No abstract

No abstract

Background and Aims Bone and mineral disorders (BMD) is a common complication of CKD in patients on chronic dialysis. Timely and adequate correction of BMD is the most important aspect of patient's treatment. This work presents a system for forecasting of phosphate-binding agents (PBA) dosage and vitamin D receptor activators (VDRA) dosage. The system consists of sequentially triggering artificial neural network forecasting models (separate model for each drug type). Method As an input dataset, system uses patient’s results of laboratory studies (blood calcium, phosphate and PTH) for the period of 6 months, information on previous drug therapy and data on adequacy of patient’s dialysis therapy. The output of the system are dosages of PBA an VDRA that have to be administered in order to bring the patient’s parameters as close as possible to target range of values (2.1-2.5 mmol/l for calcium, 0.87-1.5 mmol/l for phosphate and 150-300 pg/ml for PTH). The system consists of two sequentially triggering forecasting models (for PBA and for VDRA), where each model is an artificial neural network, that has been trained on a data, collected in more than 20 “Nefrosovet” hemodialysis clinics for the period of 3 years. The effect of system usage was examined for the group of 356 hemodialysis patients with median follow-up time of 3 month. The primary end-points were a number of patients in target range of values With respect to calcium (2.1-2.5 mmol/l), phosphate (0.87-1.5 mmol/l) and PTH (150-300 pg/ml). Results During the study we determined that as a result of using the dose forecasting system, number of patients in target range of values significantly increased with respect to calcium (from 178 to 209, p=.0196), phosphate (from 99 to 152, p=.0000), and PTH (from 83 to 109, p=.0281). Conclusion Employment of automated drug dosage forecasting system based on artificial neural network models, has a positive effect on BMD correction quality, which, in turn, reduces the risk of possible complications.

Background and Aims Life expectancy of patients with terminal stage of chronic kidney disease depends on the quality of dialysis therapy and timely and adequate correction of dialysis complications. The goal of this work is to improve the treatment quality for dialysis patients in a setting of multi-facility hospital by employing of Business intelligence (BI) tools for centralized control of diagnostic and treatment process. Method We have created a system for centralized control of patients’ condition, using Microsoft Power BI platform. This system allows to analyze the process of hemodialysis procedure as well as treatment of hypertension, anemia and mineral bone disorder. The system generates various reports that may include parameters of a specific patient, single clinic, or multi-facility hospital for the period from arbitrary date to the day, previous to the report generation date. The effect of system usage was assessed on 288 patients from 30 hemodialysis facilities of “Nefrosovet” private organization, for the period of 6 month. Results Before deployment of the system, target value of Kt/V (1.4) was reached or exceeded in 49% of hemodialysis procedures, median duration of hemodialysis procedure was 227±18 minutes (mean total duration per week - 683 minutes). As the result of usage of centralized control and prescription correction system, target values of Kt/V was reached or exceeded in 65% of hemodialysis procedures, median duration of hemodialysis procedure increased to 238±11 minutes (mean total duration per week - 714 minutes). Before the start of the study, hypotensive episodes were registered in 34% of hemodialysis procedures, and hypertensive episodes were registered in 22% of hemodialysis procedures. As the result of centralized control of hemodialysis procedures, number of procedures with hypotensive episodes reduced to 28%, and number of procedures with hypertensive episodes reduced to 17%. Number of patients with blood hemoglobin value in target range of 100-120 g/l, increased from 1617 patients (56%) to 2051 patients (71%). Number of patients with blood ferritin value in target range of values, increased from 1013 patients (35%) to 1386 patients (48%). Number of patients with TSAT value in target range of values, increased from 873 patients (30%) to 1097 patients (38%). We have also noticed an increase in number of patients with target values of calcium and phosphorus metabolism parameters: calcium corrected for albumin – from 1992 (69%) to 2165 (75%) patients, phosphorus – from 693 (24%) to 982 (34%) patients, intact parathyroid hormone (iPTH) – from 635 (22%) to 837 (29%) patients. Conclusion The usage of BI based centralized patients’ condition control system allows to improve adequacy of dialysis therapy and quality of CKD complications correction in dialysis patients.

Background and Aims Quality of life of hemodialysis patients and adequacy of hemodialysis therapy in general, is defined by the number and duration of incidents during hemodialysis procedures. In this study we examined the effect of telemedical system for control and monitoring of hemodialysis procedures on patients’ condition and their quality of life. Method The system described in this work included: doctor/patient video call functionality initiated from both ends; functionality of hemodialysis procedure parameters and patient’s condition parameters monitoring and registration; functionality of alerting medical staff about registered incidents, functionality of visual control of hemodialysis procedure. The effect of control and monitoring system usage was studied on population of 2300 hemodialysis patients (at the start of the study) with median follow-up of 2 years. The primary end-point was doctor’s reaction time on patient’s complaint, medical staff reaction time on intradialysis hypertension incidents. Secondary end-points were: number of patients who left the clinic due to reasons besides lethality, patients’ satisfaction by hemodialysis therapy (according to survey), number of incidents of intradialysis and interdialysis hypertension. Results During the study we observed that as a result of system deployment average doctor’s reaction time on patient’s complaint (defined as the time from emergence of the complaint to start of patient/doctor communication) reduced from 8 to 1.5 minutes, average staff reaction time on intradialysis hypertension incidents (defined as time from registration of hypertension incident to start of blood pressure normalization actions) reduced from 5 to 2 minutes. Number of patients who left the clinic due to reasons besides lethality reduced from 2.5 per 100 patients before system deployment to 1.7 per 100 patients at the end of the study. Average value of patient’s satisfaction by dialysis therapy increased from 7.2 to 9.1 points on 10-point scale (according to survey conducted at the beginning and at the end of the study). By the end of the study, average number (across population) of hypertension incidents per month reduced from 8.3 to 6.2 and from 20.7 to 16.5 episodes for intradialysis and interdialysis hypertension correspondingly. Conclusion The use of telemedical tools of hemodialysis procedures control and monitoring has positive impact on patients’ satisfaction level by the dialysis procedure and on duration/frequency of incidents registered by these tools, which, in return may improve the quality of patient’s life.