Experiences of living with overweight/obesity and early type 2 diabetes in Singapore-a qualitative interview study.

OBJECTIVES: To understand the lived experience of adults with overweight/obesity and early type 2 diabetes in a modern urban environment, and the interrelations among the various aspects of these experiences and participants' attitudes to weight management. DESIGN: Qualitative inductive approach to analysing data thematically from semistructured interviews and interpreted from a socioecological perspective. SETTING: Primary care clinics located in northern and central Singapore. PARTICIPANTS: 21 patients between 29 and 59 years old who are living with overweight/obese (Body Mass Index of 25.3-44.0kg/m2) and type 2 diabetes for 6 years or less. RESULTS: The main themes - everyday life, people around me and within me - pointed to a combination of barriers to weight and health management for participants. These included environmental factors such as easy physical and digital access to unhealthy food, and high-stress work environments; social factors such as ambiguous family support and dietary practices of peers; and individual factors such as challenges with self-regulation, prioritising work, dealing with co-existing medical conditions and the emotional significance of food. While lack of motivation and cultural dietary practices are hard to change, a problem-solving attitude, and presence of role models, may enable behaviour change. CONCLUSION: An exploration of the lifeworld of patients with overweight/obese and early type 2 diabetes revealed that work demands, dietary practices in the workplace and at home, and the easy availability of calorie-dense foods afforded by a technology-infused environment hindered the individual's efforts at maintaining a healthy weight and lifestyle. Policy and initiatives promoting work-life balance as well as individualised interventions can support participants' stress management, and problem-solving capability for behaviour change. These barriers stemmed from the various domains of the environmental, interpersonal and intrapersonal but were interrelated. They underscored the need for an integrated approach to weight and diabetes management.

Natural language processing in urology: Automated extraction of clinical information from histopathology reports of uro-oncology procedures.

Objectives: We aimed to automate routine extraction of clinically relevant unstructured information from uro-oncological histopathology reports by applying rule-based and machine learning (ML)/deep learning (DL) methods to develop an oncology focused natural language processing (NLP) algorithm. Methods: Our algorithm employs a combination of a rule-based approach and support vector machines/neural networks (BioBert/Clinical BERT), and is optimised for accuracy. We randomly extracted 5772 uro-oncological histology reports from 2008 to 2018 from electronic health records (EHRs) and split the data into training and validation datasets in an 80:20 ratio. The training dataset was annotated by medical professionals and reviewed by cancer registrars. The validation dataset was annotated by cancer registrars and defined as the gold standard with which the algorithm outcomes were compared. The accuracy of NLP-parsed data was matched against these human annotation results. We defined an accuracy rate of >95% as "acceptable" by professional human extraction, as per our cancer registry definition. Results: There were 11 extraction variables in 268 free-text reports. We achieved an accuracy rate of between 61.2% and 99.0% using our algorithm. Of the 11 data fields, a total of 8 data fields met the acceptable accuracy standard, while another 3 data fields had an accuracy rate between 61.2% and 89.7%. Noticeably, the rule-based approach was shown to be more effective and robust in extracting variables of interest. On the other hand, ML/DL models had poorer predictive performances due to highly imbalanced data distribution and variable writing styles between different reports and data used for domain-specific pre-trained models. Conclusion: We designed an NLP algorithm that can automate clinical information extraction accurately from histopathology reports with an overall average micro accuracy of 93.3%.