Current perspectives on the use of artificial intelligence in critical patient safety

Intensive Care Units (ICUs) have undergone enhancements in patient safety, and artificial intelligence (AI) emerges as a disruptive technology offering novel opportunities. While the published evidence is limited and presents methodological issues, certain areas show promise, such as decision support systems, detection of adverse events, and prescription error identification. The application of AI in safety may pursue predictive or diagnostic objectives. Implementing AI-based systems necessitates procedures to ensure secure assistance, addressing challenges including trust in such systems, biases, data quality, scalability, and ethical and confidentiality considerations. The development and application of AI demand thorough testing, encompassing retrospective data assessments, real-time validation with prospective cohorts, and efficacy demonstration in clinical trials. Algorithmic transparency and explainability are essential, with active involvement of clinical professionals being crucial in the implementation process.

A systematic review of the application of machine-learning algorithms in multiple sclerosis

INTRODUCTION

The applications of artificial intelligence, and in particular automatic learning or "machine learning" (ML), constitute both a challenge and a great opportunity in numerous scientific, technical, and clinical disciplines. Specific applications in the study of multiple sclerosis (MS) have been no exception, and constitute an area of increasing interest in recent years.

OBJECTIVE

We present a systematic review of the application of ML algorithms in MS.

MATERIALS AND METHODS

We used the PubMed search engine, which allows free access to the MEDLINE medical database, to identify studies including the keywords "machine learning" and "multiple sclerosis." We excluded review articles, studies written in languages other than English or Spanish, and studies that were mainly technical and did not specifically apply to MS. The final selection included 76 articles, and 38 were rejected.

CONCLUSIONS

After the review process, we established 4 main applications of ML in MS: 1) classifying MS subtypes; 2) distinguishing patients with MS from healthy controls and individuals with other diseases; 3) predicting progression and response to therapeutic interventions; and 4) other applications. Results found to date have shown that ML algorithms may offer great support for health professionals both in clinical settings and in research into MS.

Overexpression of circRNAs LRP6 in gestational diabetes mellitus predicts foetal malformation and intrauterine death

INTRODUCTION

circRNA LRP6 participates in high-glucose-regulated cellular behaviours, while its role in gestational diabetes mellitus (GDM) is unclear. Our preliminary sequencing analysis revealed the altered expression of LRP6, suggesting its potential involvement in GDM and possible clinical value. This study explored the involvement of LRP6 in GDM.

METHODS

In this study, a total of 300 pregnant women were enrolled and followed up until delivery. The occurrence of GDM and adverse outcomes was recorded. These 300 participants were grouped into high and low LRP6 level groups (n=150; cutoff=median). Occurrence of GDM and adverse outcomes were compared between the two groups. ROC curve analysis was conducted to explore the role of LRP6 expression on the day of admission in predicting GDM. Associations between LRP6 expression and adverse outcomes were analysed with the Chi-squared test.

RESULTS

We observed that participants in the high LRP6 level group experienced a higher incidence of GDM during follow-up (33/150) compared to those in the low LRP6 level group (10/150). Compared to participants who developed GDM during follow-up, participants who did not develop GDM showed lower expression levels of LRP6 in plasma. ROC curve analysis showed that high expression levels of LRP6 on the day of admission effectively distinguished potential GDM patients from other participants. Interestingly, LRP6 was only closely associated with foetal malformation and intrauterine death, but not premature delivery, hypertension, macrosomia, intrauterine distress, miscarriage and intrauterine infection in all participants.

CONCLUSION

Therefore, increased expression levels of LRP6 in GDM predicts foetal malformation and intrauterine death.

Utilizing the lymphocyte-monocyte ratio in predicting the recurrence of spontaneous pneumothorax

OBJECTIVE

Lymphocyte-to-monocyte ratio (LMR) has been introduced as a predictor and a prognostic factor for multiple diseases. This study aimed to determine the efficiency of LMR in predicting the recurrence of spontaneous pneumothorax.

MATERIALS AND METHODS

A total of 374 patients who had received chest tubes at the first episode of primary spontaneous pneumothorax were examined in terms of age, gender, side of the pneumothorax, status of recurrence, LMRs at the time of admittance and recurrence, and the interval until the recurrence.

RESULTS

Recurrence was diagnosed in 106 (28.3%) patients, whereas the mean time until the recurrence was 15.32 ± 5.57 months. Significantly, the recurrence rate was higher, while the time until the relapse was shorter for patients with elevated levels of LMR. Moreover, LMR counting over 1.25 demonstrated a 70.8% sensitivity and a 94.4% specificity in predicting a potential recurrence.

CONCLUSIONS

Calculation of LMR at the first episode of spontaneous pneumothorax contributes to predict a potential recurrence when combined with traditional risk factors.

Multivariable prediction models for difficult direct laryngoscopy: Systematic review and literature metasynthesis

CONTEXT

The difficult airway is an important scenario in anaesthesia due to the impact of its potential complications, and the difficulty in predicting its presence in current clinical practice.

METHODS

Systematic review of articles in English and Spanish retrieved from MEDLINE (Ovid), LILACS and EMBASE up to March 2018. The search strategy was defined by the authors. The reviewers uploaded the studies to specially designed tables in order to qualitatively analyse the results of each paper.

RESULTS

A total of 3602 studies were identified. Thirty-four of these were included in the qualitative review. The most commonly used definition of difficulty was the Cormack-Lehane 3 or 4 classification, with a weighted mean incidence of 7.23%. The most relevant finding was the methodological weaknesses in obtaining these scales.

CONCLUSIONS

Available prediction models show limited discrimination, and weaknesses were detected in the methodology used to develop these prediction rules.

Multivariable prediction models for difficult direct laryngoscopy: Systematic review and literature metasynthesis

CONTEXT

The difficult airway is an important scenario in anaesthesia due to the impact of its potential complications, and the difficulty in predicting its presence in current clinical practice.

METHODS

Systematic review of articles in English and Spanish retrieved from MEDLINE (Ovid), LILACS and Embase up to March 2018. The search strategy was defined by the authors. The reviewers uploaded the studies to specially designed tables in order to qualitatively analyse the results of each paper.

RESULTS

A total of 3602 studies were identified. Thirty-four of these were included in the qualitative review. The most commonly used definition of difficulty was the Cormack-Lehane3 or 4 classification, with a weighted mean incidence of 7.23%. The most relevant finding was the methodological weaknesses in obtaining these scales.

CONCLUSIONS

Available prediction models show limited discrimination, and weaknesses were detected in the methodology used to develop these prediction rules.

Computed tomographic features of coronavirus disease-2019 (COVID-19) pneumonia in three groups of Iranian patients: A single center study

Introduction and objectives

The pivotal role of chest computed tomographic (CT) to diagnosis and prognosis coronavirus disease-2019 (COVID-19) is still an open field to be explored. This study was conducted to assess the CT features in confirmed cases with COVID-19.

Materials and methods

Retrospectively, initial chest CT data of 363 confirmed cases with COVID-19 were reviewed. All subjects were stratified into three groups based on patients’ clinical outcomes; non-critical group (n = 194), critical group (n = 65), and death group (n = 104). The detailed of CT findings were collected from patients’ medical records and then evaluated for each group. In addition, multinomial logistic regression was used to analyze risk factors according to CT findings in three groups of patients with COVID-19.

Results

Compared with the non-critical group, mixed ground-glass opacities (GGO) and consolidation lesion, pleural effusion lesion, presence of diffuse opacity in cases, more than 2 lobes involved and opacity scores were significantly higher in the critical and death groups (P < 0.05). Having more mixed GGO with consolidation, pleural effusion, lack of pure GGO, more diffuse opacity, involvement of more than 2 lobes and high opacity score identified as independent risk factors of critical and death groups.

Conclusion

CT images of non-critical, critical and death groups with COVID-19 had definite characteristics. CT examination plays a vital role in managing the current COVID-19 outbreak, for early detection of COVID-19 pneumonia. In addition, initial CT findings may be useful to stratify patients, which have a potentially important utility in the current global medical situation.

Computed tomographic features of coronavirus disease-2019 (COVID-19) pneumonia in three groups of Iranian patients: A single center study

INTRODUCTION AND OBJECTIVES

The pivotal role of chest computed tomographic (CT) to diagnosis and prognosis coronavirus disease-2019 (COVID-19) is still an open field to be explored. This study was conducted to assess the CT features in confirmed cases with COVID-19.

MATERIALS AND METHODS

Retrospectively, initial chest CT data of 363 confirmed cases with COVID-19 were reviewed. All subjects were stratified into three groups based on patients' clinical outcomes; non-critical group (n=194), critical group (n=65), and death group (n=104). The detailed of CT findings were collected from patients' medical records and then evaluated for each group. In addition, multinomial logistic regression was used to analyze risk factors according to CT findings in three groups of patients with COVID-19.

RESULTS

Compared with the non-critical group, mixed ground-glass opacities (GGO) and consolidation lesion, pleural effusion lesion, presence of diffuse opacity in cases, more than 2 lobes involved and opacity scores were significantly higher in the critical and death groups (P<0.05). Having more mixed GGO with consolidation, pleural effusion, lack of pure GGO, more diffuse opacity, involvement of more than 2 lobes and high opacity score identified as independent risk factors of critical and death groups.

CONCLUSION

CT images of non-critical, critical and death groups with COVID-19 had definite characteristics. CT examination plays a vital role in managing the current COVID-19 outbreak, for early detection of COVID-19 pneumonia. In addition, initial CT findings may be useful to stratify patients, which have a potentially important utility in the current global medical situation.

A systematic review of the application of machine-learning algorithms in multiple sclerosis

INTRODUCTION

The applications of artificial intelligence, and in particular automatic learning or "machine learning" (ML), constitute both a challenge and a great opportunity in numerous scientific, technical, and clinical disciplines. Specific applications in the study of multiple sclerosis (MS) have been no exception, and constitute an area of increasing interest in recent years.

OBJECTIVE

We present a systematic review of the application of ML algorithms in MS.

MATERIALS AND METHODS

We used the PubMed search engine, which allows free access to the MEDLINE medical database, to identify studies including the keywords "machine learning" and "multiple sclerosis." We excluded review articles, studies written in languages other than English or Spanish, and studies that were mainly technical and did not specifically apply to MS. The final selection included 76 articles, and 38 were rejected.

CONCLUSIONS

After the review process, we established 4 main applications of ML in MS: 1) classifying MS subtypes; 2) distinguishing patients with MS from healthy controls and individuals with other diseases; 3) predicting progression and response to therapeutic interventions; and 4) other applications. Results found to date have shown that ML algorithms may offer great support for health professionals both in clinical settings and in research into MS.

[Predictive models of the COVID-19 epidemic in Spain with Gompertz curves]

Durante la crisis de salud internacional provocada por la pandemia de COVID-19, además de conocer los datos sobre contagios, muertes y ocupación de camas hospitalarias también es necesario hacer predicciones que ayuden a la gestión de la crisis por parte de las autoridades sanitarias. El presente trabajo tiene como objetivo describir la metodología utilizada para la elaboración de modelos predictivos de contagios y defunciones para la epidemia de COVID-19 en España basados en curvas de Gompertz. La metodología se aplica al total del país y a cada una de sus comunidades autónomas. De acuerdo con los datos oficiales publicados a la fecha de realización de este trabajo, y a través de los modelos descritos, estimamos un total de alrededor de 240.000 contagiados y 25.000 fallecidos al final de la epidemia. Pronosticamos el final de la epidemia entre los meses de junio y julio de 2020.

Preoperative prediction of autologous hamstring graft diameter in anterior cruciate ligament reconstruction

BACKGROUND AND OBJECTIVE

Currently, there is no stablished pre-operative model that helps the orthopaedic surgeon predict the final graft diameter in anterior cruciate ligament reconstruction (ACLR). The purpose of this study was to determine whether there is a correlation between semitendinosus (ST) and gracilis (GT) cross-sectional area (CSA) evaluated pre-operatively in mm² using magnetic resonance imaging (MRI) and the final intra-operative ST-GT autograft diameter in mm².

METHODS

A retrospective study was designed, 89 patients undergoing ACLR with hamstring autograft participated. We analysed ST-CSA (mm²) and GT-CSA (mm²) using pre-operative MRI, intra-operative autograft diameter, age, sex, side of the injury, weight, height and body mass index (BMI).

RESULTS

A moderate-strong correlation was identified between final autograft diameter and ST-GT CSA in MRI (Pearson correlation coefficient .6911 P<.001). We observed that, if the combination of ST-CSA and GT-STA is at least 19mm², the probability of obtaining an autograft with a diameter greater than or equal to 8mm is 91.8% or more. The ROC curve analysis demonstrated, in this model, that this predictive method on MRI correctly discriminates in over 95.6% of cases between achieving or otherwise an autograft greater than or equal to 8mm during surgery. Intra and interobserver concordance of the MRI measurements were excellent, as shown in the intraobserver intraclass correlation coefficient (CCI) of .79 and the interobserver CCI of .84 and .77 for the ST and GT respectively.

CONCLUSIONS

Preoperative determinations of ST-CSA and GT-CSA (mm²) using MRI correlate with the final autograft diameter. This method represents a reliable and reproducible model to predict the hamstring autograft diameter in ACLR.

LEVEL OF EVIDENCE

Retrospective cohort study, level IV.

CLINICAL RELEVANCE

A review of the available literature reveals a higher risk of ACL failure or re-rupture if the graft is smaller than 8mm in diameter. Despite being an important factor there is no established pre-operative model that predicts the final graft diameter. Knowing beforehand the possibilities of obtaining a hamstring autograft with a diameter greater than or equal to 8mm would help the orthopaedic surgeon to better plan the surgery and to anticipate the need for other graft options (such as bone-patellar-tendon-bone autograft or allografts, amongst other alternatives).

Prophylaxis of venous thromboembolism disease in patients with cancer

Thrombotic risk should always be assessed in the various clinical scenarios of patients with cancer. Thromboprophylaxis with low-molecular-weight heparin is recommended above other anticoagulants for most patients with cancer who are hospitalised. However, the safety of primary thromboprophylaxis in this context is unknown; however, thromboprophylaxis can be completed with mechanical methods. Thromboprophylaxis in outpatients who are treated with chemotherapy is not indicated, except for outpatients who have other factors that determine a high thrombotic risk. In these cases, prophylaxis such as apixaban, rivaroxaban and low-molecular-weight heparin may be employed, provided there are no significant risk factors for bleeding or drug interactions. In patients undergoing oncologic surgery, thromboprophylaxis should be started before the surgery, continuing for at least 7 to 10 days and, in cases of major surgery, even up to 4 weeks. Drug prophylaxis is not routinely recommended to prevent upper extremity thrombosis in patients who carry central venous catheters.

Cancer of the digestive system in Veracruz. The magnitude of the problem by 2025

INTRODUCTION

Malignant tumors of the digestive system are a public health problem with epidemiologic variations attributed to factors resulting from the aging of the population and lifestyle changes. Therefore, estimating the future magnitude of the problem is prudent.

AIM

To determine the epidemiologic projection up to 2025 of malignant tumors of the digestive system in Veracruz.

MATERIALS AND METHODS

A predictive, analytic, observational study was conducted on patients belonging to the Public health sector of Veracruz that presented with digestive system cancer, within the time frame of 2000-2016, carrying out a disease projection up to 2025. The IBM SPSS 22.0 program was utilized for the statistical analysis, employing simple linear regression. A comparative analysis of the data was carried out and results are shown in scatter graphs.

RESULTS

A total of 2,540 cases were included in the study. Mean patient age was 63.25±13.43, with a predominance of men at 56.65%. The most frequent tumor locations were in the colon and rectum (25.04%), liver (23.66%), and stomach (21.93%). Less frequent sites were the esophagus (4.88%) and small bowel (5.08%). A general 7.63% increase in the disease was predicted for 2025, with increases to 11.51% for esophageal cancer, 7.22% for gastric cancer, 9.09% for colorectal cancer, 5.98% for liver cancer, 7.88% for pancreatic cancer, and 6.86% for cancer of the gallbladder and bile ducts. Only cancer of the small bowel showed a predicted decrease to 3.33%.

DISCUSSION AND CONCLUSIONS

The results of the present study predict that digestive system cancers in Veracruz will increase importantly by 2025, with colorectal cancer, hepatocellular carcinoma, and gastric cancer as the most frequent tumors, in descending order. The other cancers are estimated to maintain a discrete line of growth. In addition to predicting the behavior of those cancers, the results of the present study are useful for estimating the resources that will be needed for their care by 2025.

Proposal of a prediction score for hematoma expansion after intracerebral hemorrhage

OBJECTIVE

To propose and validate a prediction score for intracerebral hemorrhage (ICH) patients at risk of hematoma expansion (HE).

DESIGN

A retrospective observational study was designed to propose and validate the score.

SETTING

Sanxiang Road branch and Xuguan branch belonging to the Second Affiliated Hospital of Soochow University (China).

PATIENTS

A total of 317 ICH patients in Sanxiang Road branch were registered as the development cohort, and 109 ICH patients in Xuguan branch were enrolled as the validation cohort.

PROCEDURE

Independent risk factors for HE were identified using multiple logistic regression analysis. A prediction score was then proposed based on β coefficients and preliminarily verified in the validation cohort.

MAIN VARIABLES

All clinical data of the patients were compiled from the electronic medical records. Hematoma expansion was defined as an increase in hematoma volume >33% or absolute hematoma growth >6ml from the initial scan. Specific non-contrast CT(NCCT) signs were identified by two observers independently.

RESULTS

Our score demonstrated satisfactory discrimination ability for HE (area under the ROC curve 0.854 in the development cohort versus 0.893 in the validation cohort). Appropriate calibration was found in the development cohort, whereas calibration in the validation cohort was slightly lower but still within the accuracy range (maximum deviation, average deviation and P were 0.070, 0.028, 0.773, respectively, versus 0.114, 0.056, 0.156). Decision curve analysis of the score from two samples were both far from the curve of treat all and curve of treat none, which verified its security and reliability. Patients with a total score ≥4.5 were at greatest risk of HE.

CONCLUSION

The score may provide some reference and help in accurately identifying individuals at high risk of HE, allowing rapid guidance of clinical management and also serving as an aid in clinical trials.

[Optimization of the prediction of financial problems in Spanish private health companies using genetic algorithms]

OBJECTIVE

This paper presents a methodology to optimize, using Altman's Z-Score for private companies, the prediction of private companies of the Spanish health sector entering a situation of bankruptcy.

METHOD

The proposed method consists of the application of genetic algorithms (GA) to find the coefficients of the formula of the chain of ratios proposed by Altman in the version of the score for private companies which optimize the prediction for Spanish private health companies, maximizing sensitivity and specificity, and thereby reducing type I and type II errors. For this purpose, a sample of 5,903 companies from the Spanish private health sector obtained from the database of the Iberian Balance Analysis System (SABI) between 2007 and 2015 was used.

RESULTS

The results show that the predictive model obtained with the AG presents greater accuracy, sensitivity and specificity than that proposed by Altman for private companies with both test data and all sample data.

CONCLUSIONS

The most important finding of this study was to establish a methodology that can identify the optimized coefficients for the Altman Z-Score, which allows a more accurate prediction of bankruptcy in Spanish private healthcare companies.

[Nomogram to predict a poor outcome in emergency patients with sepsis and at low risk of organ damage according to Sepsis-related Organ Failure Assessment (SOFA)]

OBJECTIVES

To develop a nomograph to predict a poor outcome (death during hospitalization or a hospital stay longer than 15 days) in emergency patients with sepsis and at low risk of organ damage according to Sepsis-related Organ Failure Assessment (SOFA).

MATERIAL AND METHODS

Prospective, observational study carried out in a single universitary hospital. All patients admitted from the emergency department with sepsis and SOFA scores of 6 or lower were enrolled. We used bivariate logistic regression analysis to develop a predictive nomogram.

RESULTS

A total of 174 patients were included. Seventeen patients (9.8%) died during hospitalization and the average hospital stay was greater than 15 days in 29 (16.7%) patient. The outcome was poor in a total of 42 patients (24.1%);. Independent variables that were significantly associated with a poor outcome were SOFA score (odds ratio [OR], 1.3; 95% CI, 1.06-1.71; P<.05), C-reactive protein (CRP) concentration (OR, 1.04; 95% CI, 1.0-1.09; P<.05), N-terminal fragment of brain natriuretic peptide (NT-proBNP) concentration over 1330 ng/mL (OR, 2.64; 95% CI, 1.17-6.22; P<.05), and septic shock (OR, 8.3; 95% CI, 1.16-166.5; P<.05). For a SOFA score of 2 or more the crude OR was 4.44 (95%, CI, 1.91-10.34) and the OR adjusted for other variables was 3.08 (95% CI, 1.24-7.69).

CONCLUSION

A high percentage of patients predicted to be at low risk of organ failure had poor outcomes, associated with SOFA score, the presence of septic shock, CRP concentration, and elevated NT-proBNP concentration. The SOFA score by itself is an inadequate prognostic tool in patients at low risk of organ damage. Other clinical and analytical variables are required to complement the SOFA score.

Systematic review of kidney transplantation functional predictors

CONTEXT

Kidney transplantation from donors with expanded criteria has increased the pool of kidneys at the cost of a higher risk of short and long-term graft dysfunction. The main issue lies in determining which kidneys will offer acceptable function and survival compared with the risk represented by surgery and subsequent immunosuppression.

OBJECTIVE

The objective of our article is to review the current evidence on the tools for predicting the functionality of kidney transplantation from cadaveric donors with expanded criteria and determining the validity for their use in standard practice.

ACQUISITION OF EVIDENCE

We conducted a systematic literature review according to the PRISM criteria, through Medline (http://www.ncbi.nlm.nih.gov) and using the keywords (in isolation or in conjunction) "cadaveric renal transplantation; kidney graft function appraisal, graft function predictors". We selected prospective and retrospective series and review articles. A total of 375 articles were analysed, 39 of which were ultimately selected for review.

SUMMARY OF THE EVIDENCE

The predictors of functionality include the following: The donor risk indices; the calculation of the renal functional weight or the assessment of the nephronic mass; the measurement of vascular resistances during perfusion in hypothermia; the measurement of the donor's biomarkers in urine and in the perfusion liquid; the measurement of functional and reperfusion parameters in normothermia; and the measurement of morphological parameters (microscopic and macroscopic) of the target organ. In this article, we present an explanatory summary of each of these parameters, as well as their most recent evidence on this issue.

DISCUSSION

None of the reviewed parameters in isolation could reliably predict renal function and graft survival. There is a significant void in terms of the macroscopic assessment of kidney transplantation.

CONCLUSIONS

We need to continue developing predictors of renal functionality to accurately define the distribution of each currently available donor kidney.

Estimated glomerular filtration rate is an early biomarker of cardiac surgery-associated acute kidney injury

BACKGROUND

and objective Acute kidney injury (AKI) diagnosis is still based on serum creatinine and diuresis. However, increases in creatinine are typically delayed 48h or longer after injury. Our aim was to determine the utility of routine postoperative renal function blood tests, to predict AKI one or 2days in advance in a cohort of cardiac surgery patients.

PATIENTS AND METHODS

Using a prospective database, we selected a sample of patients who had undergone major cardiac surgery between January 2002 and December 2013. The ability of the parameters to predict AKI was based on Acute Kidney Injury Network serum creatinine criteria. A cohort of 3,962 cases was divided into 2groups of similar size, one being exploratory and the other a validation sample. The exploratory group was used to show primary objectives and the validation group to confirm results. The ability to predict AKI of several kidney function parameters measured in routine postoperative blood tests, was measured with time-dependent ROC curves. The primary endpoint was time from measurement to AKI diagnosis.

RESULTS

AKI developed in 610 (30.8%) and 623 (31.4%) patients in the exploratory and validation samples, respectively. Estimated glomerular filtration rate using the MDRD-4 equation showed the best AKI prediction capacity, with values for the AUC ROC curves between 0.700 and 0.946. We obtained different cut-off values for estimated glomerular filtration rate depending on the degree of AKI severity and on the time elapsed between surgery and parameter measurement. Results were confirmed in the validation sample.

CONCLUSIONS

Postoperative estimated glomerular filtration rate using the MDRD-4 equation showed good ability to predict AKI following cardiac surgery one or 2days in advance.

[Multivariate Adaptive Regression Splines (MARS), an alternative for the analysis of time series]

Multivariate Adaptive Regression Splines (MARS) is a non-parametric modelling method that extends the linear model, incorporating nonlinearities and interactions between variables. It is a flexible tool that automates the construction of predictive models: selecting relevant variables, transforming the predictor variables, processing missing values and preventing overshooting using a self-test. It is also able to predict, taking into account structural factors that might influence the outcome variable, thereby generating hypothetical models. The end result could identify relevant cut-off points in data series. It is rarely used in health, so it is proposed as a tool for the evaluation of relevant public health indicators. For demonstrative purposes, data series regarding the mortality of children under 5 years of age in Costa Rica were used, comprising the period 1978-2008.

A climate-based prediction model in the high-risk clusters of the Mekong Delta region, Vietnam: towards improving dengue prevention and control

OBJECTIVE

To develop a prediction score scheme useful for prevention practitioners and authorities to implement dengue preparedness and controls in the Mekong Delta region (MDR).

METHODS

We applied a spatial scan statistic to identify high-risk dengue clusters in the MDR and used generalised linear-distributed lag models to examine climate-dengue associations using dengue case records and meteorological data from 2003 to 2013. The significant predictors were collapsed into categorical scales, and the β-coefficients of predictors were converted to prediction scores. The score scheme was validated for predicting dengue outbreaks using ROC analysis.

RESULTS

The north-eastern MDR was identified as the high-risk cluster. A 1 °C increase in temperature at lag 1-4 and 5-8 weeks increased the dengue risk 11% (95% CI, 9-13) and 7% (95% CI, 6-8), respectively. A 1% rise in humidity increased dengue risk 0.9% (95% CI, 0.2-1.4) at lag 1-4 and 0.8% (95% CI, 0.2-1.4) at lag 5-8 weeks. Similarly, a 1-mm increase in rainfall increased dengue risk 0.1% (95% CI, 0.05-0.16) at lag 1-4 and 0.11% (95% CI, 0.07-0.16) at lag 5-8 weeks. The predicted scores performed with high accuracy in diagnosing the dengue outbreaks (96.3%).

CONCLUSION

This study demonstrates the potential usefulness of a dengue prediction score scheme derived from complex statistical models for high-risk dengue clusters. We recommend a further study to examine the possibility of incorporating such a score scheme into the dengue early warning system in similar climate settings.

Exploring the genetic basis of stroke. Spanish stroke genetics consortium

This article provides an overview of stroke genetics studies ranging from the candidate gene approach to more recent studies by the genome wide association. It highlights the complexity of stroke owing to its different aetiopathogenic mechanisms, the difficulties in studying its genetic component, and the solutions provided to date. The study emphasises the importance of cooperation between the different centres, whether this takes places occasionally or through the creation of lasting consortiums. This strategy is currently essential to the completion of high-quality scientific studies that allow researchers to gain a better knowledge of the genetic component of stroke as it relates to aetiology, treatment, and prevention.