Abernathyholt3475

Paediatric disorders of impaired linear growth are challenging to manage, in part because of delays in the identification of pathological short stature and subsequent referral and diagnosis, the requirement for long-term therapy, and frequent poor adherence to treatment, notably with human growth hormone (hGH). Digital health technologies hold promise for improving outcomes in paediatric growth disorders by supporting personalisation of care, from diagnosis to treatment and follow up. The value of automated systems in monitoring linear growth in children has been demonstrated in Finland, with findings that such a system is more effective than a traditional manual system for early diagnosis of abnormal growth. Artificial intelligence has potential to resolve problems of variability that may occur during analysis of growth information, and augmented reality systems have been developed that aim to educate patients and caregivers about growth disorders and their treatment (such as injection techniques for hGH administration). Adherence to hGH treatment is often suboptimal, which negatively impacts the achievement of physical and psychological benefits of the treatment. Personalisation of adherence support necessitates capturing individual patient adherence data; the use of technology to assist with this is exemplified by the use of an electronic injection device, which shares real-time recordings of the timing, date and dose of hGH delivered to the patient with the clinician, via web-based software. The use of an electronic device is associated with high levels of adherence to hGH treatment and improved growth outcomes. It can be anticipated that future technological advances, coupled with continued 'human interventions' from healthcare providers, will further improve management of paediatric growth disorders.

To evaluate the feasibility of the use of iterative cone-beam computed tomography (CBCT) for dose calculation in the head and neck region.

This study includes phantom and clinical studies. All acquired CBCT images were reconstructed with Feldkamp-Davis-Kress algorithm-based CBCT (FDK-CBCT) and iterative CBCT (iCBCT) algorithm. The Hounsfield unit (HU) consistency between the head and body phantoms was determined in both reconstruction techniques. Volumetric modulated arc therapy (VMAT) plans were generated for 16 head and neck patients on a planning CT scan, and the doses were recalculated on FDK-CBCT and iCBCT with Anisotropic Analytical Algorithm (AAA) and Acuros XB (AXB). PLB1001 As a comparison of the accuracy of dose calculations, the absolute dosimetric difference and 1%/1mm gamma passing rate analysis were analyzed.

The difference in the mean HU values between the head and body phantoms was larger for FDK-CBCT (max value 449.1HU) than iCBCT (260.0HU). The median dosimetric difference from the planning CT were <1.0% for both FDK-CBCT and iCBCT but smaller differences were found with iCBCT (planning target volume D

0.38% (0.15-0.59%) for FDK-CBCT, 0.28% (0.13-0.49%) for iCBCT, AAA; 0.14% (0.04-0.19%) for FDK-CBCT, 0.07% (0.02-0.20%) for iCBCT). The mean gamma passing rate was significantly better in iCBCT than FDK-CBCT (AAA 98.7% for FDK-CBCT, 99.4% for iCBCT; AXB 96.8% for FDK_CBCT, 97.5% for iCBCT).

The iCBCT-based dose calculation in VMAT for head and neck cancer was accurate compared to FDK-CBCT.

The iCBCT-based dose calculation in VMAT for head and neck cancer was accurate compared to FDK-CBCT.Named entity recognition (NER) is crucial in various natural language processing (NLP) tasks. However, the nested entities which are common in practical corpus are often ignored in most of current NER models. To extract the nested entities, two categories of models (i.e., feature-based and neural network-based approaches) are proposed. However, the feature-based models suffer from the complicated feature engineering and often heavily rely on the external resources. Discarding the heavy feature engineering, recent neural network-based methods which treat the nested NER as a classification task are designed but still suffer from the heavy class imbalance issue and the high computational cost. To solve these problems, we propose a neural multi-task model with two modules Binary Sequence Labeling and Candidate Region Classification to extract the nested entities. Extensive experiments are conducted on the public datasets. Comparing with recent neural network-based approaches, our proposed model achieves the better performance and obtains the higher efficiency.

Psychiatric patients have increased risk of deep vein thrombosis (DVT). However, there is no systematic data on risk assessment of DVT among psychiatric inpatients. The aim of this study was to develop a risk stratification scoring system for DVT among psychiatic patients on admission.

A systematic review of psychiatric patient's charts, who were admitted to the Tokyo Metropolitan Matsuzawa Hospital from June 2012 to February 2016 and underwent screening for DVT, was conducted. Patients were randomly divided into development (n=2634) and validation (n=2634) groups. Estimated risk values in the multiple logistic regression model for the development sample were rounded to the nearest integer, and used as points of associated factors in the risk stratification scoring system; the total scores were tested in the validation sample. The score's discriminatory ability was assessed with the area under the receiver operating characteristic curve (AUC).

Among the 5268 patients, 258 (4.9%) had DVT. Advancing age, female sex, active cancer, previous venous thromboembolism, transfer from a general hospital, catatonia, and major depressive episode were all significantly associated with the presence of DVT in the development sample. The total score showed good discriminatory ability in the validation sample (AUC 0.816, 95% confidence interval 0.781-0.851); scores of 0-1, 2-3, 4-5, and≥6 were associated with very low risk (0.7%), low risk (4.6%), moderate risk (14.9%), and high risk (35%) for DVT, respectively.

Our risk stratification scoring system showed good performance for detection of DVT among psychiatric patients on admission.

Our risk stratification scoring system showed good performance for detection of DVT among psychiatric patients on admission.