Current Issue : January - March Volume : 2020 Issue Number : 1 Articles : 6 Articles
Background: The rapid development in big data analytics and the data-rich environment of intensive care units\ntogether provide unprecedented opportunities for medical breakthroughs in the field of critical care. We developed\nand validated a machine learning-based model, the Pediatric Risk of Mortality Prediction Tool (PROMPT), for realtime\nprediction of all-cause mortality in pediatric intensive care units.\nMethods: Utilizing two separate retrospective observational cohorts, we conducted model development and\nvalidation using a machine learning algorithm with a convolutional neural network. The development cohort\ncomprised 1445 pediatric patients with 1977 medical encounters admitted to intensive care units from January\n2011 to December 2017 at Severance Hospital (Seoul, Korea). The validation cohort included 278 patients with 364\nmedical encounters admitted to the pediatric intensive care unit from January 2016 to November 2017 at Samsung\nMedical Center.\nResults: Using seven vital signs, along with patient age and body weight on intensive care unit admission, PROMPT\nachieved an area under the receiver operating characteristic curve in the range of 0.89-0.97 for mortality prediction\n6 to 60 h prior to death. Our results demonstrated that PROMPT provided high sensitivity with specificity and\noutperformed the conventional severity scoring system, the Pediatric Index of Mortality, in predictive ability. Model\nperformance was indistinguishable between the development and validation cohorts.\nConclusions: PROMPT is a deep model-based, data-driven early warning score tool that can predict mortality in\ncritically ill children and may be useful for the timely identification of deteriorating patients....
Background and aims: Innovative treatment modalities have not yet shown a clinical benefit in patients with\nseptic shock. To reduce severe cytokinaemia, CytoSorb as an add-on to continuous renal replacement therapy\n(CRRT) showed promising results in case reports. However, there are no clinical trials investigating outcomes.\nMethods: In this investigator-initiated retrospective study, patients with septic shock were treated with CRRT +\nCytoSorb (n = 67) or CRRT alone (n = 49). The primary outcome was the 28-day all-cause mortality rate. Patients\nwere weighted by stabilized inverse probability of treatment weights (sIPTW) to overcome differences in baseline\ncharacteristics.\nResults: At the start of therapy, CytoSorb-treated patients had higher lactate levels (p < 0.001), lower mean arterial\npressure (p = 0.007) and higher levels of noradrenaline (p < 0.001) compared to the CRRT group. For CytoSorb, the\nmean predicted mortality rate based on a SOFA of 13.8 (n = 67) was 75% (95%CI 71â??79%), while the actual 28-day\nmortality rate was 48% (mean difference - 27%, 95%CI - 38 to - 15%, p < 0.001). For CRRT, based on a SOFA of 12.8\n(n = 49), the mean predicted versus observed mortality was 68% versus 51% (mean difference - 16.9% [95%CI -\n32.6 to - 1.2%, p = 0.035]). By sIPTW analysis, patients treated with CytoSorb had a significantly lower 28-day\nmortality rate compared to CRRT alone (53% vs. 72%, respectively, p = 0.038). Independent predictors of 28-day\nmortality in the CytoSorb group were the presence of pneumosepsis (adjusted odds ratio [aOR] 5.47, p = 0.029),\nhigher levels of lactate at the start of CytoSorb (aOR 1.15, p = 0.031) and older age (aOR per 10 years 1.67, p = 0.034).\nConclusions: CytoSorb was associated with a decreased observed versus expected 28-day all-cause mortality. By\nIPTW analysis, intervention with CytoSorb may be associated with a decreased all-cause mortality at 28 days\ncompared to CRRT alone....
Background: Nowadays, healthcare professionals worldwide deliver care for increasing numbers of culturally and\nlinguistically diverse patients. The importance of cultural competence is evident in terms of the quality of\nhealthcare, and more knowledge is needed about different educational models and approaches that aim to\nincrease cultural competence. This study examines the perceptions of nurses about the content and utility of\ncultural competence training that focuses on increasing awareness of oneâ??s own cultural features.\nMethods: The training was conducted at one primary care hospital in southern Finland. Participants were\nregistered nurses (n = 14) and practical nurses (n = 6) from different hospital units. Four 4-h training sessions-\nincluding lectures, discussions and short web-based learning tasks-were arranged during a four-week period.\nSemi-structured, small group interviews were conducted with 10 participants to examine their perceptions about\nthe content and utility of the training. Qualitative content analysis with a conventional approach was used to\nanalyse the data.\nResults: Perceptions about the training were divided into three main categories: general utility of the training,\npersonal utility of the training, and utility of the training for patients. General utility pertains to the general approach that\nthe training provided on cross-cultural care, the possibility to initiate an open discussion, and the opportunity to improve\ncurrent practices. Personal utility pertains to the opportunity to become aware of oneâ??s own cultural features, to change\noneâ??s way of thinking, to obtain a new perspective on oneâ??s own communication practices and to receive justification for\ncarrying out particular workable practices. Utility for patients pertains to fostering better awareness and acknowledgement\nof patientsâ?? differing cultural features and an increased respect in healthcare delivery. Additionally, the quality of the\ntraining was highlighted, and suggestions for improvement were offered.\nConclusion: Training that increases healthcare professionalsâ?? awareness of their own cultural features was perceived as\nuseful and thought-provoking. Increased awareness might facilitate the communication between healthcare professionals\nand patients, which is a crucial component of quality healthcare. It seems that in the future, training opportunities that\nallow larger groups to participate are needed, regardless of the time and place, and utilising the potential of e-learning\nshould be considered....
Background: Medication errors are a serious and complex problem in clinical practice, especially in intensive care\nunits whose patients can suffer potentially very serious consequences because of the critical nature of their diseases\nand the pharmacotherapy programs implemented in these patients. The origins of these errors discussed in the\nliterature are wide-ranging, although far-reaching variables are of particular special interest to those involved in\ntraining nurses. The main objective of this research was to study if the level of knowledge that critical-care nurses\nhave about the use and administration of medications is related to the most common medication errors.\nMethods: This was a mixed (multi-method) study with three phases that combined quantitative and qualitative\ntechniques. In phase 1 patient medical records were reviewed; phase 2 consisted of an interview with a focus\ngroup; and an ad hoc questionnaire was carried out in phase 3.\nResults: The global medication error index was 1.93%. The main risk areas were errors in the interval of\nadministration of antibiotics (8.15% error rate); high-risk medication dilution, concentration, and infusion-rate errors\n(2.94% error rate); and errors in the administration of medications via nasogastric tubes (11.16% error rate).\nConclusions: Nurses have a low level of knowledge of the drugs they use the most and with which a greater\nnumber of medication errors are committed in the ICU....
Background: Nursing care closely influences patientsâ?? satisfaction with the overall quality of care, and the importance\nof measuring patient satisfaction with nursing care cannot be emphasized enough. Data are however scarce regarding\npatientsâ?? perception of quality of nursing care in Ethiopia. We performed this study to assess patientâ??s perception of the\nquality of nursing care in a tertiary center in Ethiopia.\nMethods: Data were collected prospectively using Quality of Nursing Care Questionnaires-patient of Safford & Schlotfeldt.\nA total of 340 patients were included using systematic random sampling and data were analyzed using SPSS for windows\nversion- 20.\nResult: The nursing care performance was highest for nurse-physician relation (mean = 3.95) and low for education and\nhome care preparation and physical care (mean score of 2.79 and 2.89 respectively). The emotional care and nurse\nadministration mean score were 3.5 and 3.83 respectively. The overall nursing quality was neither satisfying nor\ndissatisfying (mean of 3.39). While only 36% of the respondents were satisfied with the nursing care, patient\neducation has the strongest (AOR of 7.4) association with satisfaction.\nConclusion: Patients perceived low quality of physical care, education and preparation for home care but\nbetter nurse-physician relation and nursing administration. However the overall quality measure was neither\nsatisfying nor dissatisfying. This calls for an action from the health care administrators, educators and other\nstakeholders to improve the patient perception of quality nursing care....
Older adults with dementia are increasing in Japan. Because of this, â??communication\nrobotsâ? are being introduced into nursing settings to substitute\nfor the shortage of nurses and other care workers. Our research group is currently\ndeveloping a humanoid nursing robot with caring function (HNR),\nspecifically for the functional and practical use of older adults with dementia.\nThe purpose of this study was to clarify improvement points of the current\nfunction of humanoid robotâ??s (Pepper) (SoftBank Robotics) dialog pattern for\nimproving optimal communication between humanoid robot and older adults.\nDialog programs were installed in the humanoid robot Pepper, including the\napplication program Care Prevention Gymnastics Exercises for Pepper (Pepper-\nCPGE) that was made by Xing Company, Japan. Dialogues between older\nadults and Pepper-CPGE were recorded by video camera. Data from transcriptions\nof the conversations captured from video and from field notes were\nanalyzed focusing on human-robot interaction. From the recorded scenes and\nconversations, the following were points to be improved: 1) Intonation of the\nwords vocalized by Pepper-CPGE was different from that expected by the\nolder adult resulted in inappropriate responses by the older adult; 2) The\ntiming between Pepperâ??s questions and the responses of the older adult were\nnot timely and did not match (differences in the question-response time),\nwhich lead to confusion among the older adults; and 3) Other surroundings\nolder adults were interested in the dialogue with Pepper-CPGE. However,\nPepper-CPGE cannot communicate with multiple older adults. Improving Pepper-CPGEâ??s ability to communicate with multiple older adults as an older\nadultâ??s dialogue with Pepper-CPGE can cause other older adults to also interact\nnot only with the older adult that Pepper-CPGE is interacting with but\nalso with Pepper-CPGE. This study shows that transactive relations among\nhumanoid robots and older adults can be facilitated. Improving communication\nbetween humanoid robots and the older adults by optimizing a structured\ndialogue is needed to enhance appropriate engagement and participation.\nIt is necessary to create a â??Caring dialogue Databaseâ? for HNRs in order\nto know the patient/client and to share the aesthetic experiences of human-\nrobot interactions. Also, it is important to develop a dialog pattern that\nenables humanoid robots to sympathize with older adults....
Loading....