning methods with radiography. A total of 3481 LV images for training, validation, and testing and 662 LV images for external validation were collected. Visual evaluation by two radiologists determined the ground truth of LV diagnoses. Three convolutional neural networks were ensembled. The accuracy, sensitivity, and specificity were 0.89, 0.83, and 0.92 in the test and 0.84, 0.76, and 0.89 in the external validation, respectively. The results suggest that the proposed method can contribute to the accurate automatic classification of LV conditions on radiography.

Quantitative magnetic resonance imaging for evaluating of the cerebrospinal fluid kinetics with 17O-labeled water tracer: A preliminary report.

The aim of this study was to evaluate the feasibility of kinetic analysis of cerebrospinal fluid (CSF) using 17O-labeled water tracer. Four subjects (two idiopathic normal pressure hydrocephalus (iNPH) and two possible AD dementia patients) were prospectively included. Injectable formulation of 17O-labeled water containing 10 mol% of H217O (PSO17), was intrathecally administered to the subjects with the lateral decubitus position between the 3rd and 4th lumbar vertebrae. MRI acquisitions were performed in four-time points, before PSO17 administration, 1, 8, and 24 h after PSO17 administration. The 3-dimensional fast spin echo sequence was used. After image registration for all four-time points data, polygonal regions of interest (ROIs) were set in the 14 regions to obtain the signal intensity of CSF. Each signal intensity within the ROI was converted to 17O concentration [%]. The peak concentration at one hour after administration, the slope of concentration changes after PSO17 administration [%/s], and the root mean square error (RMSE) for evaluating the performance of a fitting were calculated. There was no significant difference in peak concentration between the iNPH and AD group. The slope in the AD group (-2.25 ±â€¯1.62 × 10-3 [%/h]) was significantly smaller than in the iNPH group (-1.21 ±â€¯2.31 × 10-3 [%/h]), which suggests the speed of CSF clearance in the iNPH group was slower than AD group. The RMSE indicating the fit to the concentration change in the AD group (4.86 ±â€¯4.74 × 10-3) was also significantly smaller than in the iNPH group (8.64 ±â€¯7.56 × 10-3). The kinetic evaluation of CSF using 17O-labeled water was feasible, and this preliminary study suggests that the differentiation of iNPH and possible AD dementia can be achieved using this method.

Spontaneous rupture of the pancreatic arcade artery caused by neurofibromatosis type 1 successfully treated using emergency transcatheter arterial embolization, partial intra-aortic balloon occlusion, and stent graft placement: a case report and review of the literature.

BACKGROUND: Vascular abnormalities in neurofibromatosis type 1 (NF1) are rare, but are the second leading cause of death in persons with NF1. In NF1 vasculopathy (NF-V), fatal bleeding due to a spontaneous arterial rupture sometimes occurs. Ruptured extracranial arteries in patients with NF1 often involve thoracic vessels, such as the intercostal and subclavian arteries; very few reports exist regarding the abdominal region. Herein, we present the first case of intraperitoneal bleeding due to spontaneous pancreatic arcade artery (PAA) rupture associated with NF1, successfully treated by transcatheter arterial embolization (TAE) combined with stent-graft placement and partial intra-aortic balloon occlusion (IABO). CASE PRESENTATION: A 40-year-old woman complained of back and abdominal pain. Upon admission, her blood pressure was 85/41 mmHg and heart rate was 129 beats/min. Computed tomography (CT) showed large intraperitoneal bleeding due to PAA rupture. After CT scanning, her systolic blood pressure decreased to 50 mmHg. Therefore, we performed emergency TAE with partial IABO. She was treated by TAE of the anterior superior pancreaticoduodenal artery, anterior inferior pancreaticoduodenal artery, and inferior pancreaticoduodenal artery. However, even after TAE, minor extravasation around the superior mesenteric artery continued, and her vital signs remained unstable. Stent-graft placement was selected to stop the haemorrhage, preserving normal blood flow of the superior mesenteric artery trunk. Excellent patency of the stent graft was confirmed on follow-up CT, and she was discharged on postoperative day 56. CONCLUSION: PAA rupture associated with NF1 can be successfully treated by TAE combined with partial intra-aortic balloon occlusion, and stent-graft placement.

Mathematical model to estimate the increase in firefighters' core temperature during firefighting activity with a portable calorimeter.

We developed a mathematical model to estimate the increase in firefighters' core body temperature from energy expenditure (EE) measured by accelerometry to prevent heat illness during firefighting. Wearing firefighter personal protective equipment, seven male subjects aged 23-42 years underwent a graded walking test on a treadmill while esophageal temperature (Tes) and skin temperature were measured with thermocouples and EE was measured with a tri-axial accelerometer. To estimate the increase in Tes from EE, we proposed a mathematical model composed of the heat capacity of active muscles (C1, kcal·°C-1), the heat capacity of the sum of resting muscles and skin (C2), the resistance to heat flux from C1 to C2 (R1, °C·min·kcal-1), and the resistance from C2 to the skin surface (R2). We determined the parameters while minimizing the differences between the estimated and measured changes in Tes profiles during graded walking. We found that C1 and C2 in individuals were highly correlated with their body weight (kg) and body surface area (m2), respectively, whereas R1 and R2 were similar across subjects. When the profiles of measured Tes (y) and estimated Tes (x) were pooled in all subjects, they were almost identical and were described by a regression equation without an intercept, y = 0.96x (r = 0.96, P < 0.0001), with a mean difference of - 0.01 ± 0.12 °C (mean ± SD) ranging from - 0.18 to 1.56 °C of the increase in Tes by Bland-Altman analysis. Thus, the model can be used for firefighters to prevent heat illness during firefighting.

Seasonality in physical activity and walking of healthy older adults.

BACKGROUND: An increasing number of older adults require improvements in their quality of life. Physical activities, particularly walking ability, are of primary importance for older adults. The influence of season on physical activity has not been sufficiently studied among older adults. Therefore, this report compared the physical activity and walking of older individuals between summer and winter seasons using a longitudinal study design in a community in a mid-latitude area. METHODS: Participants in the study comprised 39 healthy community-dwelling adults ranging in age from 65 to 80 years. Physical parameters and activities as well as the preferred speed of walking were measured at half-year intervals. RESULTS: Significant seasonal differences from summer to winter and from winter to summer were detected. Specifically, body fat percentage, single-leg stance, walking speed, cadence, stride length, and trunk and head-trunk pitch ranges were greater in winter than in summer, whereas grip strength and steps per day were greater in summer. Temperature and total activity level were considered to be related to body fat percentage. Grip strength was thought to be affected by outdoor temperature. The possibility of relationships between increased activity per unit time in older adults and increased preferred walking speed, cadence, and stride length in winter temperatures was discussed. CONCLUSION: The seasonal climatic environment of the geographic area of this study affected the activity level of the participants. These results indicate that seasonality should be considered when analyzing physical activity and walking in older adults.

Combined effects of age and gender on gait symmetry and regularity assessed by autocorrelation of trunk acceleration.

BACKGROUND: The gait of a healthy person is believed to be more regular and symmetrical than those of an individual with a disease. Thus, symmetry and regularity are important indicators of human gait. METHODS: The effects of age and gender on gait symmetry and regularity were investigated in 87 Japanese participants by measuring trunk accelerometry during a 7-m walk. The younger group included 26 female and 21 male students, and the elderly group included 24 females and 16 males. Average age for each group was 20 and 70 years, respectively. Gait symmetry and regularity were evaluated on the basis of autocorrelation functions of trunk accelerations of vertical and anteroposterior axes. RESULTS: The relationship between age and gait symmetry and regularity was statistically significant for both vertical and anteroposterior axes. Elderly participants showed lower symmetry and regularity in their gait than young participants. A significant gender effect was observed for the symmetry index of both axes but not for the regularity index. Male participants showed lower gait symmetry than females. An interaction effect between age and gender was significant in the symmetry index of anteroposterior acceleration. Gender effect was appeared more clearly in elderly than young participants. CONCLUSION: Elderly participants showed a more asymmetrical and irregular gait than young participants. In addition to age, a significant gender effect was observed on gait symmetry. However, the effect size of gender was smaller than that of age, and it was not significant for gait regularity. The gait indices obtained by autocorrelation of trunk acceleration can be considered useful to evaluate aging effect on gait.

Development of bipedal walking in humans and chimpanzees: a comparative study.

Development of bipedal walking from the very early stage of walking was studied longitudinally in infant humans and chimpanzees. In contrast to adults, infants of neither species could walk steadily and rhythmically step by step. Short braking duration and small recovery of mechanical energy were demonstrated in infants of both species. The trunk was inclined forwards, the extension of lower limb joints was limited and the accelerating force was not strongly activated. Potential energy was not efficiently used in progression. Walking in adult chimpanzees still showed a forward-inclined trunk, short braking duration, small recovery of energy and large variance of parameters compared to the unique human adult bipedalism. The locomotor characteristics of presumed pre-bipedal ancestors are discussed.

Development of energy and time parameters in the walking of healthy human infants.

Sixteen infants were analyzed longitudinally from the onset of independent walking to 3 years of age using time parameters, speed and energy recovery. Considerable variation and irregularities were observed in many parameters of infant walking, especially until 13 months of age when infants had difficulty in walking steadily step by step. Infant walking until 3 years of age was characterized by a small braking duration, caused mainly by the forward inclination of the trunk, a large relative stance phase duration, which maintained static balance, short stride length, due to the small range of the lower limb joint angle, and a small recovery of external energy. These characteristics were also predominantly evident until 13 months of age. The small recovery characteristic of infants was caused by flexed lower limb joints, pronounced irregularities in energy output, and in younger infants, slow speed. The maximum recovery up until 2 years of age, though smaller than in adults, appeared at about 0.45 dimensionless speed, which is about the same speed that adults in particular naturally and at which their maximum recovery appeared. The forward inclination of the trunk and the lower limb joint angle, influenced the development of many characteristics of bipedal walking.

Differentiation between fore- and hindlimb bones and locomotor behaviour in primates.

Primate appendicular limb bones were measured on the cross-sectional geometry at the mid-length of the humerus and femur and on the external dimensions of long bones of the same individuals. Cross sections were directly measured by means of computer tomography or direct sectioning. The morphometry of bones and locomotor behaviour is discussed from the viewpoint of the functional differentiation between the fore- and hindlimbs. The primate group which daily adopted a relatively terrestrial locomotor type demonstrates robust forelimb bones compared with the group which adopted a fully arboreal locomotor type. In contrast, the arboreal group showed relatively large and long hindlimb bones. The difference resembled the previously reported comparison between terrestrial and arboreal groups among wholly quadrupedal mammals. Humans were more similar to the arboreal group than to the terrestrial group. Parameters of the cross-sectional geometry showed a slightly positive allometry in total primate species. Slopes of the parameters were explained by the influence of muscle force.

Acquirement of stability and mobility in infant gait.

We examined gait development in a longitudinal and cross-sectional study in 35 infants, age range 7-70 months. We estimated walking stability from mediolateral motion of body segments and mobility from the angular displacement of joints. Motion at the shoulder, hip, knee and ankle decreased significantly over several months after the onset of walking and thereafter changed gradually. The remarkable decrease began distally. The trunk-thigh and thigh-shank angles changed significantly until 9 months after the onset of walking. These results indicate that lateral stability, which develops earlier than mobility, is the most important factor in gait development in infants.

Primate limb bones and locomotor types in arboreal or terrestrial environments.

Postcranial limb bones were compared among primates of different locomotor types. Seventy-one primate species, in which all families of primates were included, were grouped into nine locomotor types. Osteometrical data on long bones and data on the cross-sectional geometry of the humerus and the femur were studied by means of allometric analysis and principal component analysis. Relatively robust forelimb bones were observed in the primate group which adopted the relatively terrestrial locomotor type compared with the group that adopted the arboreal locomotor type. The difference resembled the previously reported comparison between terrestrial and arboreal groups among all quadrupedal mammals. The degree of arboreality in daily life is connected with the degree of hindlimb dominance, or the ratio of force applied to the fore- and hindlimb in positional behaviour and also with the shape, size and robusticity of limb bones.