Nevin Manimala

BMC Med Inform Decis Mak. 2022 Sep 6;22(1):236. doi: 10.1186/s12911-022-01980-w.

ABSTRACT

INTRODUCTION: Chronic myeloid leukemia (CML) is a myeloproliferative disorder resulting from the translocation of chromosomes 19 and 22. CML includes 15-20% of all cases of leukemia. Although bone marrow transplant and, more recently, tyrosine kinase inhibitors (TKIs) as a first-line treatment have significantly prolonged survival in CML patients, accurate prediction using available patient-level factors can be challenging. We intended to predict 5-year survival among CML patients via eight machine learning (ML) algorithms and compare their performance.

METHODS: The data of 837 CML patients were retrospectively extracted and randomly split into training and test segments (70:30 ratio). The outcome variable was 5-year survival with potential values of alive or deceased. The dataset for the full features and important features selected by minimal redundancy maximal relevance (mRMR) feature selection were fed into eight ML techniques, including eXtreme gradient boosting (XGBoost), multilayer perceptron (MLP), pattern recognition network, k-nearest neighborhood (KNN), probabilistic neural network, support vector machine (SVM) (kernel = linear), SVM (kernel = RBF), and J-48. The scikit-learn library in Python was used to implement the models. Finally, the performance of the developed models was measured using some evaluation criteria with 95% confidence intervals (CI).

RESULTS: Spleen palpable, age, and unexplained hemorrhage were identified as the top three effective features affecting CML 5-year survival. The performance of ML models using the selected-features was superior to that of the full-features dataset. Among the eight ML algorithms, SVM (kernel = RBF) had the best performance in tenfold cross-validation with an accuracy of 85.7%, specificity of 85%, sensitivity of 86%, F-measure of 87%, kappa statistic of 86.1%, and area under the curve (AUC) of 85% for the selected-features. Using the full-features dataset yielded an accuracy of 69.7%, specificity of 69.1%, sensitivity of 71.3%, F-measure of 72%, kappa statistic of 75.2%, and AUC of 70.1%.

CONCLUSIONS: Accurate prediction of the survival likelihood of CML patients can inform caregivers to promote patient prognostication and choose the best possible treatment path. While external validation is required, our developed models will offer customized treatment and may guide the prescription of personalized medicine for CML patients.

PMID:36068539 | DOI:10.1186/s12911-022-01980-w

BMC Nurs. 2022 Sep 6;21(1):249. doi: 10.1186/s12912-022-01022-w.

ABSTRACT

BACKGROUND: In an acute hospital setting, diabetes can require intensive management with medication modification, monitoring and education. Yet little is known about the experiences and perspectives of nursing/midwifery staff and patients. The aim of this study was to investigate diabetes management and care for patients with diabetes in an acute care setting from the perspectives of nursing/midwifery staff and patients.

METHODS: A convergent mixed-methods study design. Patients with diabetes (Type 1, Type 2 or gestational diabetes) recruited from a public health service in Melbourne, Australia completed a survey and nurses and midwives employed at the health service participated in focus groups. Descriptive statistics were used to summarise the survey data. Thematic analysis was used for the free-text survey comments and focus group data.

RESULTS: Surveys were completed by 151 patients. Although more than half of the patients were satisfied with the diabetes care they had received (n = 96, 67.6%), about a third felt the hospital nursing/midwifery staff had ignored their own knowledge of their diabetes care and management (n = 43, 30.8%). Few reported having discussed their diabetes management with the nursing/midwifery staff whilst in hospital (n = 47, 32.6%) or thought the nurses and midwives had a good understanding of different types of insulin (n = 43, 30.1%) and their administration (n = 47, 33.3%). Patients also reported food related barriers to their diabetes management including difficulties accessing appropriate snacks and drinks (n = 46, 30.5%), restricted food choices and timing of meals (n = 41, 27.2%). Fourteen nurses and midwives participated in two focus groups. Two main themes were identified across both groups: 1. challenges caring for patients with diabetes; and 2. lack of confidence and knowledge about diabetes management.

CONCLUSIONS: Patients and nursing/midwifery staff reported challenges managing patients’ diabetes in the hospital setting, ensuring patients’ optimal self-management, and provision of suitable food and timing of meals. It is essential to involve patients in their diabetes care and provide regular and up-to-date training and resources for nursing/midwifery staff to ensure safe and high-quality inpatient diabetes care and improve patient and staff satisfaction.

PMID:36068537 | DOI:10.1186/s12912-022-01022-w

BMC Pregnancy Childbirth. 2022 Sep 6;22(1):686. doi: 10.1186/s12884-022-05019-w.

ABSTRACT

BACKGROUND: Globally, nearly 295,000 women die every year during and following pregnancy and childbirth. Emergency obstetric and newborn care (EmONC) can avert 75% of maternal mortality if all mothers get quality healthcare. Improving maternal health needs identification and addressing of barriers that limit access to quality maternal health services. Hence, this study aimed to assess the quality of EmONC service and its predictors in Wolaita Zone, southern Ethiopia.

METHODOLOGY: A facility-based cross-sectional study was conducted in 14 health facilities. A facility audit was conducted on 14 health facilities, and 423 women were randomly selected to participate in observation of care and exit interview. The Open Data Kit (ODK) platform and Stata version 17 were used for data entry and analysis, respectively. Frequencies and summary statistics were used to describe the study population. Simple and multiple linear regressions were done to identify candidate and predictor variables of service quality. Coefficients with 95% confidence intervals were used to declare the significance and strength of association. Input, process, and output quality indices were created by calculating the means of standard items available or actions performed by each category and were used to describe the quality of EmONC.

RESULT: The mean input, process, and output EmONC services qualities were 74.2, 69.4, and 79.6%, respectively. Of the study participants, 59.2% received below 75% of the standard clinical actions (observed quality) of EmONC services. Women’s educational status (B = 5.35, 95% C.I: 0.56, 10.14), and (B = 8.38, 95% C.I: 2.92, 13.85), age (B = 3.86, 95% C.I: 0.39, 7.33), duration of stay at the facility (B = 3.58, 95% C.I: 2.66, 4.9), number of patients in the delivery room (B = – 4.14, 95% C.I: – 6.14, – 2.13), and care provider’s experience (B = 1.26, 95% C.I: 0.83, 1.69) were independent predictors of observed service quality.

CONCLUSION: The EmONC services quality was suboptimal in Wolaita Zone. Every three-in-five women received less than three-fourths of the standard clinical actions. The health system, care providers, and other stakeholders should emphasize improving the quality of care by availing medical infrastructure, adhering to standard procedures, enhancing human resources for health, and providing standard care regardless of women’s characteristics.

PMID:36068531 | DOI:10.1186/s12884-022-05019-w

Cardiovasc Diabetol. 2022 Sep 6;21(1):178. doi: 10.1186/s12933-022-01612-7.

ABSTRACT

BACKGROUND: Offspring of mothers with type 1 diabetes have an increased risk for acquiring early onset cardiovascular disease (CVD). Arterial stiffness, measured as pulse wave velocity (PWV), is a non-invasive biomarker for CVD risk assessment. Our aim is to determine whether PWV is increased in young adult offspring of mothers with type 1 diabetes.

METHODS: This is a case-control study carried out in the hospital district of Helsinki and Uusimaa, Finland. 75 offspring of mothers with type 1 diabetes (cases) and 84 offspring of mothers without diabetes (controls), aged 18-23 years, were enrolled in this study. All participants attended clinical assessments, including questionnaires and laboratory tests. Carotid-femoral PWV (cfPWV), carotid-radial PWV (crPWV), and PWV ratio were measured from each participant using the Complior Analyse mechanotransducer (Alam Medical, France). Student’s t-test and chi-squared test were used to assess differences between the groups. Stata 17.0, StataCorp LP (College Station, TX, USA) statistical package was used for the analysis.

RESULTS: We did not observe any differences in conventional CVD risk factors: systolic blood pressure, LDL, Hb_A1c, and smoking between cases and controls. We detected higher cfPWV in cases 6.5 (SD ± 1.2) m/s than in controls 6.2 (SD ± 0.7) m/s, p = 0.049, after adjustments for BMI, smoking, mean arterial pressure, height, and pulse rate was made. We did not observe any difference between cases and controls regarding crPWV or PWV ratio. Additionally, we detected no sex differences.

CONCLUSIONS: We report a novel finding of signs of increased arterial stiffness already in young adult offspring of mothers with type 1 diabetes compared to matched offspring of mothers without diabetes. Our finding suggests that exposure to an adverse intrauterine environment of type 1 diabetes mothers may affect the vascular health of offspring already in young adulthood. Additional research within this topic is warranted.

PMID:36068528 | DOI:10.1186/s12933-022-01612-7

BMC Public Health. 2022 Sep 6;22(1):1693. doi: 10.1186/s12889-022-14105-9.

ABSTRACT

BACKGROUND: This study aimed to estimate annual health care and lost productivity costs associated with excess weight among the adult population in Belgium, using national health data.

METHODS: Health care costs and costs of absenteeism were estimated using data from the Belgian national health interview survey (BHIS) 2013 linked with individual health insurance data (2013-2017). Average yearly health care costs and costs of absenteeism were assessed by body mass index (BMI) categories – i.e., underweight (BMI < 18.5 kg/m²), normal weight (18.5 ≤ BMI < 25 kg/m²), overweight (25 ≤ BMI < 30 kg/m²) and obesity (BMI ≥ 30 kg/m²). Health care costs were also analysed by type of cost (i.e. ambulatory, hospital, reimbursed medication). The cost attributable to excess weight and the contribution of various other chronic conditions to the incremental cost of excess weight were estimated using the method of recycled prediction (a.k.a. standardisation).

RESULTS: According to BHIS 2013, 34.7% and 13.9% of the Belgian adult population were respectively affected by overweight or obesity. They were mostly concentrated in the age-group 35-65 years and had significantly more chronic conditions compared to the normal weight population. Average total healthcare expenses for people with overweight and obesity were significantly higher than those observed in the normal weight population. The adjusted incremental annual health care cost of excess weight in Belgium was estimated at €3,329,206,657 (€651 [95% CI: €144-€1,084] and €1,015 [95% CI: €343-€1,697] per capita for individuals with overweight and obesity respectively). The comorbidities identified to be the main drivers for these incremental health care costs were hypertension, high cholesterol, serious gloom and depression. Mean annual incremental cost of absenteeism for overweight accounted for €242 per capita but was not statistically significant, people with obesity showed a significantly higher cost (p < 0.001) compared to the normal weight population: €2,015 [95% CI: €179-€4,336] per capita. The annual total incremental costs due to absenteeism of the population affected by overweight and obesity was estimated at €1,209,552,137. Arthritis, including rheumatoid arthritis and osteoarthritis, was the most important driver of the incremental cost of absenteeism in individuals with overweight and obesity, followed by hypertension and low back pain.

CONCLUSIONS: The mean annual incremental cost of excess weight in Belgium is of concern and stresses the need for policy actions aiming to reduce excess body weight. This study can be used as a baseline to evaluate the potential savings and health benefits of obesity prevention interventions.

PMID:36068519 | DOI:10.1186/s12889-022-14105-9

BMC Pregnancy Childbirth. 2022 Sep 6;22(1):687. doi: 10.1186/s12884-022-05003-4.

ABSTRACT

BACKGROUND: A significant proportion of women with preeclampsia (PE) exhibit persistent postpartum hypertension (PHTN) at 3 months postpartum associated with cardiovascular morbidity. This study aimed to screen patients with PE to identify the high-risk population with persistent PHTN.

METHODS: This retrospective cohort study enrolled 1,000 PE patients with complete parturient and postpartum blood pressure (BP) profiles at 3 months postpartum. The enrolled patients exhibited new-onset hypertension after 20 weeks of pregnancy, while those with PE superimposed upon chronic hypertension were excluded. Latent class cluster analysis (LCCA), a method of unsupervised learning in machine learning, was performed to ascertain maternal exposure clusters from eight variables and 35 subordinate risk factors. Logistic regression was applied to calculate odds ratios (OR) indicating the association between clusters and PHTN.

RESULTS: The 1,000 participants were classified into three exposure clusters (subpopulations with similar characteristics) according to persistent PHTN development: high-risk cluster (31.2%), medium-risk cluster (36.8%), and low-risk cluster (32.0%). Among the 1,000 PE patients, a total of 134 (13.4%) were diagnosed with persistent PHTN, while the percentages of persistent PHTN were24.68%, 10.05%, and 6.25% in the high-, medium-, and low-risk clusters, respectively. Persistent PHTN in the high-risk cluster was nearly five times higher (OR, 4.915; 95% confidence interval (CI), 2.92-8.27) and three times (OR, 2.931; 95% CI, 1.91-4.49) than in the low- and medium-risk clusters, respectively. Persistent PHTN did not differ between the medium- and low-risk clusters. Subjects in the high-risk cluster were older and showed higher BP, poorer prenatal organ function, more adverse pregnancy events, and greater medication requirement than the other two groups.

CONCLUSION: Patients with PE can be classified into high-, medium-, and low-risk clusters according to persistent PHTN severity; each cluster has cognizable clinical features. This study’s findings stress the importance of controlling persistent PHTN to prevent future cardiovascular disease.

PMID:36068506 | DOI:10.1186/s12884-022-05003-4

BMC Geriatr. 2022 Sep 6;22(1):733. doi: 10.1186/s12877-022-03410-y.

ABSTRACT

BACKGROUND: The number of older adults with physical multi-morbidity is increasing. As Internet-based eHealth and mHealth increasingly require patients to use technology, it is important to examine the use of Internet/health information technology (HIT) among older adults with physical multi-morbidity. Here we examine the distribution of physical multi-morbidity, Internet use, and HIT use, and further explored the factors associated with Internet use and HIT use among older adults with physical multi-morbidity.

METHODS: One wave of data from the 2018 US National Health Interview Survey (NHIS) was analysed. We included respondents aged 65 years and older. We used 13 physical non-communicable diseases to measure physical multi-morbidity. Descriptive statistics and logistic regression models, with sociodemographic factors, health status, health insurance, health care service use, and satisfaction with health care as covariates, were used to examine the research questions.

RESULTS: Of 72,746 respondents in NHIS, 7060 were eligible for our analysis. 5380 (76.2%) eligible respondents had physical multi-morbidity in this study. Overall, 60% of older adults reported using the Internet, with 38.9% using eHealth services (defined as looking up health information online, filling a prescription, scheduling an appointment with a health care provider, or communicating with a health care provider via email). Gender, age, marital status, region, race, education, and family income were significant factors associated with the Internet and HIT use among people with multi-morbidity. The study also showed that after adjusting for confounders, good health status, having Medicare, receiving home care from a health professional, and low satisfaction with health care were positive predictors of the Internet and HIT use.

CONCLUSIONS: In summary, our study found that Internet and HIT use among older patients with chronic diseases is far from the Healthy People 2030 target. Internet and HIT use vary depending on a number of sociodemographic factors. Relevant influencing factors should be fully considered in health education interventions promoted.

PMID:36068502 | DOI:10.1186/s12877-022-03410-y

BMC Infect Dis. 2022 Sep 6;22(1):724. doi: 10.1186/s12879-022-07715-6.

ABSTRACT

BACKGROUND: Mycoplasma pneumoniae can be divided into different subtypes on the basis of the sequence differences of adhesive protein P1, but the relationship between different subtypes, macrolide resistance and clinical manifestations are still unclear. In the present study, we established a molecular beacon based real-time polymerase chain reaction (real-time PCR) p1 gene genotyping method, analyzed the macrolide resistance gene mutations and the relationship of clinical characteristics with the genotypes.

METHODS: A molecular beacon based real-time PCR p1 gene genotyping method was established, the mutation sites of macrolide resistance genes were analyzed by PCR and sequenced, and the relationship of clinical characteristics with the genotypes was analyzed.

RESULTS: The detection limit was 1-100 copies/reaction. No cross-reactivity was observed in the two subtypes. In total, samples from 100 patients with positive M. pneumoniae detection results in 2019 and 2021 were genotyped using the beacon based real-time PCR method and P1-1 M. pneumoniae accounted for 69.0%. All the patients had the A2063G mutation in the macrolide resistance related 23S rRNA gene. Novel mutations were also found, which were C2622T, C2150A, C2202G and C2443A mutations. The relationship between p1 gene genotyping and the clinical characteristics were not statistically related.

CONCLUSION: A rapid and easy clinical application molecular beacon based real-time PCR genotyping method targeting the p1 gene was established. A shift from type 1 to type 2 was found and 100.0% macrolide resistance was detected. Our study provided an efficient method for genotyping M. pneumoniae, valuable epidemiological monitoring information and clinical treatment guidance to control high macrolide resistance.

PMID:36068499 | DOI:10.1186/s12879-022-07715-6

J Headache Pain. 2022 Sep 6;23(1):115. doi: 10.1186/s10194-022-01482-0.

ABSTRACT

BACKGROUND: Patients with chronic migraine (CM) treated with eptinezumab in the PROMISE-2 trial achieved greater reductions in migraine and headache frequency, impact, and acute headache medication (AHM) use than did patients who received placebo. This post hoc analysis examines relationships between headache frequency reductions and changes in AHM use in patients in PROMISE-2.

METHODS: PROMISE-2 was a double-blind, placebo-controlled trial conducted in adults with CM. Patients were randomized to eptinezumab 100 mg, 300 mg, or placebo, administered intravenously once every 12 weeks for up to two doses. Patients recorded headache/AHM information daily and for each event in an electronic diary; data from all days with daily reports were included. Shifts in headache frequency and AHM use were assessed in the three populations: total CM population, patients with CM and medication-overuse headache (MOH), and patients with CM and MOH who were ≥ 50% responders during treatment (response over weeks 1-24).

RESULTS: A total of 1072 adults with CM received treatment (eptinezumab, n = 706; placebo, n = 366). Mean baseline headache frequency was 20.5 days; mean baseline AHM days was 13.4; 431 patients had MOH, of which 225 (52.2%) experienced ≥50% response over weeks 1-24. Relative to baseline, the proportion of days with both headache and AHM use decreased 25.1% (eptinezumab) versus 17.0% (placebo) in the total population (N = 1072), 29.2% versus 18.4% in the MOH subpopulation (n = 431), and 38.3% versus 31.5% in the CM with MOH population with ≥50% response subgroup (n = 225) during weeks 1-24. The proportion of days with headache and triptan use decreased 9.1% (eptinezumab) versus 5.8% (placebo), 11.8% versus 7.2%, and 14.5% versus 12.6%, respectively. Reductions in other AHM types were smaller.

CONCLUSIONS: In this post hoc analysis, eptinezumab use in patients with CM was associated with greater decreases in days with headache with AHM overall and with triptans in particular. The magnitude of effect was greater in the subgroup of CM patients with MOH and ≥ 50% response.

TRIAL REGISTRATION: ClinicalTrials.gov Identifier: NCT02974153 . Eptinezumab reduces headache frequency and acute medication use in patients with chronic migraine.

PMID:36068494 | DOI:10.1186/s10194-022-01482-0

BMC Cardiovasc Disord. 2022 Sep 6;22(1):399. doi: 10.1186/s12872-022-02842-z.

ABSTRACT

OBJECTIVE: The present study aimed to investigate whether different preoperative left atrial appendage emptying speeds (LAAEVs) have an effect on left atrial function in patients with sinus arrhythmia after left atrial appendage closure (LAAC) combined with catheter ablation (CA).

METHODS: A total of 163 patients with persistent non-valvular atrial fibrillation who received combined LAAC+CA surgery were included in the present study. Regular follow-up was conducted for 12 months, and patients with complete data and successful sinus rhythm recovery were selected as the study subjects (n = 82). The patients were divided into two groups: the LAAEV < 25 cm/s group and the LAAEV ≥ 25 cm/s group (n = 41 each). The propensity score was used for matching according to gender, age, CHA₂DS₂-VASc score, and HAS-BLED score. The changes in the two groups in LA structure, storage function, conduit function, and pump function were compared.

RESULTS: Before surgery, the maximum LA volume (LAV_max) and minimum LA volume (LAV_min) were greater in the LAAEV < 25 cm/s group than in the LAAEV ≥ 25 cm/s group. The LA storage function (eg. Ƹ and SRs), conduit function (eg. SRe), and pump function (eg. SRa) were all worse in the LAAEV < 25 cm/s group than in the LAAEV ≥ 25 cm/s group. After the combined LAAC+CA surgery, the LA storage, conduit, and pump functions improved in both groups. At 12 months after surgery, there were no statistically significant differences between the two groups.

CONCLUSION: Before combined LAAC+CA surgery, the LA structure and function of the LAAEV < 25 cm/s group were worse than those of the LAAEV ≥ 25 cm/s group. However, after LAAC+CA surgery, the LA structure and function of the patients were improved, and there were no significant differences between the two groups. Inferred improvement in LA structure and function in the LAAEV < 25 cm/s group was superior to that in the LAAEV ≥ 25 cm/s group.

PMID:36068492 | DOI:10.1186/s12872-022-02842-z