Category: Statistics

Gerontol Geriatr Educ. 2023 Apr-Jun;44(2):151-153. doi: 10.1080/02701960.2023.2192395.

NO ABSTRACT

PMID:37102191 | DOI:10.1080/02701960.2023.2192395

J Mach Learn Res. 2022 Nov;23:291.

ABSTRACT

Unmeasured or latent variables are often the cause of correlations between multivariate measurements, which are studied in a variety of fields such as psychology, ecology, and medicine. For Gaussian measurements, there are classical tools such as factor analysis or principal component analysis with a well-established theory and fast algorithms. Generalized Linear Latent Variable models (GLLVMs) generalize such factor models to non-Gaussian responses. However, current algorithms for estimating model parameters in GLLVMs require intensive computation and do not scale to large datasets with thousands of observational units or responses. In this article, we propose a new approach for fitting GLLVMs to high-dimensional datasets, based on approximating the model using penalized quasi-likelihood and then using a Newton method and Fisher scoring to learn the model parameters. Computationally, our method is noticeably faster and more stable, enabling GLLVM fits to much larger matrices than previously possible. We apply our method on a dataset of 48,000 observational units with over 2,000 observed species in each unit and find that most of the variability can be explained with a handful of factors. We publish an easy-to-use implementation of our proposed fitting algorithm.

PMID:37102181 | PMC:PMC10129058

Patient Prefer Adherence. 2023 Apr 19;17:1093-1105. doi: 10.2147/PPA.S406894. eCollection 2023.

ABSTRACT

PURPOSE: As gene therapies for hemophilia are incorporated into clinical practice, shared decision-making (SDM) is recommended for implementation. SDM tools may facilitate informed decision-making for gene therapy and other novel therapies.

OBJECTIVE: To inform the development of SDM tools for hemophilia gene therapy.

PATIENTS AND METHODS: Men with severe hemophilia were recruited from the National Hemophilia Foundation (NHF) Community Voices in Research (CVR). Semi-structured interviews were completed, and the interviews were transcribed verbatim for quantitative and qualitative analysis.

RESULTS: Twenty-five men with severe hemophilia A participated. All participants reported treatment with prophylaxis, nine (36%) on continuous prophylaxis with clotting factor, one (4%) on intermittent prophylaxis with clotting factor, and 15 (60%) on continuous prophylaxis with emicizumab. Ten (40%) indicated that they are excited about gene therapy, 12 (48%) indicated that they are hopeful about gene therapy, one (4%) indicated that they are worried or scared about gene therapy, and one (4%) indicated that they do not have strong feelings about gene therapy. Participants reported engaging Hemophilia Treatment Center, family, and the hemophilia community in their decision-making process. The most reported information needs are efficacy, safety, cost/insurance, mechanism of action, and follow-up. In addition, key information themes that emerged were patient testimonials, hard data and statistics, and comparison to other products. Twenty-two (88%) indicated that a SDM tool would be useful when discussing gene therapy with their hemophilia team. Two indicated that they do their own research, and the tool would not add anything. One needed more information to provide an answer.

CONCLUSION: These data highlight the utility of a SDM tool for hemophilia gene therapy and key information needs. Data including comparison to other treatments should be provided along with patient testimonials in a transparent format. Patients will engage the Hemophilia Treatment Center, family, and community members in the decision-making process.

PMID:37102127 | PMC:PMC10123005 | DOI:10.2147/PPA.S406894

Patient Prefer Adherence. 2023 Apr 20;17:1117-1130. doi: 10.2147/PPA.S405567. eCollection 2023.

ABSTRACT

BACKGROUND: Psychosocial, lifestyle and practical needs are not routinely attended to during outpatient hepatology management, and little is known about the type and effectiveness of support services accessed by patients with cirrhosis. We quantified the type and use of community and allied health services in patients with cirrhosis.

METHODS: The study included 562 Australian adults with a diagnosis of cirrhosis. Health service use was assessed via questionnaire and via linkage to the Australian Medicare Benefits Schedule. Patient needs were assessed using the Supportive Needs Assessment tool for Cirrhosis (SNAC).

RESULTS: Although most patients (85.9%) used at least one community/allied health service for support with their liver disease, many reported requiring additional help with psychosocial (67.4%), lifestyle (34.3%) or practical needs (21.9%) that were not met by available services, or patients did not access services. A multidisciplinary care plan or case conference (in the 12 months prior to recruitment) was accessed by 48% of patients, 56.2% reported the use of a general practitioner for support with cirrhosis, and a dietician was the allied health clinician most accessed by patients (45.9%). Despite the high prevalence of psychosocial needs, there was relatively limited use of mental health and social work services (14.1% of patients reported the use of a psychologist), confirmed by a low prevalence of use of mental health services (17.7%) in the linked data.

CONCLUSION: Patients with cirrhosis who have unmet complex physical and psychosocial needs require better strategies to increase their engagement with allied health and community services.

PMID:37102126 | PMC:PMC10124554 | DOI:10.2147/PPA.S405567

J Pharm Anal. 2023 Mar;13(3):296-304. doi: 10.1016/j.jpha.2023.01.002. Epub 2023 Feb 6.

ABSTRACT

The rapid and accurate authentication of traditional Chinese medicines (TCMs) has always been a key scientific and technical problem in the field of pharmaceutical analysis. Herein, a novel heating online extraction electrospray ionization mass spectrometry (H-oEESI-MS) was developed for the rapid and direct analysis of extremely complex substances without the requirement for any sample pretreatment or pre-separation steps. The overall molecular profile and fragment structure features of various herbal medicines could be completely captured within 10-15 s, with minimal sample (<0.5 mg) and solvent consumption (<20 μL for one sample). Furthermore, a rapid differentiation and authentication strategy for TCMs based on H-oEESI-MS was proposed, including metabolic profile characterization, characteristic marker screening and identification, and multivariate statistical analysis model validation. In an analysis of 52 batches of seven types of Aconitum medicinal materials, 20 and 21 key compounds were screened out as the characteristic markers of raw and processed Aconitum herbal medicines, respectively, and the possible structures of all the characteristic markers were comprehensively identified based on Compound Discoverer databases. Finally, multivariate statistical analysis showed that all the different types of herbal medicines were well differentiated and identified (R²X > 0.87, R²Y > 0.91, and Q² > 0.72), which further verified the feasibility and reliability of this comprehensive strategy for the rapid authentication of different TCMs based on H-oEESI-MS. In summary, this rapid authentication strategy realized the ultra-high-throughput, low-cost, and standardized detection of various complex TCMs for the first time, thereby demonstrating wide applicability and value for the development of quality standards for TCMs.

PMID:37102106 | PMC:PMC10123936 | DOI:10.1016/j.jpha.2023.01.002

J Taibah Univ Med Sci. 2022 Oct 12;18(2):356-365. doi: 10.1016/j.jtumed.2022.09.013. eCollection 2023 Apr.

ABSTRACT

OBJECTIVES: Following periodontal treatment, tooth supporting structures are restored to functionality and hence improve muscle activity. In this study, we aimed to investigate the influence of periodontal disease on muscle activity by electromyography and the subjective perception of periodontal therapy through the Oral Impact on Daily Performance (OIDP) questionnaire.

METHODS: Sixty subjects with moderate to severe periodontitis were included. Periodontal condition was re-evaluated 4-6 weeks after non-surgical periodontal therapy (NSPT). Subjects with persistent probing pocket depths ≥5 mm were designated for flap surgery. All clinical parameters were recorded at baseline, 3 months and 6 months after surgery. The activities of the masseter and temporalis muscles were measured by electromyography and OIDP scores were recorded at baseline and 3 months.

RESULTS: The mean plaque index scores, probing pocket depths, and clinical attachment levels were reduced from baseline to 3 months. Mean EMG scores were compared at baseline and 3 months post-surgery. The mean OIDP total score prior to and after periodontal therapy was significantly different.

CONCLUSION: There was a statistically significant correlation between clinical parameters, muscle activity and a patient’s subjective perception. Therefore, it can be concluded that successful periodontal flap surgery led to improvements in masticatory efficiency and subjective perception, as determined by the OIDP questionnaire.

PMID:37102081 | PMC:PMC10124113 | DOI:10.1016/j.jtumed.2022.09.013

Stat Sin. 2023 Jan;33(1):259-279. doi: 10.5705/ss.202020.0226.

ABSTRACT

In some supervised learning settings, the practitioner might have additional information on the features used for prediction. We propose a new method which leverages this additional information for better prediction. The method, which we call the feature-weighted elastic net (“fwelnet”), uses these “features of features” to adapt the relative penalties on the feature coefficients in the elastic net penalty. In our simulations, fwelnet outperforms the lasso in terms of test mean squared error and usually gives an improvement in true positive rate or false positive rate for feature selection. We also apply this method to early prediction of preeclampsia, where fwelnet outperforms the lasso in terms of 10-fold cross-validated area under the curve (0.86 vs. 0.80). We also provide a connection between fwelnet and the group lasso and suggest how fwelnet might be used for multi-task learning.

PMID:37102071 | PMC:PMC10129060 | DOI:10.5705/ss.202020.0226

Malays J Med Sci. 2023 Apr;30(2):153-160. doi: 10.21315/mjms2023.30.2.14. Epub 2023 Apr 18.

ABSTRACT

BACKGROUND: The vaccinated travel lane (VTL) between Malaysia and Singapore was implemented to facilitate travelling between countries without the need for quarantine.

OBJECTIVES: i) Observe the rate of positive SARS-CoV-2 test results amongst inbound international travellers; ii) Explore possible factors associated with the outcome of test results between VTL and non-VTL travellers.

METHOD: This is a retrospective cross-sectional study involving air travellers arriving in Malaysia via the Kuala Lumpur International Airport (KLIA) or Kuala Lumpur International Airport 2 (KLIA2) who were tested for SARS-CoV-2 by reverse transcriptase polymerase chain reaction (RT-PCR) from 29 November 2021 to 15 March 2022. Subject demographics and RT-PCR results were retrieved from the laboratory information system and statistically analysed.

RESULTS: Out of 118,902 travellers, mostly were Malaysian nationals (62.7%) and VTL travellers (68.2%) with a median age of 35 years old. A total of 699 (0.6%) of travellers tested positive on arrival, out of which 70.2% had cycle threshold (Ct) values > 30 (70.8% of VTL and 70.0% of non-VTL cohorts). Non-VTL travellers were 4.5 times more likely to test positive compared with VTL travellers (1.25% versus 0.28%; P < 0.001).

CONCLUSION: Tighter entry requirements including vaccination status and testing frequency, the use of sensitive detection methods on arrival and similar public health policies between countries may have contributed to the VTL being a safe and cost-effective mode of travel.

PMID:37102055 | PMC:PMC10125236 | DOI:10.21315/mjms2023.30.2.14

J Educ Eval Health Prof. 2023;20:14. doi: 10.3352/jeehp.2023.20.14. Epub 2023 Apr 27.

ABSTRACT

PURPOSE: The aim of this study was to identify factors influencing the learning transfer of nursing students in a non-face-to-face educational environment through structural equation modeling and suggest ways to improve the transfer of learning.

METHODS: In this cross-sectional descriptive study, data were collected via online surveys from February 9 to March 1, 2022, from 218 nursing students in Korea. Learning transfer, learning immersion, learning satisfaction, learning efficacy, self-directed learning ability and information technology utilization ability were analyzed using IBM SPSS for Windows ver. 22.0 and AMOS ver. 22.0.

RESULTS: The assessment of structural equation modeling showed adequate model fit, with normed χ2=1.74 (P<0.024), goodness-of-fit index=0.97, adjusted goodness-of-fit index=0.93, comparative fit index=0.98, root mean square residual=0.02, Tucker-Lewis index=0.97, normed fit index=0.96, and root mean square error of approximation=0.06. In a hypothetical model analysis, 9 out of 11 pathways of the hypothetical structural model for learning transfer in nursing students were statistically significant. Learning self-efficacy and learning immersion of nursing students directly affected learning transfer, and subjective information technology utilization ability, self-directed learning ability, and learning satisfaction were variables with indirect effects. The explanatory power of immersion, satisfaction, and self-efficacy for learning transfer was 44.4%.

CONCLUSION: The assessment of structural equation modeling indicated an acceptable fit. It is necessary to improve the transfer of learning through the development of a self-directed program for learning ability improvement, including the use of information technology in nursing students’ learning environment in non-face-to-face conditions.

PMID:37100591 | DOI:10.3352/jeehp.2023.20.14

Int Forum Allergy Rhinol. 2023 Apr 26. doi: 10.1002/alr.23173. Online ahead of print.

ABSTRACT

BACKGROUND: Nasal airway obstruction (NAO) is a highly prevalent disorder. Septal swell body (SSB) hypertrophy is an often-overlooked contributor to NAO. SSB treatment may relieve symptoms of NAO. The objective of this study was to assess the clinical use of a temperature-controlled radiofrequency (TCRF) device to treat SSBs to improve symptoms in adults with NAO.

METHODS: In this prospective, multicenter, open-label, single arm study, patients with severe or extreme NAO related to SSB hypertrophy received bilateral TCRF treatment in the SSB area. The primary endpoint was improvement in Nasal Obstruction Symptom Evaluation (NOSE) scale scores from baseline to 3 months post-procedure. A subset of study patients underwent computed tomography (CT) imaging to evaluate post-treatment changes in SSB size.

RESULTS: Mean NOSE scale scores significantly improved from 73.5 (SD 14.2) at baseline to 27.9 (SD 17.2) at 3 months post-procedure; a reduction of -45.3 (SD 21.4), (95% confidence interval [CI]: -50.4 to -40.1; p< 0.0001): the responder rate was 95.7% (95% CI: 0.88 to 0.99; p < 0.0001). CT evaluation at 3 months showed statistically significant reductions in the SSB with the greatest reduction in the middle thickness: (mean change -3.4 [SD 1.8] millimeters [95% CI: -4.0 to -2.8; p<.0001]). Minimal adverse events with any relationship to the device or procedure were reported, none were serious in nature and no septal perforations occurred.

CONCLUSIONS: This study demonstrates that temperature-controlled radiofrequency treatment of SSB hypertrophy is well-tolerated and effective at reducing both SSB size and symptoms of NAO at 3 months post-treatment.

PMID:37100587 | DOI:10.1002/alr.23173