Machine learning-driven clinical decision support system for concept-based searching: a field trial in a Norwegian hospital.

BACKGROUND: Natural language processing (NLP) based clinical decision support systems (CDSSs) have demonstrated the ability to extract vital information from patient electronic health records (EHRs) to facilitate important decision support tasks. While obtaining accurate, medical domain interpretable results is crucial, it is demanding because real-world EHRs contain many inconsistencies and inaccuracies. Further, testing of such machine learning-based systems in clinical practice has received limited attention and are yet to be accepted by clinicians for regular use. METHODS: We present our results from the evaluation of an NLP-driven CDSS developed and implemented in a Norwegian Hospital. The system incorporates unsupervised and supervised machine learning combined with rule-based algorithms for clinical concept-based searching to identify and classify allergies of concern for anesthesia and intensive care. The system also implements a semi-supervised machine learning approach to automatically annotate medical concepts in the narrative. RESULTS: Evaluation of system adoption was performed by a mixed methods approach applying The Unified Theory of Acceptance and Use of Technology (UTAUT) as a theoretical lens. Most of the respondents demonstrated a high degree of system acceptance and expressed a positive attitude towards the system in general and intention to use the system in the future. Increased detection of patient allergies, and thus improved quality of practice and patient safety during surgery or ICU stays, was perceived as the most important advantage of the system. CONCLUSIONS: Our combined machine learning and rule-based approach benefits system performance, efficiency, and interpretability. The results demonstrate that the proposed CDSS increases detection of patient allergies, and that the system received high-level acceptance by the clinicians using it. Useful recommendations for further system improvements and implementation initiatives are reducing the quantity of alarms, expansion of the system to include more clinical concepts, closer EHR system integration, and more workstations available at point of care.

Efficacy and side effects of intravenous remifentanil patient-controlled analgesia used in a stepwise approach for labour: an observational study.

BACKGROUND: Remifentanil has a suitable pharmacological profile for labour analgesia. In this prospective, observational study, intravenous patient-controlled analgesia with remifentanil, using stepwise bolus doses without background infusion, was examined during the first and second stages of labour. Outcomes were pain reduction, maternal satisfaction, maternal and neonatal side effects and remifentanil metabolism in the neonate. METHODS: Parturients with normal term singleton pregnancies were recruited. The initial remifentanil bolus dose was 0.15 µg/kg, increasing in steps of 0.15 µg/kg, with a 2-min lock-out. Pain scores using a 100 mm visual analogue scale, systolic and diastolic blood pressures, respiratory rate and maternal sedation were recorded every 15 min. Maternal oxygen saturation and heart rate were monitored continuously. Neonatal data included Apgar scores, clinical examination, naloxone use, resuscitation, umbilical cord blood gases and remifentanil concentrations. RESULTS: Forty-one parturients were enrolled. Pain scores were significantly reduced in the first 3 h of patient-controlled analgesia use compared to baseline, and at the end of the first and second stages of labour (P<0.05). Maximal pain reduction was 60% (P<0.01). One patient had inadequate pain relief and converted to epidural analgesia. The mean highest dose of remifentanil was 0.7 µg/kg [range 0.3-1.05]. Ninety-three percent of patients were satisfied with their analgesia. The lowest oxygen saturation was 91% and the lowest respiratory rate was 9 breaths/min. Eleven parturients (27%) received supplemental oxygen due to oxygen saturations <92%. Maternal sedation was moderate, and neonatal data reassuring. CONCLUSIONS: Remifentanil intravenous patient-controlled analgesia provides adequate pain relief and high maternal satisfaction during the first and second stages of labour. Maternal sedation and respiratory depression may occur, but no serious neonatal side effects were recorded. Careful monitoring is mandatory.

Analgesia for labour: a survey of Norwegian practice - with a focus on parenteral opioids.

BACKGROUND: During the last two decades, epidural analgesia has become 'a gold standard' for labour pain in most Western countries. Newer short-acting opioids given systemically represent an alternative for adequate pain relief without using regional techniques. With this survey, we wish to explore how Norwegian hospitals practice labour analgesia, especially their use of systemic opioids. METHODS: A questionnaire was sent to the head of all 46 registered Norwegian labour units in 2005. The questionnaire focused on epidural and the use of systemic opioids. In 2008, the same questionnaire was sent to the 19 largest units reporting >1000 births a year, seeking updated information. RESULTS: Forty-three of the 46 original questionnaires were returned. An epidural frequency of 25.9% was registered. For epidural treatment, bupivacaine was the preferred local anaesthetic, while sufentanil was the opioid of choice for the majority of units. Pethidine was the most commonly used opioid for systemic administration (77%). All units reported nurse administration of systemic opioids. The intramuscular route was most commonly used, either alone (58%) or in combination with an intravenous (i.v.) administration (34%). Only one unit used i.v. fentanyl. There were only minor changes with the repeated survey, except for one large unit, which reported over a 50% increase in the epidural frequency. CONCLUSION: In Norway, the frequency of epidural for labour analgesia is still relatively low, but seems to be increasing. Systemic opioids are often used instead of or as a supplement. Clinical practice seems to be conservative, and newer short-acting opioids are seldom used systemically.