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.

Effects of anaesthetic agents on gastrin-stimulated and histamine-stimulated gastric acid secretion in the totally isolated vascularly perfused rat stomach.

BACKGROUND: Anaesthetic agents affect gastric acid secretion, but the mechanisms behind this action have not been fully evaluated. The enterochromaffin-like (ECL) cell plays a key role in the regulation of gastric acid secretion, and anaesthetic agents have recently been described as inhibiting histamine release from the ECL cell. The present study examines the effect of anaesthetic agents on the ECL cell and on parietal cell functions. METHODS: Different concentrations of urethane, pentobarbital and a mixture of fluanisone/fantanyl/midazolam (FFM) were examined for the effect on gastrin-stimulated histamine release and acid secretion and on histamine-stimulated acid secretion in the totally isolated vascularly perfused rat stomach. The luminal acid output and histamine concentrations in venous effluents were measured by titration and radioimmunoassay, respectively. RESULTS: Pentobarbital caused an inhibition on both histamine release and acid output in gastrin-stimulated stomachs in a concentration-dependent way. The mixture of FFM at higher concentrations inhibited histamine release from the ECL cell and luminal H+ output in gastrin-stimulated acid secretion. Urethane exerted a slight inhibitory effect on histamine release only at the lowest concentration. Pentobarbital also reduced histamine-stimulated gastric acid secretion, while the mixture of FFM did not. CONCLUSIONS: pentobarbital inhibits acid secretion both by reducing ECL cell histamine release and parietal cell H+ secretion, whereas FFM inhibits acid secretion by interaction with the ECL cell only. Urethane also had a slight inhibitory effect on the ECL cell histamine release at the lowest concentration.

Glycine-extended gastrin-17 stimulates acid secretion only via CCK-2 receptor-induced histamine release in the totally isolated vascularly perfused rat stomach.

The effects of gastrin precursors have been discussed during recent years. However, the mechanism for their action, whether through a novel receptor on the parietal cell or a cholecystokinin-2 (CCK-2) receptor on the enterochromaffin like (ECL) cells, is still not settled. This study examines the effect of glycine-extended gastrin-17 (Gly-G-17), the main non-amidated gastrin precursor, on gastric acid secretion and histamine release in the totally isolated vascularly perfused rat stomach. Glycine-extended gastrin-17 at the concentrations from 0.52 to 520 nmol L(-1) was administered to the totally isolated vascularly perfused rat stomach. Glycine-extended gastrin-17 at 52 or 520 nmol L(-1), and gastrin-17 at 0.52 nmol L(-1)were co-administered to examine whether glycine-extended gastrin augmented maximal gastrin stimulated acid secretion and histamine release. Both Gly-G-17 at 52 nmol L(-1) and gastrin-17 (G-17) at 0.52 nmol L(-1) were administered together with the histamine-2 receptor antagonist ranitidine at 10 micromol L(-1). Gastric acid and venous histamine output were measured. Glycine-extended gastrin-17 at lower concentrations from 0.52 to 5.2 nmol L(-1) did not stimulate gastric acid output or histamine release, whereas higher concentrations from 52 to 520 nmol L(-1) elicited a concentration-dependent increase in acid secretion and histamine release. The outputs of acid and histamine at 520 nmol L(-1) Gly-G-17 were at the same level as those found for G-17 at its maximally effective concentration of 0.52 nmol L(-1). Glycine-extended gastrin-17 at maximally effective concentration of 520 nmol L(-1) did not augment maximal gastrin stimulated acid secretion or histamine release. Ranitidine inhibited G-17 and Gly-G-17 stimulated acid secretion to a similar degree. This study confirms that the stimulatory effect of Gly-G-17 on gastric acid secretion is via a CCK-2 receptor on the ECL cell.

PACAP stimulates gastric acid secretion in the rat by inducing histamine release.

Previous studies have shown that pituitary adenylate cyclase-activating peptide (PACAP) stimulates enterochromaffin-like (ECL) cell histamine release, but its role in the regulation of gastric acid secretion is disputed. This work examines the effect of PACAP-38 on aminopyrine uptake in enriched rat parietal cells and on histamine release and acid secretion in the isolated vascularly perfused rat stomach and the role of PACAP in vagally (2-deoxyglucose) stimulated acid secretion in the awake rat. PACAP has no direct effect on the isolated parietal cell as assessed by aminopyrine uptake. PACAP induces a concentration-dependent histamine release and acid secretion in the isolated stomach, and its effect on histamine release is additive to gastrin. The histamine H2 antagonist ranitidine potently inhibits PACAP-stimulated acid secretion without affecting histamine release. Vagally stimulated acid secretion is partially inhibited by a PACAP antagonist. The results from the present study strongly suggest that PACAP plays an important role in the neurohumoral regulation of gastric acid secretion. Its effect seems to be mediated by the release of ECL cell histamine.