Automated method for detecting and reading seven-segment digits from images of blood glucose metres and blood pressure monitors.

There is an increasing need for fast and accurate transfer of readings from blood glucose metres and blood pressure monitors to a smartphone mHealth application, without a dependency on Bluetooth technology. Most of the medical devices recommended for home monitoring use a seven-segment display to show the recorded measurement to the patient. We aimed to achieve accurate detection and reading of the seven-segment digits displayed on these medical devices using an image taken in a realistic scenario by a smartphone camera. A synthetic dataset of seven-segment digits was developed in order to train and test a digit classifier. A dataset containing realistic images of blood glucose metres and blood pressure monitors using a variety of smartphone cameras was also created. The digit classifier was evaluated on a dataset of seven-segment digits manually extracted from the medical device images. These datasets along with the code for its development have been made public. The developed algorithm first preprocessed the input image using retinex with two bilateral filters and adaptive histogram equalisation. Subsequently, the digit segments were automatically located within the image by two techniques operating in parallel: Maximally Stable Extremal Regions (MSER) and connected components of a binarised image. A filtering and clustering algorithm was then designed to combine digit segments to form seven-segment digits. The resulting digits were classified using a Histogram of Orientated Gradients (HOG) feature set and a neural network trained on the synthetic digits. The model achieved 93% accuracy on digits found on the medical devices. The digit location algorithm achieved a F1 score of 0.87 and 0.80 on images of blood glucose metres and blood pressure monitors respectively. Very few assumptions were made of the locations of the digits on the devices so that the proposed algorithm can be easily implemented on new devices.

Feasibility of Telemonitoring Blood Pressure in Patients With Kidney Disease (Oxford Heart and Renal Protection Study-1): Observational Study.

BACKGROUND: Blood pressure (BP) is a key modifiable risk factor for patients with CKD, with current guidelines recommending strict control to reduce the risk of both progression of CKD and cardiovascular disease. Trials of BP lowering require multiple visits to achieve target BP which increases the costs of such trials, and in routine care BP measured in clinic may not accurately reflect usual BP. OBJECTIVE: We sought to assess whether a telemonitoring system for BP (using a Bluetooth-enable BP machine which could transmit BP measurements to a tablet device which had a bespoke app to guide measurement of BP and collect questionnaire data) was acceptable to patients with CKD, and whether patients would provide sufficient BP readings to assess variability and guide treatment. METHODS: 25 participants with CKD were trained to use the telemonitoring equipment, asked to record BP daily for 30 days, attend a study visit, and then record BP on alternate days for the next 60 days. They were also offered a wrist-worn applanation tonometry device (BPro) which measures BP every 15 minutes over a 24 hour period.Participants were given questionnaires at the one-month and three-month time points, derived from the System Usability Scale and Technology Acceptance Model. All eligible participants completed the study. RESULTS: Mean age was 58 (SD 11) years and mean eGFR was 36 (SD 13) mL/min/1.73m2. 13 out of 25 (52%) participants provided >90% of expected data and 18 out of 25 (72%) provided >80% expected data. The usability of the telemonitoring system was rated highly with mean scores of 84.9/100 (SE 2.8) after 30 days and 84.2/100 (SE 4.1) after 90 days. The coefficient of variation (CV) for variability of telemonitoring systolic BP was 9.4% (95% confidence interval [CI] 7.8 to 10.9), compared to 7.9% (95% CI 6.4-9.5) for the BPro device (P=0.05) (and 9.0% over one year in a recently completed trial with identical eligibility criteria), indicating that most variation in BP is short-term. CONCLUSIONS: Telemonitoring is acceptable to patients with CKD and provides sufficient data to inform titration of antihypertensive therapies in either a randomized trial setting (comparing different targets BPs) or routine clinical practice. Such methods could be employed in both scenarios and reduce costs currently associated with such activities.Registration ISRCTN13725286.

Geriatric psycho-social history outline.

The details of a Geriatric Psycho-Social History Outline for use with the institutional aged are presented. All health care facilities require background information on the patient at the time of admission, but with long-term facilities a more comprehensive psycho-social history is needed. The Outline provides a basis for obtaining information in five categories: 1) identification (detailed, observational and attitudinal); 2) referral source; 3) background; 4) family constellation or environmental factors; and 5) finances. Its comprehensiveness requires more than one pre-admission interview. It is aimed at reducing morbidity and mortality rates following admission to long-term facilities. If the aged person becomes somewhat familiar with the institution before admission, he is less susceptible to accelerated physiologic and psycho-social deterioration and death. Because of constant growth in the field of gerontology, new and improved instruments must be devised to help carry the load. The Geriatric Psycho-Social History Outline is for use as a guide to those who require such information if they are to function at maximum efficiency.