A fuzzy rule-based expert system for diagnosing cystic fibrosis

Prevalence of Anemia and its Relation with Shwachman Score in Children with Cystic Fibrosis

Background

Cystic fibrosis is a chronic and progressive genetic disease with a worldwide prevalence. As the disease progresses, symptoms develop, and make its management more challenging. Accumulating evidence suggests that early diagnosis of CF can significantly contribute to preventing reported nutritional problems including anemia, vitamin deficiencies, and hypoalbuminemia. This cross-sectional study was conducted to assess disease severity in cystic fibrosis patients using the Shwachman-Kulczycki score, as well as to determine its relation with anemia and vitamin D deficiency.

Materials and Methods

Clinical and CF-related laboratory data were collected from the medical records of 57 CF patients with a definitive diagnosis. At the time of diagnosis, physicians performed simultaneous, blood sampling and scoring of patients using the Shwachman scoring system.

Results

The mean age of patients was 16.12±6.48 years. Total scores of 86-100, 71-85, 56-70, 41-55, and <40, were reported in 5.4%, 7.1%, 14.3%, 14.3%, and 58.9% of CF patients, respectively. A significant correlation was found between disease severity and patients' age (P=0.02). The analysis also showed that the disease severity was significantly higher in anemic patients when compared to non-anemics (p =0.006). Based on the results, 33 patients with normochromic, 11 patients with microcytic, and 6 patients with macrocytic anemia were diagnosed in this study. We did not find a significant difference between disease severity and vitamin D levels (P=0.150).

Conclusion

The scoring system used in the current study could reflect properly the clinical status of CF patients. However, simultaneous use of various methods using a larger sample size for comparison of results is suggested to improve the accuracy of findings.

Assessing the effect of arrival time of physician and cardiopulmonary resuscitation (CPR) team on the outcome of CPR

Introduction

Negligence of proper time and poor performance of resuscitation team can lead to more mortality and negative consequences of cardiac arrest, as well as less survival. This study was conducted with objective of determining the arrival time of physician and resuscitation team to survive the victims of cardiopulmonary arrest.

Materials and methods

In this prospective and descriptive-analytic study, the resuscitation performance and the arrival time of resuscitation team in 143 inpatients who had been diagnosed with witnessed cardiopulmonary arrest were examined using a researcher-made checklist. Data analysis was performed using parametric and non-parametric statistical tests and SPSS.

Results

Initial survival rate was 26.6%. In general, the mean time of physician’s presence after the code announcement in minutes and seconds was 02:31 ± 01:22. It was also 02:24 ± 01:15 in successful cases and 02:34 ± 01:25 in unsuccessful cases. Independent t-test did not show a significant difference between the physician’s presence time and the rate of initial successful resuscitation (p = 0.504). The time of first shock after observing ventricular fibrillation/tachycardia (in minutes and seconds) was 01:30 ± 00:47. According to independent t-test, the aforementioned time was less than the mean time (02:31 ± 01:22) of physician’s presence (p < 0.001).

Conclusions

In this study, the initial survival rate in comparison to other regions in the country was almost more favorable and it was similar to global norms. In this study, the starting time of resuscitation was within the acceptable range. There was no relationship between the presence of physician and the initial survival rate of patients, as well as the use of defibrillator (by physician compared to other team members) and intubation with the initial survival rate. This could indicate the adequate performance of resuscitation team in the absence of physician on the condition of having sufficient knowledge and skill.

Diagnosis support systems for rare diseases: a scoping review

INTRODUCTION

Rare diseases affect approximately 350 million people worldwide. Delayed diagnosis is frequent due to lack of knowledge of most clinicians and a small number of expert centers. Consequently, computerized diagnosis support systems have been developed to address these issues, with many relying on rare disease expertise and taking advantage of the increasing volume of generated and accessible health-related data. Our objective is to perform a review of all initiatives aiming to support the diagnosis of rare diseases.

METHODS

A scoping review was conducted based on methods proposed by Arksey and O'Malley. A charting form for relevant study analysis was developed and used to categorize data.

RESULTS

Sixty-eight studies were retained at the end of the charting process. Diagnosis targets varied from 1 rare disease to all rare diseases. Material used for diagnosis support consisted mostly of phenotype concepts, images or fluids. Fifty-seven percent of the studies used expert knowledge. Two-thirds of the studies relied on machine learning algorithms, and one-third used simple similarities. Manual algorithms were encountered as well. Most of the studies presented satisfying performance of evaluation by comparison with references or with external validation. Fourteen studies provided online tools, most of which aimed to support the diagnosis of all rare diseases by considering queries based on phenotype concepts.

CONCLUSION

Numerous solutions relying on different materials and use of various methodologies are emerging with satisfying preliminary results. However, the variability of approaches and evaluation processes complicates the comparison of results. Efforts should be made to adequately validate these tools and guarantee reproducibility and explicability.

Artificial Intelligence in Clinical Decision Support: a Focused Literature Survey

OBJECTIVES

This survey analyses the latest literature contributions to clinical decision support systems (DSSs) on a two-year period (2017-2018), focusing on the approaches that adopt Artificial Intelligence (AI) techniques in a broad sense. The goal is to analyse the distribution of data-driven AI approaches with respect to "classical" knowledge-based ones, and to consider the issues raised and their possible solutions.

METHODS

We included PubMed and Web of ScienceTM publications, focusing on contributions describing clinical DSSs that adopted one or more AI methodologies.

RESULTS

We selected 75 papers, 49 of which describe approaches in the data-driven AI area, 20 present purely knowledge-based DSSs, and 6 adopt hybrid approaches relying on both formalized knowledge and data.

CONCLUSIONS

Recent studies in the clinical DSS area demonstrate a prevalence of data-driven AI, which can be adopted autonomously in purely data-driven systems, or in cooperation with domain knowledge in hybrid systems. Such hybrid approaches, able to conjugate all available knowledge sources through proper knowledge integration steps, represent an interesting example of synergy between the two AI categories. This synergy can lead to the resolution of some existing issues, such as the need for transparency and explainability, nowadays recognized as central themes to be addressed by both AI and medical informatics research.

Evaluation of Quality of Life in Terms of Sinonasal Symptoms in Children with Cystic Fibrosis

Objective

Sinusitis is a common complaint in children with cystic fibrosis. However, the actual prevalence of chronic rhinosinusitis and its effect on the quality of life of children have not been well considered. Therefore, the objective of this study was to determine the effect of sinonasal quality of life in children with cystic fibrosis.

Materials and methods

This study was a diagnostic study performed on 80 children with cystic fibrosis ranging from 2 to 20 years old, who were referred to the cystic fibrosis clinic of Masih Daneshvari Hospital from 2017–2018. The questionnaires used in this study were chronic rhinosinusitis screening questionnaire based on the European task force and the evaluation of the sinonasal quality of life was based on the SN-5 survey.

Results

Of the 80 patients with fibrosis from 2 to 20 years old who were recruited in the study, 41 patients were female (51.3%) and 39 were male (48.8%). In 61 cases (76.3%), there was no chronic rhinosinusitis and 19 cases (23.8%) had chronic rhinosinusitis. The mean SN-5 score in 19 patients with chronic rhinosinusitis was 3.4105 and the mean score of patients without rhinosinusitis was 1.8426, with a P-value of 0.000. The mean SN-5 score was significant between the two groups. In patients with nasal congestion, there was a significant difference in quality of life factors such as sinus infection, nasal obstruction, and allergy symptoms (P<0.001). In patients with facial pain, there was a significant difference in quality of life factors such as sinus infection, nasal obstruction, allergic symptoms, and physical activity limitation (P <0.001). There was also a significant difference in the quality of life factors such as sinus infection, nasal obstruction, and allergy symptoms in patients with postnasal drip (P <0.001).

Conclusion

In children with cystic fibrosis, the quality of life of sinonasal has a significant relationship with absence of chronic rhinosinusitis. This study showed that children with chronic renosinusitis have significantly lower quality of sinonasal life than children with chronic rhinosinusitis. The results demonstrated that quality of life scores in sinus infections, nasal obstruction, and allergy symptoms were significantly higher in patients with chronic rhinosinusitis than in those without chronic rhinosinusitis. The findings of this study are important for improving children’s health related quality of life, as it leads to promoting communication between the patient and the health care provider, identifying overlooked problems, monitoring the progress of the disease and the burden of treatment, and promoting interventions in the daily life of patients.

A Fuzzy Expert System to Predict the Risk of Postpartum Hemorrhage

Introduction:

The American College of Obstetricians and Gynecologists (ACOG) defines postpartum hemorrhage (PPH) as a blood loss of >500mL following vaginal delivery or >1000mL following cesarean section. PPH is widely recognized as a common cause of maternal death. However, there is currently no effective method to predict its risk of occurrence.

Aim:

To develop a fuzzy expert system to predict the risk of developing PPH and to evaluate its performance in the clinical setting.

Methods:

This system was developed using MATLAB software. Mamdani inference was used to simulate reasoning of experts in the field. To evaluate the performance of the system, a dataset of 1705 patients admitted at the Labor and Delivery ward of The Second Affiliated Hospital of Nanjing Medical University from 2017-10 to 2018-04, was considered.

Results:

The Negative Predictive value (NPV), Positive Predictive value PPV), Specificity and Sensitivity were calculated and were 99.72%, 18.50%, 87.48% and 92.16% respectively.

Conclusions:

Our findings suggest that the fuzzy expert system can be used to predict PPH in clinical settings and thus decrease maternal mortality rate due to hemorrhage.