Using artificial intelligence to reduce orthopedic surgical site infection surveillance workload: Algorithm design, validation, and implementation in 4 Spanish hospitals.

BACKGROUND: Surgical site infection (SSI) surveillance is a labor-intensive endeavor. We present the design and validation of an algorithm for SSI detection after hip replacement surgery, and a report of its successful implementation in 4 public hospitals in Madrid, Spain. METHODS: We designed a multivariable algorithm, AI-HPRO, using natural language processing (NLP) and extreme gradient boosting to screen for SSI in patients undergoing hip replacement surgery. The development and validation cohorts included data from 19,661 health care episodes from 4 hospitals in Madrid, Spain. RESULTS: Positive microbiological cultures, the text variable "infection", and prescription of clindamycin were strong markers of SSI. Statistical analysis of the final model indicated high sensitivity (99.18%) and specificity (91.01%) with an F1-score of 0.32, AUC of 0.989, accuracy of 91.27%, and negative predictive value of 99.98%. DISCUSSION: Implementation of the AI-HPRO algorithm reduced the surveillance time from 975 person/hours to 63.5 person/hours and permitted an 88.95% reduction in the total volume of clinical records to be reviewed manually. The model presents a higher negative predictive value (99.98%) than algorithms relying on NLP alone (94%) or NLP and logistic regression (97%). CONCLUSIONS: This is the first report of an algorithm combining NLP and extreme gradient-boosting to permit accurate, real-time orthopedic SSI surveillance.

Impact of sink removal from intensive care unit rooms on the consumption of antibiotics and on results of Zero Resistance Project.

INTRODUCTION: Due to the favourable impact of removing the sinks on isolations in bronchoaspirate samples of patients with mechanical ventilation, we now evaluate the impact on the consumption of antibiotics as well as on the results of the Zero Resistance Project (ZRP). PATIENTS AND METHODS: All the patients admitted to the unit in a quasi-experimental before-after study with a pre-intervention period between 2014 and 2016 and a post-intervention period from 2016 to 2017, to evaluate antibiotic consumption in defined daily doses, and until 2018, to evaluate the ZRP indicators. The intervention was the removal of the sinks from the rooms of the ICU. We evaluated antibiotic consumption densities and their ratios, grouped as Enterobacteriaceae and non-fermenting gram-negative bacilli (NFGNB) according to their antibiograms; the absolute number of 'antibiotic days', 'hospitalised days', 'isolation days', and 'multi-resistant bacteria (MRB) days'; as well as their incidence densities per 1000 hospitalised days and the ratio between the two years prior to and the two years after the intervention. RESULTS: Post-intervention antibiotic use was 1.61-fold (1.60-1.62) and 2.24-fold (2.10-2.37) lower for antibiotics used against Enterobacteriaceae and NFGNB, respectively. There were also reductions in the number of days of antibiotic use by 1.29-fold (1.22-1.36), number of MRB days by 1.84-fold (1.63-2.08), and number of patient isolation days by 1.51-fold (1.38-1.66). DISCUSSION: The results suggest that the intervention had a favourable impact on the consumption of antibiotics, as well as on the number of days on antibiotics, MRB, and isolation.

Transcutaneous Supraorbital Stimulation as a Preventive Treatment for Chronic Migraine: A Prospective, Open-Label Study.

BACKGROUND AND OBJECTIVE: Successful preventive treatment in chronic migraine (CM) remains an unmet need in some cases, and new therapeutic strategies are emerging. We aimed to test the effect of noninvasive, transcutaneous supraorbital nerve stimulation (tSNS) in a group of patients with CM. PATIENTS AND METHODS: This was an open label, quasi-experimental design. Twenty-five CM patients were recruited from two hospital headache clinics. After a one-month baseline period, monthly visits were scheduled during three months. Headache occurrence, its intensity, and symptomatic medication intake were recorded through a diary kept by each patient. Both a per-protocol analysis and an intention-to-treat analysis were performed for the main outcome measures. RESULTS: Twenty-one and 24 patients were included in the per-protocol and the intention-to-treat analyses, respectively. In the per-protocol analysis, a significant four-day decrease in the mean monthly days with moderate or severe headache was observed from baseline to the end of the study (t test, P = 0.0163), and there was a nonsignificant reduction of 2.95 in the mean monthly total headache days. In the intention-to-treat analysis, a nonsignificant 3.37 reduction in the mean monthly days with moderate or severe headache was observed for the same period, and there was a significant 2.75 reduction in the mean monthly days with any headache (t test, P = 0.016). CONCLUSIONS: tSNS could hold preventive properties in the treatment of CM, but the effect may be either mild or controversial. Double blind, sham-controlled studies are essential to confirm these findings and to outline their clinical relevance in the CM therapeutic scenario.

Impact of removing sinks from an intensive care unit on isolations by gram-negative non-fermenting bacilli in patients with invasive mechanical ventilation. / Impacto de la retirada de los lavabos en una unidad de cuidados intensivos sobre los aislamientos por bacilos gramnegativos no fermentadores en pacientes con ventilación mecánica invasiva.

INTRODUCTION AND OBJECTIVE: Contamination of sinks, even due to their underuse, is associated with the transmission of non-fermenting gram-negative bacilli (NFGNB) to patients in Augmented Care Units. After previous monitoring with environmental and patient samples, we now explore the impact of removing sinks from ICU cubicles on incidental isolations related to health care in bronchoaspirate samples of patients with invasive mechanical ventilation (IMV). MATERIAL AND METHODS: Quasi-experimental study, before-and-after, pre-intervention annuities April 2014-2016 and post-intervention April 2016-2017. Incidence densities per 1,000 days of IMV were studied, comparing by the exact method based on the binomial distribution and estimating the incidence density ratio. RESULTS: The incidence densities per 1,000 days of IMV of isolations by NFGNB in bronchoaspirate samples of the pre and post-intervention periods were 11.28 and 1.9, respectively. This implies a post-intervention incidence density 5.90 times lower than before (95% CI: 1.49-51.05, P=.003). CONCLUSIONS: Despite of the limitations of the design, the removal of sinks showed a reduction of the isolations.

Under-utilization of taps in intensive care unit as a cause of reservoirs of nonfermenting gram-negative bacilli. / La infrautilización de grifos en una unidad de cuidados intensivos como causa de reservorios de bacilos gramnegativos no fermentadores.

INTRODUCTION: The under-utilisation of taps is associated with the generation of reservoirs of non-fermenting gram-negative bacilli with the ability to disseminate. We describe the detection and approach of the problem in an ICU. METHODS: Observational descriptive study in an ICU with individual cubicles with their own sink. We collected clinical samples from patients and environmental samples from tap aerators and reviewed the unit's hygiene measures. RESULTS: We detected four cases due to Chryseobacterium indologenes, one to Elizabethkingia meningoseptica and another to Pseudomonas aeruginosa; they were identified both in clinical and the environmental samples. The healthcare professionals reported that almost every hand hygiene opportunity was performed with a hydroalcoholic solution. After considered the daily flushing of water outlets as inefficient, it was decided to remove them. CONCLUSIONS: National recommendations were insufficient for preventing, detecting and controlling tap contamination in units with a high risk of infection. The management of taps in these units needs to be improved.

CuidaCare: effectiveness of a nursing intervention on the quality of life's caregiver: cluster-randomized clinical trial.

BACKGROUND: In Spain, family is the main source of care for dependent people. Numerous studies suggest that providing informal (unpaid) care during a prolonged period of time results in a morbidity-generating burden. Caregivers constitute a high-risk group that experiences elevated stress levels, which reduce their quality of life.Different strategies have been proposed to improve management of this phenomenon in order to minimize its impact, but definitive conclusions regarding their effectiveness are lacking. METHODS/DESIGN: A community clinical trial is proposed, with a 1-year follow-up period, that is multicentric, controlled, parallel, and with randomized allocation of clusters in 20 health care centers within the Community of Madrid. The study's objective is to evaluate the effectiveness of a standard care intervention in primary health care (intervention CuidaCare) to improve the quality of life of the caregivers, measured at 0, 6, and 12 months after the intervention.One hundred and forty two subjects (71 from each group) ≥65 years, identified by the nurse as the main caregivers, and who provide consent to participate in the study will be included.The main outcome variable will be perceived quality of life as measured by the Visual Analogue Scale (VAS) of EuroQol-5D (EQ-5D). The secondary outcome variables will be EQ-5D Dimensions, EQ-5D Index, nursing diagnosis, and Zarit's test. Prognostic variables will be recorded for the dependent patient and the caregiver.The principle analysis will be done by comparing the average change in EQ-5D VAS value before and after intervention between the two groups. All statistical tests will be performed as intention-to-treat. Prognostic factors' estimates will be adjusted by mixed-effects regression models. Possible confounding or effect-modifying factors will be taken into account. DISCUSSION: Assistance for the caregiver should be integrated into primary care services. In order to do so, incorporating standard, effective interventions with relevant outcome variables such as quality of life is necessary. Community care nurses are at a privileged position to develop interventions like the proposed one. TRIAL REGISTRATION: This trial has been registered in ClinicalTrials.gov under code number NCT 01478295.

[Notifiable infectious diseases: knowledge and notification among hospital physicians]. / Enfermedades de declaración obligatoria: conocimiento y notificación en el ámbito hospitalario.

INTRODUCTION: Notifiable infectious diseases represent a public health hazard, which is why they are under surveillance and must be reported. We tried to assess hospital physicians' knowledge of hospital physicians on notifiable infectious diseases and their self-reported attitudes to notification. METHODS: An observational study was conducted using a questionnaire with 11 multiple choice questions, two yes/no questions and one short-answer question. It was distributed to all senior doctors and residents in 19 medical and surgical departments. RESULTS: A total of 248 questionnaires were sent out, with a response rate of 79.84%. More than three-quarters (76.3%) of the respondents were senior doctors. As regards specific knowledge about whether a particular disease is a notifiable disease, 29.5% identified correctly 100% of the named diseases, 3.2% could not identify any of them. All urgent named notifiable infectious diseases were correctly identified by 25.3% of physicians. Statistically significant differences were found in the knowledge of notifiable diseases knowledge in medical and surgical departments, as well as for senior doctors (P=.047) and residents (P=.035). A high percentage of medical services (40%) and surgical (70%) department reported never failing to notify. When asked about the causes of under-reporting, 72% did not know whether notification was mandatory or not, and 88% did not know what diseases must be notified. CONCLUSIONS: Although many respondents are aware that diseases notification is part of their daily activity, many of them admit under-reporting. There is insufficient knowledge about what diseases are considered notifiable infectious diseases and how to notify them.

[Preoperative preparation, antibiotic prophylaxis and surgical wound infection in breast surgery]. / Preparación prequirúrgica, profilaxis antibiótica y vigilancia de infección de herida quirúrgica en cirugía de mama.

INTRODUCTION: The impact of surgical wound infection on public health justifies its surveillance and prevention. Our objectives were to estimate the incidence of surgical wound infection in breast procedures and assess its protocol of antibiotic prophylaxis and preoperative preparation. METHODS: Observational multicentre prospective cohort study of incidence of surgical wound infection. Incidence was evaluated, stratified by National Nosocomial Infection Surveillance (NNIS) risk index and we calculated the standardized incidence ratio (SIR). The SIR was compared with Spanish rates and U.S. rates. The compliance and performance of the antibiotic prophylaxis and preoperative preparation protocol were assessed and their influence in the incidence of infection with the relative risk. RESULTS: Ten hospitals from the Comunidad de Madrid were included, providing 592 procedures. The cumulative incidence of surgical wound infection was 3.89% (95% CI: 2.3-5.5). The SIR was 1.82 on the Spanish rate and 2.16 on the American. Antibiotic prophylaxis was applied in 97.81% of cases, when indicated. The overall performance of antibiotic prophylaxis was 75%, and 53% for preoperative preparation. No association was found between infection and performance of prophylaxis or preoperative preparation (P>.05). CONCLUSION: Our incidence is within those seen in the literature although it is somewhat higher than the national surveillance programs. The performance of prophylaxis antibiotic must be improved, as well as the recording of preoperative preparation data.