Translation of evidence into kidney transplant clinical practice: managing drug-lab interactions by a context-aware clinical decision support system.

BACKGROUND: Drug-laboratory (lab) interactions (DLIs) are a common source of preventable medication errors. Clinical decision support systems (CDSSs) are promising tools to decrease such errors by improving prescription quality in terms of lab values. However, alert fatigue counteracts their impact. We aimed to develop a novel user-friendly, evidence-based, clinical context-aware CDSS to alert nephrologists about DLIs clinically important lab values in prescriptions of kidney recipients. METHODS: For the most frequently prescribed medications identified by a prospective cross-sectional study in a kidney transplant clinic, DLI-rules were extracted using main pharmacology references and clinical inputs from clinicians. A CDSS was then developed linking a computerized prescription system and lab records. The system performance was tested using data of both fictitious and real patients. The "Questionnaire for User Interface Satisfaction" was used to measure user satisfaction of the human-computer interface. RESULTS: Among 27 study medications, 17 needed adjustments regarding renal function, 15 required considerations based on hepatic function, 8 had drug-pregnancy interactions, and 13 required baselines or follow-up lab monitoring. Using IF & THEN rules and the contents of associated alert, a DLI-alerting CDSS was designed. To avoid alert fatigue, the alert appearance was considered as interruptive only when medications with serious risks were contraindicated or needed to be discontinued or adjusted. Other alerts appeared in a non-interruptive mode with visual clues on the prescription window for easy, intuitive notice. When the system was used for real 100 patients, it correctly detected 260 DLIs and displayed 249 monitoring, seven hepatic, four pregnancy, and none renal alerts. The system delivered patient-specific recommendations based on individual lab values in real-time. Clinicians were highly satisfied with the usability of the system. CONCLUSIONS: To our knowledge, this is the first study of a comprehensive DLI-CDSS for kidney transplant care. By alerting on considerations in renal and hepatic dysfunctions, maternal and fetal toxicity, or required lab monitoring, this system can potentially improve medication safety in kidney recipients. Our experience provides a strong foundation for designing specialized systems to promote individualized transplant follow-up care.

Predicting the function of transplanted kidney in long-term care processes: Application of a hybrid model.

BACKGROUND: A tool that can predict the estimated glomerular filtration rate (eGFR) in routine daily care can help clinicians to make better decisions for kidney transplant patients and to improve transplantation outcome. In this paper, we proposed a hybrid prediction model for predicting a future value for eGFR during long-term care processes. METHODS: Longitudinal, historical data of 942 transplant patients who received a kidney between 2001 and 2016 at Urmia kidney transplant center was used to develop a hybrid model. The model was based on three primary models: multi-layer perceptron (MLP), linear regression (LR), and a model that predicted a smoothed value of eGFR. The hybrid model used at-hand, longitudinal data of physical examinations and laboratory test values available at each visit. Two different datasets, a generalized dataset (GData) and a personalized dataset (PData), were created. Then, in both datasets, two data subsets of development and validation were created. For prediction, all records related to the fourth to tenth previous visits of patients in time order from the target date, i.e., window size (WS) = 4-10, were used. The performance of the models was evaluated using Mean Square Error (MSE) and Mean Absolute Error (MAE). The differences between the models were evaluated with the F-test and the Akaike Information Criterion (AIC). RESULTS: The datasets contained 35,066 records, totally. The GData contained 26,210 and 8856 records and the PData had 24,079 and 9103 records in the development and validation datasets, respectively. In the hybrid model, the MSE and MAE were 153 and 8.9 in the GData, and 113 and 7.5 in the PData, respectively. The model performance improved using a wider WS of historical records (from 4 to 10). When the WS of ten was used the MSE and MAE declined to 141 and 8.5 in the GData and to 91 and 6.9 in the PData, respectively. In both datasets, the F-test showed that the hybrid model was significantly different from other models. The AIC showed that the hybrid model had a better performance than that of others. CONCLUSIONS: The hybrid model can predict a reliable future value for eGFR. Our results showed that longitudinal covariates help the models to produce better results. Smoothing eGFR values and using a personalized dataset to develop the models also improved the models' performances. They can be considered as a step forward towards personalized medicine.

A dynamic model for predicting graft function in kidney recipients' upcoming follow up visits: A clinical application of artificial neural network.

BACKGROUND: Predicting the function of transplanted kidneys would help clinicians in individualized medical interventions. We aimed to develop and validate a predictive tool for a future value of estimated glomerular filtration rate (eGFR) at upcoming visits. METHODS: We used static and time-dependent covariates as inputs of artificial neural network based prediction models for predicting an eGFR value for an upcoming visit. We included 675 kidney recipients, who received transplant in the Urmia kidney transplant center in 2001-2013 and were longitudinally cared for in 2001-2017. The first 75% of records of longitudinal data of each patient were used to develop the prediction models and the remaining last 25% for evaluating its performance. Models' performances were evaluated by Mean Square Error (MSE) and Mean Absolute Error (MAE). RESULTS: The development and validation datasets included 18,773 and 7038 records of historical data, respectively. The most accurate model included 3 static covariates of recipients' gender and donors' age and gender as well as 11 dynamic covariates of recipients including current age, time since transplant, serum creatinine, fasting blood sugar, weight and blood pressures available at each visit time. The performance of prediction models in the validation cohort was improved when history window of time dependent variables' recent values was increased from 1 to 10 (an MSE decline from 161 to 99). CONCLUSIONS: Our best performed model is able to dynamically predict a future eGFR value for kidney recipients' upcoming visits. Integrating such a clinical tool into daily workflow of outpatient clinics can potentially support clinicians in optimal and individualized decision makings.

The impact of health information technology on organ transplant care: A systematic review.

BACKGROUND: Health Information Technology (HIT) has a potential to promote transplant care. However, a systematic appraisal on how HIT application has so far affected transplant care is greatly missing from the literature. We systematically reviewed trials that evaluated HIT impact on process and patient outcomes as well as costs in organ transplant care. METHODS: A systematic search was conducted in OVID versions of MEDLINE, EMBASE, Cumulative Index to Nursing and Allied Health Literature (CINAHL), the Cochrane, and IEEE databases from January 1990 to December 2015. Studies were included if they: (i) evaluated HIT interventions; (ii) reported results for organ transplant population; (iii) reported quantitative data on process, patient, and cost outcomes; and (iv) used a randomized controlled trial or quasi-experimental study design. RESULTS: Primarily, 12,440 publications were identified; from which ten met inclusion criteria. Among HIT systems, uses of clinical decision support systems (CDSS) targeting different aspects of the complex organ transplant care were common. In terms of process outcomes, HIT positively impacted the timeliness of care, laboratory and medication management practices such as promoting therapeutic or diagnostic protocol compliance by clinicians, and reducing medication errors. Regarding patient outcomes, HIT demonstrated a beneficial impact on the percentage of post-transplant patients with normal lab values and decreasing immunosuppressive toxicity and also deviation from the predefined immunosuppressive therapeutic window. However, in terms of mortality, readmission, rejection, and antiviral resistance rates, the impact was not clearly established in the literature. Finally, these systems were associated with savings in the costs of transplant care in three studies. CONCLUSION: This is the first study reviewing HIT impact on transplant care outcomes. CDSSs have mainly been reported to support transplant care in realizing the above-mentioned benefits. However, to make conclusions, more evidence with less risk of bias is warranted. Several gaps in the literature, including comparison of the impact of commercial systems in different transplant settings, was identified which can motivate future research.

Towards Realizing Benefits of Information Technology in Organ Transplant: A Review.

Organ transplantation comprises of many phases, processes, and activities and involves multiple stakeholders. Effective management of such a complex and costly medical domain requires an efficient, multifaceted solution. Although, Information Technology (IT) can basically play an important role here, it is not clear how IT potentials have been deployed so far. We systematically reviewed MEDLINE, EMBASE, CINAHL, The Cochrane and IEEE databases and identified 27 publications describing IT application in organ transplantation. Although the IT coverage spans over waiting list management, donor-recipient matching, and inpatient and outpatient medication and lab monitoring practices, the coverage is still patchy and whole process IT support is missing in practice.