Optimizing postprandial glucose prediction through integration of diet and exercise: Leveraging transfer learning with imbalanced patient data.

BACKGROUND: In recent years, numerous methods have been introduced to predict glucose levels using machine-learning techniques on patients' daily behavioral and continuous glucose data. Nevertheless, a definitive consensus remains elusive regarding modeling the combined effects of diet and exercise for optimal glucose prediction. A notable challenge is the propensity for observational patient datasets from uncontrolled environments to overfit due to skewed feature distributions of target behaviors; for instance, diabetic patients seldom engage in high-intensity exercise post-meal. METHODS: In this study, we introduce a unique application of Bayesian transfer learning for postprandial glucose prediction using randomized controlled trial (RCT) data. The data comprises a time series of three key variables: continuous glucose levels, exercise expenditure, and carbohydrate intake. For building the optimal model to predict postprandial glucose levels we initially gathered balanced training data from RCTs on healthy participants by randomizing behavioral conditions. Subsequently, we pretrained the model's parameter distribution using RCT data from the healthy cohort. This pretrained distribution was then adjusted, transferred, and utilized to determine the model parameters for each patient. RESULTS: The efficacy of the proposed method was appraised using data from 68 gestational diabetes mellitus (GDM) patients in uncontrolled settings. The evaluation underscored the enhanced performance attained through our method. Furthermore, when modeling the joint impact of diet and exercise, the synergetic model proved more precise than its additive counterpart. CONCLUSION: An innovative application of the transfer-learning utilizing randomized controlled trial data can improve the challenging modeling task of postprandial glucose prediction for GDM patients, integrating both dietary and exercise behaviors. For more accurate prediction, future research should focus on incorporating the long-term effects of exercise and other glycemic-related factors such as stress, sleep.

Periodic mobile application (eMOM) with self-tracking of glucose and lifestyle improves treatment of diet-controlled gestational diabetes without human guidance: a randomized controlled trial.

BACKGROUND: Digitalization with minimal human resources could support self-management among women with gestational diabetes and improve maternal and neonatal outcomes. OBJECTIVE: This study aimed to investigate if a periodic mobile application (eMOM) with wearable sensors improves maternal and neonatal outcomes among women with diet-controlled gestational diabetes without additional guidance from healthcare personnel. STUDY DESIGN: Women with gestational diabetes were randomly assigned in a 1:1 ratio at 24 to 28 weeks' gestation to the intervention or the control arm. The intervention arm received standard care in combination with use of the periodic eMOM, whereas the control arm received only standard care. The intervention arm used eMOM with a continuous glucose monitor, an activity tracker, and a food diary 1 week/month until delivery. The primary outcome was the change in fasting plasma glucose from baseline to 35 to 37 weeks' gestation. Secondary outcomes included capillary glucose, weight gain, nutrition, physical activity, pregnancy complications, and neonatal outcomes, such as macrosomia. RESULTS: In total, 148 women (76 in the intervention arm, 72 in the control arm; average age, 34.1±4.0 years; body mass index, 27.1±5.0 kg/m2) were randomized. The intervention arm showed a lower mean change in fasting plasma glucose than the control arm (difference, -0.15 mmol/L vs -2.7 mg/mL; P=.022) and lower capillary fasting glucose levels (difference, -0.04 mmol/L vs -0.7 mg/mL; P=.002). The intervention arm also increased their intake of vegetables (difference, 11.8 g/MJ; P=.043), decreased their sedentary behavior (difference, -27.3 min/d; P=.043), and increased light physical activity (difference, 22.8 min/d; P=.009) when compared with the control arm. In addition, gestational weight gain was lower (difference, -1.3 kg; P=.015), and there were less newborns with macrosomia in the intervention arm (difference, -13.1 %; P=.036). Adherence to eMOM was high (daily use >90%), and the usage correlated with lower maternal fasting (P=.0006) and postprandial glucose levels (P=.017), weight gain (P=.028), intake of energy (P=.021) and carbohydrates (P=.003), and longer duration of the daily physical activity (P=.0006). There were no significant between-arm differences in terms of pregnancy complications. CONCLUSION: Self-tracking of lifestyle factors and glucose levels without additional guidance improves self-management and the treatment of gestational diabetes, which also benefits newborns. The results of this study support the use of digital self-management and education tools in maternity care.

Gyroscope sensor data of shank motion during normal and barefoot walking.

In recent years, shank angular velocity (SAV) has emerged as a valuable tool for accurate temporal gait analysis and motion pattern assessment. To explore SAV among healthy subjects and its capability to distinguish differences between walking conditions, three-dimensional SAV data was measured with a gyroscope sensor during normal and barefoot walking. The resulting dataset contains measurement data from 58 healthy adult subjects aged 19 to 75 years. A single gyroscope was positioned on the lateral side of both shanks just above the lateral malleolus. The data collection involved the subjects walking a 10 m distance three times, both wearing shoes and barefoot. The subjects were instructed to walk with their own natural walking velocity, and each walk began from a stationary position. The dataset has the potential to provide information on how height and weight affect gait kinematics and how barefoot walking differ from walking with shoes. The data also supports designing the collection protocol for more extensive datasets of IMU-based shank motion during gait.

Unsupervised gait detection using biomechanical restrictions.

Quantification of human gait with sensors has enormous potential in health and rehabilitation applications. Objective measurement of gait features in the home and community can reveal the true nature of impact of disease on activities of daily living or response to interventions. Previously reported gait event detection methods have achieved good success, yet can produce errors in some irregular gait patterns. In this paper, we propose a novel unsupervised detection of gait events and gait duration by combining two exclusive processes: (i) exploration of gait event candidates based on iterative running of existing methods with changing parameters and, (ii) selection of the candidate which satisfies gait-specific biomechanical restrictions (e.g., when one leg is in swing, another leg is likely to be in stance). We evaluated this approach using data from a single-axis gyroscope on the left and right ankles in three experimental conditions. The proposed method decreased the timing error for detection of gait events (toe off and heel strike) in irregular gait patterns compared with the conventional method. It also improved the accuracy of measurement of gait duration in a longitudinal free-living dataset and distinguishing gait from non-gait actions.

Aberrant vertebral artery course in a case of Chiari malformation and occipitoatlantal assimilation. Case report.

tThe authors report an unusual case of a patient with combined vertebral artery and Chiari malformation anomalies. Unless such anomalies are properly recognized prior to decompression and fusion, this condition can have grave surgical consequences. The diagnostic and surgery-related implications of such anomalous codiseases are discussed.

Pituitary apoplexy as a consequence of lymphocytic adenohypophysitis in a pregnant woman: a case report.

OBJECTIVE AND IMPORTANCE: A patient with pituitary apoplexy resulting from lymphocytic adenohypophysitis, which caused visual disturbance during pregnancy, is described. This is the first report of such case. CLINICAL PRESENTATION: A 23-year-old primigravida in her 25th week of gestation experienced headache and bitemporal hemianopsia of sudden onset. Magnetic resonance imaging (MRI) revealed a large pituitary mass with intratumoral hemorrhage. Although conservative treatment with intravenous glycerol improved the symptoms partially, the visual symptoms worsened again 6 weeks later. After delivering a girl by scheduled caesarean section her visual symptoms improved. Despite the symptomatic improvement, MRI showed the chiasmatic compression by the enlarged pituitary gland had not changed. Therefore, trans-sphenoidal surgery to decompress the chiasm was performed. Necrotic tissue was seen exuding behind the enlarged pituitary gland and adenohypophysitis with bleeding (apoplexy) was diagnosed histologically. After follow-up for 40 months, she was doing well without any visual or neurological deficits. CONCLUSION: Although relatively rare, pituitary apoplexy as a consequence of lymphocytic adenohypophysitis should be borne in mind when a pregnant woman presents with headache and visual disturbance of sudden onset.

Tilting operating table with self-control foot switch: a new neurosurgical tool.

BACKGROUND: Observation of the surgical field from all directions is essential in microneurosurgery. A tilting operating table operated by the surgeon can satisfy this need. METHODS: A tilting operating table operated by the surgeon using a foot switch was developed by modifying the Sugita table incorporating the X-Y shifter. RESULTS AND CONCLUSIONS: The modified operating table allows the surgeon to move the patient in the head up or down directions, as well as the left side down or right side down directions, so the surgical field can be inspected from all aspects without changing the vertical axis of the operating microscope.

Snare technique of vascular transposition for microvascular decompression--technical note.

Recurrence of trigeminal neuralgia (TN) or hemifacial spasm (HFS) after microvascular decompression (MVD) is not rare. The prosthesis material eventually adheres to the neurovascular structures and again transmits arterial pulsation to the nerve. A snare ligature technique using a Gore-Tex tape can be used for the transposition of the offending artery. No prosthesis is necessary once the transposition is complete. This technique requires introduction of either Gore-Tex tape or thread around the artery and suture over the petrous dura, so an adequate working space as if operating in a shallow basin is essential. Therefore, the osteoplastic craniotomy is a little larger than usual with the scalp flap entirely reflected using a semicircular skin incision. The Gore-Tex tape can be directly snared around the artery and sutured over the petrous dura. If this procedure is difficult, a thread can be attached to both ends of the Gore-Tex tape to pass the tape around the vessel. Seven patients with TN and 13 patients with HFS have undergone this surgery. Although the follow-up period is not yet long enough, there has been no case of recurrence. The present technique for MVD can provide complete and permanent transposition of the offending artery.

[Surgery of AVM of the inferior medullary velum by the uvulotonsillar approach--advantage of moving of the cerebellar tonsil: technical case report].

An incidentally found arteriovenous malformation (AVM) of the inferior medullary velum behind the medulla was removed by the lateral approach to the fourth ventricle originally described by Seeger in 1980. A wide posterior fossa craniotomy was performed to move the cerebellar tonsil laterally with C-1 laminectomy. The tela chroidea and inferior medullary velum, the two main sheets of tissue that form the lower half of the roof of the fourth ventricle can be exposed by gently displacing the tonsils laterally without splitting the vermis. Both the cerebellomedullary and uvulotonsillar spaces were exposed. Because the lateral cerebellomedullary cistern was also exposed, the moving of the cerebellar tonsil in a lateral direction was easy to do without injuring the cerebellar tissues. The nidus was located mainly in the extrapial plane that received feeding arteries from the posterior inferior cerebellar artery. The nidus was removed in a dry field without bleeding. This report is the first report of surgical removal of unruptured AVM of the inferior medullary velum through the so-called telovelar or transcerebellomedullary fissure approach. We propose to call this approach the uvulotonsillar approach to emphasize the dissecting plane between the uvula and the tonsil.