MyMedR

Displaying all 8 publications

Abstract:

Sort:

Fulltext Hyperparameter Tuning and Pipeline Optimization via Grid Search Method and Tree-Based AutoML in Breast Cancer Prediction

Radzi SFM, Karim MKA, Saripan MI, Rahman MAA, Isa INC, Ibahim MJ

J Pers Med, 2021 Sep 29;11(10).
PMID: 34683118 DOI: 10.3390/jpm11100978

Automated machine learning (AutoML) has been recognized as a powerful tool to build a system that automates the design and optimizes the model selection machine learning (ML) pipelines. In this study, we present a tree-based pipeline optimization tool (TPOT) as a method for determining ML models with significant performance and less complex breast cancer diagnostic pipelines. Some features of pre-processors and ML models are defined as expression trees and optimal gene programming (GP) pipelines, a stochastic search system. Features of radiomics have been presented as a guide for the ML pipeline selection from the breast cancer data set based on TPOT. Breast cancer data were used in a comparative analysis of the TPOT-generated ML pipelines with the selected ML classifiers, optimized by a grid search approach. The principal component analysis (PCA) random forest (RF) classification was proven to be the most reliable pipeline with the lowest complexity. The TPOT model selection technique exceeded the performance of grid search (GS) optimization. The RF classifier showed an outstanding outcome amongst the models in combination with only two pre-processors, with a precision of 0.83. The grid search optimized for support vector machine (SVM) classifiers generated a difference of 12% in comparison, while the other two classifiers, naïve Bayes (NB) and artificial neural network-multilayer perceptron (ANN-MLP), generated a difference of almost 39%. The method's performance was based on sensitivity, specificity, accuracy, precision, and receiver operating curve (ROC) analysis.
Fulltext Neoadjuvant Therapy Using Checkpoint Inhibitors before Radical Cystectomy for Muscle Invasive Bladder Cancer: A Systematic Review

Shsm H, Fahmy UA, Alhakamy NA, Khairul-Asri MG, Fahmy O

J Pers Med, 2021 Nov 13;11(11).
PMID: 34834547 DOI: 10.3390/jpm11111195

BACKGROUND: Neoadjuvant chemotherapy is the standard of care before radical cystectomy for muscle invasive bladder cancer. Recently, checkpoint inhibitors have been investigated as a neoadjuvant treatment after the reported efficacy of checkpoint inhibitors in metastatic urothelial carcinoma.
OBJECTIVES: The aim of this systematic review is to investigate the role of checkpoint inhibitors as a neoadjuvant treatment for muscle invasive bladder cancer before radical cystectomy.
METHODS: Based on the PRISMA statement, a systematic review of the literature was conducted through online databases and the American Society of Clinical Oncology (ASCO) Meeting Library. Suitable publications were subjected to full-text assessment. The primary outcome of this review was to identify the impact of neoadjuvant immunotherapy on the oncological outcomes and survival benefits.
RESULTS: From the retrieved 254 results, 8 studies including 404 patients were included. Complete response varied between 30% and 50%. Downstaging varied between 50% and 74%. ≥Grade 3 AEs were recorded in 8.6% of patients who received monotherapy with either Atezolizumab or Pembrolizumab. In patients who received combination treatment, the incidence of ≥Grade 3 AEs was 16.3% for chemoimmunotherapy and 36.5% for combined immunotherapy. A total of 373 patients (92%) underwent radical cystectomy. ≥Grade 3 Clavien-Dindo surgical complications were reported in 21.7% of the patients. One-year overall survival (OS) and relapse-free survival (RFS) varied between 81% and 92%, and 70% and 88%, respectively.
CONCLUSION: The evidence on the use of immune checkpoint inhibitors in the setting of pre-radical cystectomy is quite limited, with noted variability within published trials. Combination with chemotherapy or another checkpoint inhibitor may boost response, although prospective studies with extended follow-up are needed to report on the survival advantages.
Fulltext Oncological Response and Predictive Biomarkers for the Checkpoint Inhibitors in Castration-Resistant Metastatic Prostate Cancer: A Systematic Review and Meta-Analysis

Fahmy O, Alhakamy NA, Khairul-Asri MG, Ahmed OAA, Fahmy UA, Fresta CG, et al.

J Pers Med, 2021 Dec 23;12(1).
PMID: 35055323 DOI: 10.3390/jpm12010008

Recently, checkpoint inhibitors have been investigated in metastatic prostate cancer, however their overall effect is unclear and needs to be further investigated.
OBJECTIVES: The aim of this systematic review is to investigate the oncological response of metastatic castration-resistant prostate cancer patients to immune checkpoint inhibitors.
METHODS: Based on the preferred reporting items for systematic reviews and meta-analyses (PRISMA) statement, a systematic review of the literature was conducted through online electronic databases and the American Society of Clinical Oncology (ASCO) Meeting Library. Eligible publications were selected after a staged screening and selection process. RevMan 5.4 software was employed to run the quantitative analysis and forest plots. Risk of bias assessment was conducted using the Cochrane tool and Newcastle-Ottawa Scale for the randomized and non-randomized trials, respectively.
RESULTS: From the 831 results retrieved, 8 studies including 2768 patients were included. There was no significant effect on overall survival (OS) (overall response (OR) = 0.98; Z = 0.42; p = 0.67). Meanwhile, progression-free survival (PFS) was significantly better with immune checkpoint inhibitors administration (OR = 0.85; Z = 3.9; p < 0.0001). The subgroup analysis for oncological outcomes based on programmed death ligand 1 (PD-L1) positivity status displayed no significant effect, except on prostate-specific antigen response rate (PSA RR) (OR = 3.25; Z = 2.29; p = 0.02). Based on DNA damage repair (DDR), positive patients had a significantly better PFS and a trend towards better OS and overall response rate (ORR); the ORR was 40% in positive patients compared to 20% in the negative patients (OR = 2.46; Z = 1.3; p = 0.19), while PSA RR was 23.5% compared to 14.3% (OR = 1.88; Z = 0.88; p = 0.38). Better PFS was clearly associated with DDR positivity (OR = 0.70; Z = 2.48; p = 0.01) with a trend towards better OS in DDR positive patients (OR = 0.71; Z = 1.38; p = 0.17). Based on tumor mutation burden (TMB), ORR was 46.7% with high TMB versus 8.8% in patients with low TMB (OR = 11.88; Z = 3.0; p = 0.003).
CONCLUSIONS: Checkpoint inhibitors provide modest oncological advantages in metastatic castration-resistant prostate cancer. There are currently no good predictive indicators that indicate a greater response in some patients.
Fulltext Pharmacogenomics of Cancer Pain Treatment Outcomes in Asian Populations: A Review

Satkunananthan SE, Suppiah V, Toh GT, Yow HY

J Pers Med, 2022 Nov 18;12(11).
PMID: 36422103 DOI: 10.3390/jpm12111927

In advanced cancer, pain is a poor prognostic factor, significantly impacting patients' quality of life. It has been shown that up to 30% of cancer patients in Southeast Asian countries may receive inadequate analgesia from opioid therapy. This significant under-management of cancer pain is largely due to the inter-individual variability in opioid dosage and relative efficacy of available opioids, leading to unpredictable clinical responses to opioid treatment. Single nucleotide polymorphisms (SNPs) cause the variability in opioid treatment outcomes, yet their association in Asian populations remains unclear. Therefore, this review aimed to evaluate the association of SNPs with variability in opioid treatment responses in Asian populations. A literature search was conducted in Medline and Embase databases and included primary studies investigating the association of SNPs in opioid treatment outcomes, namely pharmacokinetics, opioid dose requirements, and pain control among Asian cancer patients. The results show that CYP2D6*10 has the most clinical relevance in tramadol treatment. Other SNPs such as rs7439366 (UGT2B7), rs1641025 (ABAT) and rs1718125 (P2RX7) though significant have limited pharmacogenetic implications due to insufficient evidence. OPRM1 rs1799971, COMT rs4680 and ABCB1 (rs1045642, rs1128503, and rs2032582) need to be further explored in future for relevance in Asian populations.
Fulltext Prolonged Maternal Separation Reduces Anxiety State and Increases Compulsive Burying Activity in the Offspring of BALB/c Mice

Jarrar Q, Ayoub R, Alhussine K, Goh KW, Moshawih S, Ardianto C, et al.

J Pers Med, 2022 Nov 17;12(11).
PMID: 36422097 DOI: 10.3390/jpm12111921

BACKGROUND: The elevated plus maze (EPM) and the marble burying (MB) tests are common behavioral tests used for behavioral phenotyping in mouse models for neurodevelopmental disorders. However, the behavioral effects of maternal separation (MS), a standard paradigm for early life stress in animals, in both the EPM and MB tests remain incompletely known.
OBJECTIVES: This study aimed to investigate the behavioral effects of prolonged MS in the offspring of mice using the EPM and MB tests.
METHODS: Male BALB/c mice were isolated from their mothers for 4 h each day during the first 30 days after birth. On day 50 postnatal, groups of separated and non-separated mice (n = 18/each group) were subjected to the EPM and MB tests for comparative behavioral evaluations. In addition, the locomotor activity of mice was evaluated using the actophotometer test.
RESULTS: The findings of the EPM test revealed that separated mice exhibited anxiolytic-like behaviors, as evidenced by a significant increase in the latency to closed arms and the time spent in the open arms compared with non-separated mice. Separated mice also showed compulsive burying activity in the MB test, as determined by a significant increase in the number of buried marbles. The results of the actophotometer test did not show any significant change in locomotor activity.
CONCLUSIONS: Prolonged MS caused the adult offspring of mice to exhibit a decrease in anxiety state and increased compulsive burying activity, which were not associated with a change in locomotor activity. Further investigations with validated tests are needed to support these findings.
Fulltext Adoption of a Digital Patient Health Passport as Part of a Primary Healthcare Service Delivery: Systematic Review

Tuan Soh TY, Nik Mohd Rosdy NMM, Mohd Yusof MYP, Azhar Hilmy SH, Md Sabri BA

J Pers Med, 2022 Nov 01;12(11).
PMID: 36579540 DOI: 10.3390/jpm12111814

The utilization of digital personal health records is considered to be appropriate for present-time usage; it is expected to further enhance primary care's quality-of-service delivery. Despite numerous studies conducted on digital personal health records, efforts in a systematic evaluation of the topic have failed to establish the specific benefits gained by patients, health providers, and healthcare systems. This study aimed to conduct a systematic review regarding the impact of digital personal health records in relation to the delivery of primary care. The review methods included five methodological elements that were directed by the review protocol 2020 (PRISMA). Over a time period of 10 years (2011-2021), 2492 articles were retrieved from various established databases, including Scopus, Web of Science, PubMed, EBSCO-Medline, and Google Scholar, and based on reference mining. The Mixed Method Appraisal Tool (MMAT) was used for quality appraisal. A thematic analysis was performed to develop the themes in this study. The thematic analysis performed on 13 articles resulted in seven main themes, which were empowering the patient, helping with communication, improving relationships, improving the quality of care, maintaining health records, sharing records, and saving time. We concluded the study by expanding the seven themes into 26 sub-themes, of which each served as answers to our main research question that prompted this systematic review.
Fulltext SLC1A2 Gene Polymorphism Influences Methamphetamine-Induced Psychosis

Yahya DN, Guad RM, Wu YS, Gan SH, Gopinath SCB, Zakariah HA, et al.

J Pers Med, 2023 Jan 31;13(2).
PMID: 36836504 DOI: 10.3390/jpm13020270

SLC1A2 is a gene encoded for the excitatory amino acid transporter 2 which is responsible for glutamate reuptake from the synaptic cleft in the central nervous system. Recent studies have suggested that polymorphisms on glutamate transporters can affect drug dependence, leading to the development of neurological diseases and psychiatric disorders. Our study investigated the association of rs4755404 single nucleotide polymorphism (SNP) of the SLC1A2 gene with methamphetamine (METH) dependence and METH-induced psychosis and mania in a Malaysian population. The rs4755404 gene polymorphism was genotyped in METH-dependent male subjects (n = 285) and male control subjects (n = 251). The subjects consisted of the four ethnic groups in Malaysia (Malay, Chinese, Kadazan-Dusun, and Bajau). Interestingly, there was a significant association between rs4755404 polymorphism and METH-induced psychosis in the pooled METH-dependent subjects in terms of genotype frequency (p = 0.041). However, there was no significant association between rs4755404 polymorphism and METH dependence. Also, the rs455404 polymorphism was not significantly associated with METH-induced mania for both genotype frequencies and allele frequencies in the METH-dependent subjects, regardless of stratification into the different ethnicities. Our study suggests that the SLC1A2 rs4755404 gene polymorphism confers some susceptibility to METH-induced psychosis, especially for those who carry the GG homozygous genotype.
Fulltext Systematic Identification of Familial Hypercholesterolaemia in Primary Care-A Systematic Review

Silva L, Qureshi N, Abdul-Hamid H, Weng S, Kai J, Leonardi-Bee J

J Pers Med, 2021 Apr 15;11(4).
PMID: 33920869 DOI: 10.3390/jpm11040302

Familial hypercholesterolaemia (FH) is a common inherited cause of premature cardiovascular disease, but the majority of patients remain undiagnosed. The aim of this systematic review was to assess the effectiveness of interventions to systematically identify FH in primary care. No randomised, controlled studies were identified; however, three non-randomised intervention studies were eligible for inclusion. All three studies systematically identified FH using reminders (on-screen prompts) in electronic health records. There was insufficient evidence that providing comments on laboratory test results increased the identification of FH using the Dutch Lipid Clinic Network (DLCN) criteria. Similarly, using prompts combined with postal invitation demonstrated no significant increase in definite FH identification using Simon-Broome (SB) criteria; however, the identification of possible FH increased by 25.4% (CI 17.75 to 33.97%). Using on-screen prompts alone demonstrated a small increase of 0.05% (95% CI 0.03 to 0.07%) in identifying definite FH using SB criteria; however, when the intervention was combined with an outreach FH nurse assessment, the result was no significant increase in FH identification using a combination of SB and DLCN criteria. None of the included studies reported adverse effects associated with the interventions. Currently, there is insufficient evidence to determine which is the most effective method of systematically identifying FH in non-specialist settings.