MyMedR

Displaying all 4 publications

Abstract:

Sort:

Fulltext Boosting-based ensemble machine learning models for predicting unconfined compressive strength of geopolymer stabilized clayey soil

Abdullah GMS, Ahmad M, Babur M, Badshah MU, Al-Mansob RA, Gamil Y, et al.

Sci Rep, 2024 Jan 28;14(1):2323.
PMID: 38282061 DOI: 10.1038/s41598-024-52825-7

The present research employs new boosting-based ensemble machine learning models i.e., gradient boosting (GB) and adaptive boosting (AdaBoost) to predict the unconfined compressive strength (UCS) of geopolymer stabilized clayey soil. The GB and AdaBoost models were developed and validated using 270 clayey soil samples stabilized with geopolymer, with ground-granulated blast-furnace slag and fly ash as source materials and sodium hydroxide solution as alkali activator. The database was randomly divided into training (80%) and testing (20%) sets for model development and validation. Several performance metrics, including coefficient of determination (R2), mean absolute error (MAE), root mean square error (RMSE), and mean squared error (MSE), were utilized to assess the accuracy and reliability of the developed models. The statistical results of this research showed that the GB and AdaBoost are reliable models based on the obtained values of R2 (= 0.980, 0.975), MAE (= 0.585, 0.655), RMSE (= 0.969, 1.088), and MSE (= 0.940, 1.185) for the testing dataset, respectively compared to the widely used artificial neural network, random forest, extreme gradient boosting, multivariable regression, and multi-gen genetic programming based models. Furthermore, the sensitivity analysis result shows that ground-granulated blast-furnace slag content was the key parameter affecting the UCS.
Fulltext Long short term memory networks for predicting resilient Modulus of stabilized base material subject to wet-dry cycles

Al-Zubi MA, Ahmad M, Abdullah S, Khan BJ, Qamar W, Abdullah GMS, et al.

Sci Rep, 2024 Nov 13;14(1):27928.
PMID: 39537833 DOI: 10.1038/s41598-024-79588-5

The resilient modulus (MR) of different pavement materials is one of the most important input parameters for the mechanistic-empirical pavement design approach. The dynamic triaxial test is the most often used method for evaluating the MR, although it is expensive, time-consuming, and requires specialized lab facilities. The purpose of this study is to establish a new model based on Long Short-Term Memory (LSTM) networks for predicting the MR of stabilized base materials with various additives during wet-dry cycles (WDC). A laboratory dataset of 704 records has been used using input parameters, including WDC, ratio of calcium oxide to silica, alumina, and ferric oxide compound, Maximum dry density to the optimal moisture content ratio (DMR), deviator stress (σd), and confining stress (σ3). The results demonstrate that the LSTM technique is very accurate, with coefficients of determination of 0.995 and 0.980 for the training and testing datasets, respectively. The LSTM model outperforms other developed models, such as support vector regression and least squares approaches, in the literature. A sensitivity analysis study has determined that the DMR parameter is the most significant factor, while the σd parameter is the least significant factor in predicting the MR of the stabilized base material under WDC. Furthermore, the SHapley Additive exPlanations approach is employed to elucidate the optimal model and examine the impact of its features on the final result.
CROCuS, a Phase II Study Evaluating the Antiviral Activity, Clinical Outcomes, and Safety of Rilematovir in Children Aged ≥ 28 Days and ≤ 3 Years with Acute Respiratory Tract Infection Due to Respiratory Syncytial Virus

Ferrero F, Lin CY, Liese J, Luz K, Stoeva T, Nemeth A, et al.

Paediatr Drugs, 2024 Apr 22.
PMID: 38649595 DOI: 10.1007/s40272-024-00625-x

BACKGROUND: Respiratory syncytial virus (RSV) causes significant morbidity and mortality in children aged ≤ 5 years and adults aged ≥ 60 years worldwide. Despite this, RSV-specific therapeutic options are limited. Rilematovir is an investigational, orally administered inhibitor of RSV fusion protein-mediated viral entry.
OBJECTIVE: To establish the antiviral activity, clinical outcomes, safety, and tolerability of rilematovir (low or high dose) in children aged ≥ 28 days and ≤ 3 years with RSV disease.
METHODS: CROCuS was a multicenter, international, double-blind, placebo-controlled, randomized, adaptive phase II study, wherein children aged ≥ 28 days and ≤ 3 years with confirmed RSV infection who were either hospitalized (Cohort 1) or treated as outpatients (Cohort 2) were randomized (1:1:1) to receive rilematovir (low or high dose) or placebo. Study treatment was administered daily as an oral suspension from days 1 to 7, with dosing based on weight and age groups. The primary objective was to establish antiviral activity of rilematovir by evaluating the area under the plasma concentration-time curve of RSV viral load in nasal secretions from baseline through day 5. Severity and duration of RSV signs and symptoms and the safety and tolerability of rilematovir were also assessed through day 28 (± 3).
RESULTS: In total, 246 patients were randomized, treated, and included in the safety analysis population (Cohort 1: 147; Cohort 2: 99). Of these, 231 were included in the intent-to-treat-infected analysis population (Cohort 1: 138; Cohort 2: 93). In both cohorts, demographics were generally similar across treatment groups. In both cohorts combined, the difference (95% confidence interval) in the mean area under the plasma concentration-time curve of RSV RNA viral load through day 5 was - 1.25 (- 2.672, 0.164) and - 1.23 (- 2.679, 0.227) log10 copies∙days/mL for the rilematovir low-dose group and the rilematovir high-dose group, respectively, when compared with placebo. The estimated Kaplan-Meier median (95% confidence interval) time to resolution of key RSV symptoms in the rilematovir low-dose, rilematovir high-dose, and placebo groups of Cohort 1 was 6.01 (4.24, 7.25), 5.82 (4.03, 8.18), and 7.05 (5.34, 8.97) days, respectively; in Cohort 2, estimates were 6.45 (4.81, 9.70), 6.26 (5.41, 7.84), and 5.85 (3.90, 8.27) days, respectively. A similar incidence of adverse events was reported in patients treated with rilematovir and placebo in Cohort 1 (rilematovir: 61.9%; placebo: 58.0%) and Cohort 2 (rilematovir: 50.8%; placebo: 47.1%), with most reported as grade 1 or 2 and none leading to study discontinuation. The study was terminated prematurely, as the sponsor made a non-safety-related strategic decision to discontinue rilematovir development prior to full recruitment of Cohort 2.
CONCLUSIONS: Data from the combined cohort suggest that rilematovir has a small but favorable antiviral effect of indeterminate clinical relevance compared with placebo, as well as a favorable safety profile. Safe and effective therapeutic options for RSV in infants and young children remain an unmet need.
CLINICAL TRIAL REGISTRATION: EudraCT Number: 2016-003642-93; ClinicalTrials.gov Identifier: NCT03656510. First posted date: 4 September, 2018.
Subcutaneous versus Intravenous Amivantamab, both in Combination with Lazertinib, in Refractory EGFR-mutated NSCLC: Primary Results from the Phase 3 PALOMA-3 Study

Leighl NB, Akamatsu H, Lim SM, Cheng Y, Minchom AR, Marmarelis ME, et al.

J Clin Oncol, 2024 Jun 10.
PMID: 38857463 DOI: 10.1200/JCO.24.01001

PURPOSE: Phase 3 studies of intravenous amivantamab demonstrated efficacy across EGFR-mutated advanced non-small cell lung cancer (NSCLC). A subcutaneous formulation could improve tolerability and reduce administration time while maintaining efficacy.
PATIENTS AND METHODS: Patients with EGFR-mutated advanced NSCLC who progressed following osimertinib and platinum-based chemotherapy were randomized 1:1 to receive subcutaneous or intravenous amivantamab, both combined with lazertinib. Co-primary pharmacokinetic noninferiority endpoints were trough concentrations (Ctrough; on cycle-2-day-1 or cycle-4-day-1) and cycle-2 area under the curve (AUCD1-D15). Key secondary endpoints were objective response rate (ORR) and progression-free survival (PFS). Overall survival (OS) was a predefined exploratory endpoint.
RESULTS: Overall, 418 patients underwent randomization (subcutaneous group, n=206; intravenous group, n=212). Geometric mean ratios of Ctrough for subcutaneous to intravenous amivantamab were 1.15 (90% CI, 1.04-1.26) at cycle-2-day-1 and 1.42 (90% CI, 1.27-1.61) at cycle-4-day-1; the cycle-2 AUCD1-D15 was 1.03 (90% CI, 0.98-1.09). ORR was 30% in the subcutaneous and 33% in the intravenous group; median PFS was 6.1 and 4.3 months, respectively. OS was significantly longer in the subcutaneous versus intravenous group (hazard ratio for death, 0.62; 95% CI, 0.42-0.92; nominal P=0.02). Fewer patients in the subcutaneous group experienced infusion-related reactions (13% versus 66%) and venous thromboembolism (9% versus 14%) versus the intravenous group. Median administration time for first infusion was reduced to 4.8 minutes (range, 0-18) for subcutaneous amivantamab from 5 hours (range, 0.2-9.9) for intravenous amivantamab. During cycle-1-day-1, 85% and 52% of patients in the subcutaneous and intravenous groups, respectively, considered treatment convenient; end-of-treatment rates were 85% and 35%, respectively.
CONCLUSION: Subcutaneous amivantamab-lazertinib demonstrated noninferiority to intravenous amivantamab-lazertinib, offering a consistent safety profile with reduced infusion-related reactions, increased convenience, and prolonged survival.