Completeness of data is vital for the decision making and forecasting on Building Management Systems (BMS) as missing data can result in biased decision making down the line. This study creates a guideline for imputing the gaps in BMS datasets by comparing four methods: K Nearest Neighbour algorithm (KNN), Recurrent Neural Network (RNN), Hot Deck (HD) and Last Observation Carried Forward (LOCF). The guideline contains the best method per gap size and scales of measurement. The four selected methods are from various backgrounds and are tested on a real BMS and metereological dataset. The focus of this paper is not to impute every cell as accurately as possible but to impute trends back into the missing data. The performance is characterised by a set of criteria in order to allow the user to choose the imputation method best suited for its needs. The criteria are: Variance Error (VE) and Root Mean Squared Error (RMSE). VE has been given more weight as its ability to evaluate the imputed trend is better than RMSE. From preliminary results, it was concluded that the best K‐values for KNN are 5 for the smallest gap and 100 for the larger gaps. Using a genetic algorithm the best RNN architecture for the purpose of this paper was determined to be GatedRecurrent Units (GRU). The comparison was performed using a different training dataset than the imputation dataset. The results show no consistent link between the difference in Kurtosis or Skewness and imputation performance. The results of the experiment concluded that RNN is best for interval data and HD is best for both nominal and ratio data. There was no single method that was best for all gap sizes as it was dependent on the data to be imputed.
MULTIFILE
Completeness of data is vital for the decision making and forecasting on Building Management Systems (BMS) as missing data can result in biased decision making down the line. This study creates a guideline for imputing the gaps in BMS datasets by comparing four methods: K Nearest Neighbour algorithm (KNN), Recurrent Neural Network (RNN), Hot Deck (HD) and Last Observation Carried Forward (LOCF). The guideline contains the best method per gap size and scales of measurement. The four selected methods are from various backgrounds and are tested on a real BMS and meteorological dataset. The focus of this paper is not to impute every cell as accurately as possible but to impute trends back into the missing data. The performance is characterised by a set of criteria in order to allow the user to choose the imputation method best suited for its needs. The criteria are: Variance Error (VE) and Root Mean Squared Error (RMSE). VE has been given more weight as its ability to evaluate the imputed trend is better than RMSE. From preliminary results, it was concluded that the best K‐values for KNN are 5 for the smallest gap and 100 for the larger gaps. Using a genetic algorithm the best RNN architecture for the purpose of this paper was determined to be Gated Recurrent Units (GRU). The comparison was performed using a different training dataset than the imputation dataset. The results show no consistent link between the difference in Kurtosis or Skewness and imputation performance. The results of the experiment concluded that RNN is best for interval data and HD is best for both nominal and ratio data. There was no single method that was best for all gap sizes as it was dependent on the data to be imputed.
BACKGROUND: Medication-related problems are common after hospitalization, for example when changes in patients' medication regimens are accompanied by insufficient patient education, poor information transfer between healthcare providers, and inadequate follow-up post-discharge. We investigated the effect of a pharmacy-led transitional care program on the occurrence of medication-related problems four weeks post-discharge.METHODS: A prospective multi-center before-after study was conducted in six departments in total of two hospitals and 50 community pharmacies in the Netherlands. We tested a pharmacy-led program incorporating (i) usual care (medication reconciliation at hospital admission and discharge) combined with, (ii) teach-back at hospital discharge, (iii) improved transfer of medication information to primary healthcare providers and (iv) post-discharge home visit by the patient's own community pharmacist, compared with usual care alone. The difference in medication-related problems four weeks post-discharge, measured by means of a validated telephone-interview protocol, was the primary outcome. Multiple logistic regression analysis was used, adjusting for potential confounders after multiple imputation to deal with missing data.RESULTS: We included 234 (January-April 2016) and 222 (July-November 2016) patients in the usual care and intervention group, respectively. Complete data on the primary outcome was available for 400 patients. The proportion of patients with any medication-related problem was 65.9% (211/400) in the usual care group compared to 52.4% (189/400) in the intervention group (p = 0.01). After multiple imputation, the proportion of patients with any medication-related problem remained lower in the intervention group (unadjusted odds ratio 0.57; 95% CI 0.38-0.86, adjusted odds ratio 0.50; 95% CI 0.31-0.79).CONCLUSIONS: A pharmacy-led transitional care program reduced medication-related problems after discharge. Implementation research is needed to determine how best to embed these interventions in existing processes.
