Assessment of a hybrid decision support system using machine learning with artificial intelligence to safely rule out prescriptions from medication review in daily practice.

Background Medication review is time-consuming and not exhaustive in most French hospitals. We routinely use an innovative hybrid decision support system using Artificial Intelligence to prioritize medication review by scoring prescriptions by their risk of containing at least one drug related problem (DRP). Aim Our aim was to attest that the prescriptions with low risk of DRPs ruled out by the tool in everyday practice were effectively free of any DRPs with potentially severe clinical impact. Methods We conducted a randomized single-blinded study to compare the rate of pharmaceutical interventions (PI) between low and high-risk prescriptions defined by the tool's calculated score. Prescriptions were reviewed daily by a clinical pharmacist. Proportion of prescriptions with at least one severe DRP was calculated in both groups. Severe DRPs were characterized through a multidisciplinary approach. Results Four hundred and twenty (107 low score and 313 high score) prescriptions were analyzed. The percentage of prescriptions with severe DRPs was dramatically decreased in low score prescriptions (2.8% vs. 15.3% for high-risk; p = 0.0248). A significant difference was found (94% vs. 20%; p < 0.001) in the percentage of severe DRPs detected by the hybrid approach compared to a CDSS. During the study period, the hybrid tool allowed to rule out 55% of all prescriptions in our hospital.Conclusion This hybrid decision support tool has shown to be accurate to detect DRPs in daily practice. Despite some limitations, it offers the best possible solution to prioritized medication review, considering the shortage of clinical pharmacists in France and considerably improves the safety of patients' care.

Low admission blood pressure as a marker of poor 1-year survival in patients with revascularized critical limb ischemia.

OBJECTIVE: To contrast the association between blood pressure (BP) level and antihypertensive medications at hospital admission with 1-year mortality in patients undergoing revascularization for critical limb ischemia (CLI). METHODS: From November 2013 to May 2019, 315 consecutive patients were retrospectively included. A median of seven (IQR 3-13) separate readings were recorded for each patient before revascularization procedure and the average represented patient's mean BP. BP-lowering medications, clinical and biological parameters were recorded at baseline. The main outcome was total 1-year mortality. RESULTS: The cohort included 172 men (55%) and 143 women (45%), with a mean age of 77.9 ±â€Š11.9 years. Treated hypertension was present in 245 (78%) patients; 288 (91%) patients had BP-lowering drug prescriptions (2.1 ±â€Š1.3 medications at baseline). Mean SBP, DBP, mean BP (MBP) and pulse pressure (PP) were 132 ±â€Š18, 70 ±â€Š8, 90 ±â€Š10 and 62 ±â€Š16mmHg. During 1-year follow-up, 80 (25.4%) patients died. In single-pressure multivariate analysis, SBP (hazard ratio 0.97; 95% CI 0.96-0.99; P = 0.005), MBP (hazard ratio 0.96; 95% CI 0.92-0.99; P = 0.01), PP (hazard ratio 0.97; 95% CI 0.95-0.99; P = 0.009), but not DBP, were inversely correlated with 1-year mortality, independently of age, coronary heart disease, left ventricular ejection fraction, brain natriuretic peptide, serum albumin, institutionalized status and antihypertensive drugs. Association between SBP, MBP and PP with 1-year mortality had a quite linear reverse pattern. CONCLUSION: Among patients undergoing revascularization for CLI, there is an inverse correlation between admission SBP, MBP and PP with 1-year mortality. BP may represent a modifiable therapeutic target to prevent poor outcome in CLI patients.

A machine learning-based clinical decision support system to identify prescriptions with a high risk of medication error.

OBJECTIVE: To improve patient safety and clinical outcomes by reducing the risk of prescribing errors, we tested the accuracy of a hybrid clinical decision support system in prioritizing prescription checks. MATERIALS AND METHODS: Data from electronic health records were collated over a period of 18 months. Inferred scores at a patient level (probability of a patient's set of active orders to require a pharmacist review) were calculated using a hybrid approach (machine learning and a rule-based expert system). A clinical pharmacist analyzed randomly selected prescription orders over a 2-week period to corroborate our findings. Predicted scores were compared with the pharmacist's review using the area under the receiving-operating characteristic curve and area under the precision-recall curve. These metrics were compared with existing tools: computerized alerts generated by a clinical decision support (CDS) system and a literature-based multicriteria query prioritization technique. Data from 10 716 individual patients (133 179 prescription orders) were used to train the algorithm on the basis of 25 features in a development dataset. RESULTS: While the pharmacist analyzed 412 individual patients (3364 prescription orders) in an independent validation dataset, the areas under the receiving-operating characteristic and precision-recall curves of our digital system were 0.81 and 0.75, respectively, thus demonstrating greater accuracy than the CDS system (0.65 and 0.56, respectively) and multicriteria query techniques (0.68 and 0.56, respectively). DISCUSSION: Our innovative digital tool was notably more accurate than existing techniques (CDS system and multicriteria query) at intercepting potential prescription errors. CONCLUSIONS: By primarily targeting high-risk patients, this novel hybrid decision support system improved the accuracy and reliability of prescription checks in a hospital setting.

Predictive value of admission blood pressure for 3-month mortality in patients undergoing revascularization for critical limb ischemia.

OBJECTIVE: In patients with critical limb ischemia (CLI), blood pressure (BP) impact on mortality is unknown. We analyzed the predictive value of SBP, DBP and pulse pressure (PP) at hospital admission on 3-month mortality in patients with CLI undergoing revascularization procedure. METHODS: From November 2013 to December 2018, 297 consecutive patients were retrospectively included. Admission BP was recorded using automated brachial sphygmomanometer, before revascularization procedure. A median of seven (IQR3-13) separate readings were recorded for each patient and the average represented patient's mean BP (mBP). Clinical and biological parameters were recorded at baseline. RESULTS: The cohort included 163 men (55%) and 134 women (45%) with a mean age of 77.7 ±â€Š11.9 years. Treated hypertension and diabetes were present in, respectively, 62 and 48% of patients. Mean SBP, DBP and PP were 132 ±â€Š18, 70 ±â€Š8 and 62 ±â€Š16 mmHg. Thirty-four patients (11.4%) died during 3-month follow-up, mostly from cardiovascular causes. In univariate analysis, age, female sex, brain natriuretic peptide and C-reactive protein were positively correlated with mortality. BMI, mSBP, mDBP, mPP, hemoglobin, serum albumin and statin treatment were negatively correlated with mortality. In single-pressure multivariate analyses, mSBP (P = 0.024) and mPP (P = 0.030) were negatively correlated with mortality. Association between mSBP and mortality had an asymptotic curve pattern and SBP level 135 mmHg or less was significantly correlated with mortality. CONCLUSION: In patients undergoing revascularization for CLI, admission SBP is an independent predictor for short-term mortality with a negative relationship. SBP level 135 mmHg or less represents a warning sign to explore and correct associated comorbidities.