Prediction of mortality risk and duration of hospitalization of COVID-19 patients with chronic comorbidities based on machine learning algorithms

Background

The severity of coronavirus (COVID-19) in patients with chronic comorbidities is much higher than in other patients, which can lead to their death. Machine learning (ML) algorithms as a potential solution for rapid and early clinical evaluation of the severity of the disease can help in allocating and prioritizing resources to reduce mortality.

Objective

The objective of this study was to predict the mortality risk and length of stay (LoS) of patients with COVID-19 and history of chronic comorbidities using ML algorithms.

Methods

This retrospective study was conducted by reviewing the medical records of COVID-19 patients with a history of chronic comorbidities from March 2020 to January 2021 in Afzalipour Hospital in Kerman, Iran. The outcome of patients, hospitalization was recorded as discharge or death. The filtering technique used to score the features and well-known ML algorithms were applied to predict the risk of mortality and LoS of patients. Ensemble Learning methods is also used. To evaluate the performance of the models, different measures including F1, precision, recall, and accuracy were calculated. The TRIPOD guideline assessed transparent reporting.

Results

This study was performed on 1291 patients, including 900 alive and 391 dead patients. Shortness of breath (53.6%), fever (30.1%), and cough (25.3%) were the three most common symptoms in patients. Diabetes mellitus(DM) (31.3%), hypertension (HTN) (27.3%), and ischemic heart disease (IHD) (14.2%) were the three most common chronic comorbidities of patients. Twenty-six important factors were extracted from each patient's record. Gradient boosting model with 84.15% accuracy was the best model for predicting mortality risk and multilayer perceptron (MLP) with rectified linear unit function (MSE = 38.96) was the best model for predicting the LoS. The most common chronic comorbidities among these patients were DM (31.3%), HTN (27.3%), and IHD (14.2%). The most important factors in predicting the risk of mortality were hyperlipidemia, diabetes, asthma, and cancer, and in predicting LoS was shortness of breath.

Conclusion

The results of this study showed that the use of ML algorithms can be a good tool to predict the risk of mortality and LoS of patients with COVID-19 and chronic comorbidities based on physiological conditions, symptoms, and demographic information of patients. The Gradient boosting and MLP algorithms can quickly identify patients at risk of death or long-term hospitalization and notify physicians to do appropriate interventions.

Toxin A and B genes expression of Clostridium difficile in the sub-minimum inhibitory concentration of clindamycin, vancomycin and in combination with ceftazidime

BACKGROUND AND OBJECTIVES

Antibiotics prescribed for infections have diverse effects on microbiota and the pathogen Clostridium difficile (C. difficile) as the most important antibiotic-associated diarrhea. This study aims to determine the gene expression of toxins A and B at the transcription level in the sub-MIC of vancomycin (VAN), clindamycin (CLI), and ceftazidime (CAZ) alone and in combination.

MATERIALS AND METHODS

The MIC and fractional inhibitory concentration (FIC) of two C. difficile samples (a clinical isolate and ATCC 9689) were determined by microdilution and checkerboard microdilution methods, respectively. The total RNA was extracted from the medium inoculated with ∼10⁶ CFU/mL of fresh bacteria in the pre-reduced medium containing ½ MIC of antibiotics alone and ½ FIC of antibiotics in combination. Real-time PCR was performed by sybrGreen methods in triplicate, and the data were analyzed by the comparative ΔΔ^CT method.

RESULTS

All antibiotics except CAZ (alone and in combination) decreased the gene expression of toxins A and B within 24 hours. VAN and CLI reduced toxin gene expression within 24 and 48 hours. However, CAZ alone and in combination with VAN as well as CLI increased the gene expression of toxins A and B.

CONCLUSION

The results confirmed toxin gene transcription and toxin production are associated with the type of isolates and antibiotics, as well as the combined form of antibiotics. This could be the reason which can explain the occurrence of C. difficile infection among patients who were treated with the third generation of cephalosporins alone and in combination with another antibiotic in the form of combinational therapy.

Green tea as an adjunctive therapy for treatment of acute uncomplicated cystitis in women: A randomized clinical trial

BACKGROUND

and purpose: Different in vitro studies have reported the antimicrobial effects of green tea catechins and also their synergistic effects with trimethoprim-sulfamethoxazole against E. coli. The aim of the present study was to evaluate the efficacy of green tea as an adjunctive therapy to standard antimicrobial treatment in women with acute uncomplicated cystitis.

MATERIALS AND METHODS

In this blinded randomized trial, 70 patients were assigned to receive four 500 mg capsules of green tea or starch as placebo daily for three days along with trimethoprim-sulfamethoxazole. The presence of acute uncomplicated cystitis symptoms was recorded and urinalysis was performed.

RESULTS

Women in the green tea group showed a statistically significant decrease in the prevalence of cystitis symptoms and a statistically significant improvement in the urinalysis results except for hematuria after 3 days of treatment.

CONCLUSION

Green tea was an effective adjunct to trimethoprim-sulfamethoxazole to treat acute uncomplicated cystitis in women.

Effect of sub-MIC of vancomycin and clindamycin alone and in combination with ceftazidime on Clostridium difficile surface layer protein A (slpA) gene expression

Clostridium difficile (C.difficile) infection is often established in the presence of antibiotics and probably antibiotics can influence surface layer protein A (slpA) expression as a colonization factor. The aim of this study is to evaluate the effect of vancomycin (VAN), clindamycin (CLI) alone and in combination with ceftazidime (CAZ) on slpA gene expression to determine whether such antibiotics can have any effect on slpA expression. About ∼10⁶ CFU/mL was inoculated to medium containing an appropriate concentration of antibiotics alone and in combination. After 24 and 48 h incubation under anaerobic condition, 3 mL of culture was excluded and centrifuged in 8000 × g per 3 min. The pellet was washed and used for RNA extraction. The RNA extraction, Dnase I treatment and cDNA synthesis was performed by RNA extraction, Dnase I, and cDNA synthesis kits, respectively. The real-time PCR were carried out by sybrGreen methods and data were analyzed based on comparative ΔΔC_T. All antibiotics alone and in combination, except VAN/CAZ in clinical isolate, decreased the level of slpA gene expression in the 24-h incubation. While the expression profile of slpA was different in the 48-h incubation period. The VAN and CLI decreased the slpA expression, although the template of expression is closed to control medium. CAZ alone and in combination increased slpA expression. C. difficile may down-regulate slpA expression in the early stages of growth in sub-inhibitory concentration of antibiotics. But, over time C. difficile increases or over expresses the slpA expression level. Consequently C. difficile binds strongly to epithelial cells and continues to survive in the presence of sub-MIC concentration of antibiotics. This effect is observed especially with regard to CAZ and probably other third generation cephalosporins or in combination therapy with VAN or CLI, which are prescribed in the clinic. CAZ can interfere with the anti-down regulatory feature of VAN, CLI, and maybe other antibiotics.

Influence of pharmacy students on the attitudes of medical students following an interprofessional course

BACKGROUND

Clinical interprofessional education (IPE) can promote mutual understanding of other health professions and respectful behaviors among health-care professionals. The aims of this study were to evaluate the effects of IPE on the attitudes of medical and pharmacy students in an inpatient hospital setting and, in particular, the influence of pharmacy students on the attitudes of medical students.

METHODS

The 6th year doctor of pharmacy students and medical students were enrolled in a prospective cohort study. They were paired and each pair was responsible for three beds and all the patients occupying these mentioned beds over the 2-week course. The Readiness for Interprofessional Learning Scale (RIPLS) questionnaire was used to assess the students' attitudes before and after the course.

RESULTS

The attitudes of the medical students changed positively after the IPE course based on RIPLS teamwork and collaboration and professional identity subscales. Changes in the attitudes of the pharmacy students were not statistically significant based on the mentioned scale and subscales.

DISCUSSION

IPE could improve the attitudes of the medical students regarding interprofessional teamwork, communication, and sharing learning experience. Based on the current investigation, IPE did not have an effect on pharmacy students.

Toxin production of Clostridium difficile in sub-MIC of vancomycin and clindamycin alone and in combination with ceftazidime

Toxin production in Clostridium difficile (C. difficile) is a key process for induction of diarrhea. Several factors such as sub-MIC of antibiotics impact on toxin production. The aim of this research is investigation of sub-minimum inhibitory concentration (sub-MIC) of vancomycin (VAN), clindamycin (CLI) separately and in combination with ceftazidime (CAZ) on toxin production in C. difficile. About ∼10⁶ colony forming units (CFU) from 18-h culture of C. difficile ATCC 9689 and clinical isolates A⁺/B⁺/CTD^-, were cultured anaerobically in the pre-reduced medium with appropriate concentration of separated and in combination antibiotics. After 24 and 48 h, 1 mL of culture was removed, centrifuged and the supernatant stored at-70 °C for later use. The evaluation of toxin production was carried out by the ELISA technique. All antibiotics alone and in combination formats inhibited toxin production over a period of 24 h. This effect is also observed in presence of VAN and CLI during a period of 48 h. Over a 4 h period, CAZ increased toxin production alone and in combination, especially with CLI. The data showed VAN and CLI decrease the level of toxins. In contrast, the CAZ not only increases the level of produced toxin, but also can interfere with VAN and CLI. Based on the results, combination therapy which is performed for treatment or prevention of other infections may cause toxin production and probably the severity of C. difficile AAD to increase.

Evaluation of TGF β1, IL-8 and nitric oxide in the serum of diffuse axonal injury patients and its association with clinical status and outcome

AIM

The aim was to evaluate the level of interleukin 8 (IL-8), transforming growth factor β1 (TGF β1) and Nitric oxide (NO) in diffuse axonal injury (DAI) and its association to the outcome and clinical status.

MATERIAL AND METHODS

This cross-sectional study was conducted on 20 patients with DAI and 20 patients with multiple traumas without head injury and 20 healthy subjects as controls. Blood levels of IL-8, TGF β1 and nitric oxide in the 1st, 2nd, 3rd and 7th days of injury were measured. Glasgow coma scale (GCS) of patients was recorded. The patients' outcome was evaluated by Glasgow Outcome Scale (GOS).

RESULTS

The level of TGF β1 was increasing during the admission and had the maximum level at the 7th day. In the DAI group, there was significant correlation between GOS score and serum IL-8 at 7th day of admission (r=-0.68, p= 0.002). In this group the GCS was found to be significantly correlated with the IL-8 concentration at 7th day of admission (p= 0.026, r=-0.55).

CONCLUSION

IL-8 has negative correlation with GCS and GOS. TGF β1 could protect the brain from cytotoxics, hypoxia and acidosis so its level comes down in brain injuries as a result of its overuse.

Detection of the Most Common Microorganisms and Their Resistance against Anti-microbials in Intubated Patients in an ICU in Kerman, Iran

The purpose of this study was to determine the prevalence of anti-microbial resistance in intubated patients in intensive care unit (ICU) of Bahonar hospital in Kerman province, Iran during the year 2008. Tracheal samples were obtained from 111 intubated patients in the ICU by broncoalveolar lavage method. Amikacin, Ceftazidim and Imipenem were used to evaluate antibiotic susceptibility. For detecting anti-microbial susceptibility, minimum inhibitory concentration method were used. Colony counts equal or more than 104 microorganisms/mL were considered resistant. Overall we obtained positive tracheal cultures from 32 patients (29%) out of 111 intubated ones. The most common micro organisms isolated were Klebsiella (90.6%), Acinetobacter (28.1%) and Pseudomonas (21.9%). The results showed that the most common resistance was against to ceftazidim. The susceptibility of Klebsiellain tracheal cultures to the antibiotics was only 5%. E. coli in both sexes was 100% resistant to the tested antibiotics. In the ICU, There was a very big problem concerning antibiotic resistance. Most of the isolated microorganisms were resistant to both the old and the new antibiotics. It may be related to the inappropriate use of antibiotics, bacterial contamination of enteral feeding and infection transmission by medical staff or instruments.