Morten Hasselstrøm Jensen

Moving prediction of exacerbation in chronic obstructive pulmonary disease for patients in telecare

We investigated whether physiological data can be used for predicting chronic obstructive pulmonary disease (COPD) exacerbations. Home measurements from 57 patients were analysed, during which 10 exacerbations occurred in nine patients. A total of 273 different features were evaluated for their discrimination abilities between periods with and without exacerbations. The analysis showed that if a sensitivity level of 70% is considered to be acceptable, then the specificity was 95% and the AUC was 0.73, i.e. it is possible to discriminate between periods of exacerbation and periods without. A system capable of predicting risk could provide support to COPD patients in their tele-rehabilitation.

Professional continuous glucose monitoring in subjects with type 1 diabetes: retrospective hypoglycemia detection.

Background: An important task in diabetes management is detection of hypoglycemia. Professional continuous glucose monitoring (CGM), which produces a glucose reading every 5 min, is a powerful tool for retrospective identification of unrecognized hypoglycemia. Unfortunately, CGM devices tend to be inaccurate, especially in the hypoglycemic range, which limits their applicability for hypoglycemia detection. The objective of this study was to develop an automated pattern recognition algorithm to detect hypoglycemic events in retrospective, professional CGM. Method: Continuous glucose monitoring and plasma glucose (PG) readings were obtained from 17 data sets of 10 type 1 diabetes patients undergoing insulin-induced hypoglycemia. The CGM readings were automatically classified into a hypoglycemic group and a nonhypoglycemic group on the basis of different features from CGM readings and insulin injection. The classification was evaluated by comparing the automated classification with PG using sample-based and event-based sensitivity and specificity measures. Results: With an event-based sensitivity of 100%, the algorithm produced only one false hypoglycemia detection. The sample-based sensitivity and specificity levels were 78% and 96%, respectively. Conclusions: The automated pattern recognition algorithm provides a new approach for detecting unrecognized hypoglycemic events in professional CGM data. The tool may assist physicians and diabetologists in conducting a more thorough evaluation of the diabetes patients glycemic control and in initiating necessary measures for improving glycemic control.

Real-Time Hypoglycemia Detection from Continuous Glucose Monitoring Data of Subjects with Type 1 Diabetes

BACKGROUND Hypoglycemia is a potentially fatal condition. Continuous glucose monitoring (CGM) has the potential to detect hypoglycemia in real time and thereby reduce time in hypoglycemia and avoid any further decline in blood glucose level. However, CGM is inaccurate and shows a substantial number of cases in which the hypoglycemic event is not detected by the CGM. The aim of this study was to develop a pattern classification model to optimize real-time hypoglycemia detection. MATERIALS AND METHODS Features such as time since last insulin injection and linear regression, kurtosis, and skewness of the CGM signal in different time intervals were extracted from data of 10 male subjects experiencing 17 insulin-induced hypoglycemic events in an experimental setting. Nondiscriminative features were eliminated with SEPCOR and forward selection. The feature combinations were used in a Support Vector Machine model and the performance assessed by sample-based sensitivity and specificity and event-based sensitivity and number of false-positives. RESULTS The best model was composed by using seven features and was able to detect 17 of 17 hypoglycemic events with one false-positive compared with 12 of 17 hypoglycemic events with zero false-positives for the CGM alone. Lead-time was 14 min and 0 min for the model and the CGM alone, respectively. CONCLUSIONS This optimized real-time hypoglycemia detection provides a unique approach for the diabetes patient to reduce time in hypoglycemia and learn about patterns in glucose excursions. Although these results are promising, the model needs to be validated on CGM data from patients with spontaneous hypoglycemic events.

Clinical Impact of Home Telemonitoring on Patients with Chronic Obstructive Pulmonary Disease

BACKGROUND Chronic obstructive pulmonary disease (COPD) affects millions of people worldwide. A complication of COPD is exacerbations that result in increased utilization of healthcare services, readmissions to the hospital, and a decline in health-related quality of life. Home telehealth has been shown both to improve health-related quality of life and to reduce admission rates. Using clinical data from a home telemonitoring group, this study sought to investigate the clinical impact of telemonitoring. SUBJECTS AND METHODS Fifty-seven subjects with COPD were included in a 4-month telemonitoring project. Differences between the clinical parameters during the first and last months of participation in the project were tested for significance, and the levels for the first month versus the difference were tested for correlation. RESULTS Significant declines were observed in prescriptions for antibiotics and steroids (p=0.03), clinical consultations (p=0.05), mean systolic blood pressure (p<0.001), standard deviation of systolic blood pressure (p=0.03), and mean diastolic blood pressure (p=0.02). No significant differences were observed for mean of oxygen saturation (p=0.77), standard deviation of oxygen saturation (p=0.36), mean of forced expiratory volume in 1 s (p=0.17), mean of forced vital capacity (p=0.29), mean of pulse rate (p=0.78), standard deviation of pulse rate (p=0.57), and standard deviation of diastolic blood pressure (p=0.27). CONCLUSIONS The results suggest that telemonitoring improves the condition of the patient by lowering the blood pressure, the number of prescribed antibiotics and steroids, and the number of clinical consultations.

Accuracy Evaluation of a New Real-Time Continuous Glucose Monitoring Algorithm in Hypoglycemia

BACKGROUND The purpose of this study was to evaluate the performance of a new continuous glucose monitoring (CGM) calibration algorithm and to compare it with the Guardian(®) REAL-Time (RT) (Medtronic Diabetes, Northridge, CA) calibration algorithm in hypoglycemia. SUBJECTS AND METHODS CGM data were obtained from 10 type 1 diabetes patients undergoing insulin-induced hypoglycemia. Data were obtained in two separate sessions using the Guardian RT CGM device. Data from the same CGM sensor were calibrated by two different algorithms: the Guardian RT algorithm and a new calibration algorithm. The accuracy of the two algorithms was compared using four performance metrics. RESULTS The median (mean) of absolute relative deviation in the whole range of plasma glucose was 20.2% (32.1%) for the Guardian RT calibration and 17.4% (25.9%) for the new calibration algorithm. The mean (SD) sample-based sensitivity for the hypoglycemic threshold of 70 mg/dL was 31% (33%) for the Guardian RT algorithm and 70% (33%) for the new algorithm. The mean (SD) sample-based specificity at the same hypoglycemic threshold was 95% (8%) for the Guardian RT algorithm and 90% (16%) for the new calibration algorithm. The sensitivity of the event-based hypoglycemia detection for the hypoglycemic threshold of 70 mg/dL was 61% for the Guardian RT calibration and 89% for the new calibration algorithm. Application of the new calibration caused one false-positive instance for the event-based hypoglycemia detection, whereas the Guardian RT caused no false-positive instances. The overestimation of plasma glucose by CGM was corrected from 33.2 mg/dL in the Guardian RT algorithm to 21.9 mg/dL in the new calibration algorithm. CONCLUSIONS The results suggest that the new algorithm may reduce the inaccuracy of Guardian RT CGM system within the hypoglycemic range; however, data from a larger number of patients are required to compare the clinical reliability of the two algorithms.

Distribution volume assessment compartment modelling: theoretic phosphate kinetics in steady state hemodialys patients

Purpose Hyperphosphatemia constitutes a major problem in end-stage renal disease patients. At this stage, dialysis efficacy usually plays an important role in obtaining phosphate levels within the normal range. Currently, no practical tool capable of making individualized predictions about phosphate changes during and after hemodialysis (HD) have gained clinical acceptance. As a result, optimal dialysis prescriptions seem to be difficult to achieve. The objective of the present study was to develop and test a quantitative tool to predict intradialytic and postdialytic (2 hours) phosphate kinetics in HD therapy. This included distribution volume assessment. Methods The approach included compartment modeling. Various model attempts were produced and tested using experimental data that included 2 treatment regimens; conventional and nocturnal HD, with 2-hour postdialysis rebound. Graphical comparison and determination of R2 was applied to determine the best model variation. Results 1-, 2- and 3-compartment simulations were produced. Both 2- and 3-compartment model variations showed a close fit with the experimental data. However, a 3-compartment model showed the best graphical fit. This was supported by R2 values in the 0.951–0.979 range. Conclusions The 3-compartment model seems promising for prediction about plasma phosphate and holds the potential to be employed as a decision support tool and to enhance optimal dialysis prescriptions. Furthermore, the results provide specific suggestions about the distribution of phosphate in the body. Despite the promising results, further data and testing are necessary to validate the initial results.

Evaluation of an Algorithm for Retrospective Hypoglycemia Detection Using Professional Continuous Glucose Monitoring Data

Background: People with type 1 diabetes (T1D) are unable to produce insulin and thus rely on exogenous supply to lower their blood glucose. Studies have shown that intensive insulin therapy reduces the risk of late-diabetic complications by lowering average blood glucose. However, the therapy leads to increased incidence of hypoglycemia. Although inaccurate, professional continuous glucose monitoring (PCGM) can be used to identify hypoglycemic events, which can be useful for adjusting glucose-regulating factors. New pattern classification approaches based on identifying hypoglycemic events through retrospective analysis of PCGM data have shown promising results. The aim of this study was to evaluate a new pattern classification approach by comparing the performance with a newly developed PCGM calibration algorithm. Methods: Ten male subjects with T1D were recruited and monitored with PCGM and self-monitoring blood glucose during insulin-induced hypoglycemia. A total of 19 hypoglycemic events occurred during the sessions. Results: The pattern classification algorithm detected 19/19 hypoglycemic events with 1 false positive, while the PCGM with the new calibration algorithm detected 17/19 events with 2 false positives. Conclusions: We can conclude that even after the introduction of new calibration algorithms, the pattern classification approach is still a valuable addition for improving retrospective hypoglycemia detection using PCGM.

Prediction of exacerbation onset in chronic obstructive pulmonary disease patients

Abstract The objective of this study was to develop an algorithm for prediction of exacerbation onset in Chronic Obstructive Pulmonary Disease (COPD) patients based on continuous self-monitoring of physiological parameters from telehome-care monitoring. 151 physiological parameters of COPD patients were monitored on a daily/weekly basis for up to 2 years. Data were segmented in 30-day periods leading up to an exacerbation (exacerbation episode) and starting from a 14-day recovery period post-exacerbation (control episode) and tested in 6 intervals to predict exacerbation onset using k-nearest neighbour (k = 1, 3, 5). A classifier with sensitivity of 73%, specificity of 74%, positive predictive value of 69%, negative predictive value of 78% and an accuracy of 74% was achieved using data intervals consisting of 5 days. Intelligent processing of physiological recordings have potential for predicting exacerbation onset.

A diet management information and communication system to help chronic kidney patients cope with diet restrictions.

Hyperphosphatemia, hyperkalemia, and fluid overload are frequently observed and pose major physiological concerns in chronic kidney patients. The problems are closely related to inadequate diet and phosphate binder intake, which are considerable challenges for many patients. The objective of this study was to develop and test an educational decision support system to help kidney patients cope with diet restrictions and phosphate binder dosage. A prototype was designed including three main functions: 1) information and education, 2) food analyser database and diet registration, and 3) model-based decision support to phosphate binder dosage. The functions and the usability of the prototype were evaluated through user testing and qualitative interviews including five kidney patients. The decision support function was modified and tested using experimental data. In conclusion, the system was evaluated to be a relevant, and potentially beneficial tool to cope with kidney diet restrictions. Further data are necessary to validate the correct phosphate binder dosage and assess the ability of the system to decrease the incidence of fluid and electrolyte disorders in kidney patients.

An information and communication technology system to detect hypoglycemia in people with type 1 diabetes.

Continuous glucose monitoring (CGM) is a new technology with the potential to detect hypoglycemia in people with Type 1 diabetes. However, the inaccuracy of the device in the hypoglycemic range is unfortunately too large. The aim of this study was to develop an information and communication technology system for improving hypoglycemia detection in CGM. The system was developed as an Android application with a build-in pattern classification algorithm. The algorithm processes features from CGM and typed in data from the patient, then warns the patient about incoming hypoglycemia. The system improved the detection of hypoglycemic events by 29%, with only one 1 false alert compared to CGM alone. Furthermore, the algorithm increased the average lead-time by 14 minutes. These findings indicate that it is possible to improve the hypoglycemia detection with an information and communication technology system, but that the system must be validated on a larger dataset.