Real Utility Research Articles

Clinical Utility of Metagenomic Next-Generation Sequencing of Plasma Microbial Cell-Free DNA: a Single-Center Retrospective Study

Abstract Infectious diseases account for significant morbidity and mortality in healthcare, and metagenomic next-generation sequencing of plasma microbial cell-free DNA has emerged as a promising non-invasive diagnostic tool in this scenario. However, the available data on the real impact of this test in clinical practice is limited and conflicting. In this context, we performed a retrospective evaluation of the utilization of this test at our institution since February 17, 2019. A total of 76 tests were performed in this period in 68 different patients. The mean age of the patients was 9 years old, with 40 being male (58.82%) and 28 female (41.18%). The ordering specialties included infectious diseases (82.90%), hematology/oncology (9.21%), neurology (3.95%), pulmonology (2.63%), and dermatology (1.31%). The vast majority of the tests were ordered as inpatient (73 tests, 96.05%). 45 tests (59.21%) resulted as positive, of which 19 (42.22%) were polymicrobial. The tests were concordant with conventional microbiological studies 47 times (61.84%). Most tests (67 tests, 88.16%) had no significant clinical impact, 8 tests (10.53%) had a positive impact, and one test (1.31%) had an indeterminate impact. No tests were determined to have a negative clinical impact. Overall, our data is consistent with most studies which assessed the clinical utility of metagenomic next-generation sequencing of plasma microbial cell-free DNA in the literature, showing that testing did not have a significant impact on patient care for the majority of cases. There were some cases, however, in which testing showed a positive impact in escalating or de-escalating antibiotic therapy. In conclusion, despite being mostly a bystander, in selected cases and in the right clinical context, the test can be useful to guide antimicrobial treatment without causing significant harm. More studies are needed to further investigate the real utility of the test.

A dream of preventive medicine

Multi-Cancer Early Detection is a highly popular topic, bringing the hope of being able to detect very early, non-symptomatic cancers and allowing more successful therapy. A major company in this space is GRAIL, which has attracted very significant financing and launched large-scale tests of its detection systems. However, the real clinical utility of these tests remains to be demonstrated, and fundamental issues are still pending.

L’utilité du facteur d’épissage SRSF1 dans le grading des tumeurs gliales: Une méta-analyse

The grading of glial tumors is based on morphological and sometimes on molecular features. Many markers have been assessed in order to grade the glial tumours without a real consensus. Some authors reported that SRSF1, a spiling factor, presents an expression correlated to the tumours grades. In this study, we aimed to assess the utility of the SRSF1 into the grading of gliomas based on its immunohistochemical expression. The authors conducted a meta-analysis under the PRISMA guidelines during a 10-year-period (2013-2023). The Meta-Disc software 5.4 (free version) was used. Q test and I2 statistics were carried out to explore the heterogeneity among studies. Meta-regression was performed in case of significant heterogeneity. Publication bias was assessed using the funnel plot test and the Egger's test (free version JASP). According to the inclusion criteria, 4 studies from 193 articles were included. The pooled SEN, SPE and DOR accounted respectively for 0.592, 0.565 and 1.852. The AUC was estimated to 0.558 suggesting a bad diagnostic accuracy. The heterogeneity in the pooled SEN and SPE was statistically significant. The meta-regression analysis focusing on the technique used, the clones, the dilution, the interpretation technique revealed no covariate factors (P>0.05). Even if this meta-analysis highlighted the absence of a real diagnostic utility of the SRSF1 in grading the glial tumours, the heterogeneity revealed reinforces the need for more prospective studies performed according to the quality assessment criteria.

Interpreting and managing preservation fluids positive for Gram-negative bacteria.

Culturing preservation fluids of solid organs before transplantation is not a standardized procedure. In this review, we aim to describe the state-of-the-art of literature evidence in this debated setting with a special focus on Gram-negative bacteria (GNB). Contamination of preservation fluids is frequent, but preservation fluids related infections are rare and most commonly caused by high-risk pathogens, including GNB. GNB preservation fluids related infections are characterized by high morbidity and mortality. Recent studies showed improved outcomes in solid organ transplant recipients receiving antibiotic therapy tailored according to preservation fluids cultures especially when multidrug-resistant GNB are found. A robust procurement network is needed to alert recipients' centers in cases of positivity and the support of transplant infectious diseases specialists is essential to choose the best therapy. Culturing preservation fluids is a further step into preventing donor-derived infections. Interpreting and managing GNB positivity require a multidisciplinary team with specific skills. Standardized randomized trials are needed for insight into the real utility of preservation fluids cultures, the role of preservation fluids positivity, and the impact of antimicrobial therapy.

The Value of CEUS LI-RADS combined with AFP in early diagnosis of hepatocellular carcinoma in low- and high-risk patients.

We found that the occurrence of hepatocellular carcinoma (HCC) has increased significantly in non-cirrhotic individuals, with HCC being frequently overlooked or misdiagnosed. Contrast-enhanced ultrasound (CEUS) Liver Imaging Reporting and Data System (LI-RADS) is known to have a high diagnostic quality in high-risk HCC patients. Therefore, we aimed to compare the detection accuracy of CEUS LI-RADS for HCC between low- and high-risk individuals, to confirm its value in low-risk patients at increased risk of HCC, but not yet included in the high-risk groups of LI-RADS. In addition, since CEUS LR-4 and LR-M categories contain a relatively high proportion of HCC, and serum alpha-fetoprotein (AFP) is the most commonly used biomarker for HCC, and the clinically valid, we attempted to further improve the early diagnostic capability of CEUS LI-RADS for HCC in the low-risk and high-risk patients by combining CEUS LR-4 and LR-M categories with AFP. We defined high-risk groups (HR)-included in the high-risk patients of LI-RADS, low-risk groups (LR)-not included in the high-risk patients of LI-RADS and enrolled 189 HCC patients with LR and HR settings in a retrospective study. All lesions were confirmed histopathologically. The CEUS LI-RADS accuracy for detecting HCC in these two patients was compared. In addition, the diagnostic algorithm in our study was proposed (for CEUS LR-4 and LR-M patients with AFP>20 ng/ml). we analyzed the ability of CEUS LI-RADS as a valid method of establishing the early diagnosis of HCC in LR and HR patients by combining LR-4 and LR-M categories with AFP. Through comparative analysis, the specificity of the CEUS LR-5 category for HCC in the HR group was 78.4%, whereas in the LR group, it was 94.2%. Meanwhile, the sensitivity (63.2% vs. 63.0%) and positive predictive value (PPV) (75.0% vs. 88.7%) did not differ between the LR and HR groups ( P = 0.990, P = 0.299). It is noteworthy that there were the high proportion of HCC in CEUS LR-4 and LR-M categories in our cases and when we combined CEUS LR-4 and LR-M categories with AFP significantly improved the sensitivity by 21.0% (84.2%) in the LR group, and by 16.0% (79.0%) in the HR group, with statistically difference in sensitivity after combination in the HR group ( P = 0.014). The CEUS LR-5 category has real meaningful utility in the diagnosis of HCC in both LR and HR patients. The early detection power of the CEUS LI-RADS category for HCC patients was further increased when the CEUS LR-4 and LR-M categories were combined with elevated AFP.

Disseminating the Real-World Importance of Conjunct Studies of Acculturation, Transculturation, and Deculturation Processes: Why this can be a Useful Technique to Analyze Real-World Observations

We begin this paper by reviewing the core tenets and principles of the symbiotic approach of sociocultural change or the “Proactive-interactive- symbiotic approach to long-term cultural change”, that we had proposed several years ago, and by representing it in brief for the benefit of our readers. We also then review and go through various others concepts centered on, and pertaining to acculturation, enculturation, and transculturation, and compare them with the already preexisting concepts in the market. We also then go on to explain why conjunct studies of acculturation, transculturation, and deculturation processes of various types need to be carried out, and lay forth their real world utility as well. We do this by examining the different types of acculturation, transculturation, and deculturation processes and methods from the aforesaid perspective. We also provide various case studies drawn from different communities from different parts of the world around these concepts to beef up our case, and lend more credence to the tenets of our thesis. Last, but not the least, we explain why these concepts could form an essential and an intrinsic component of post-colonial studies, and form an intrinsic part of our globalization of science movement as well. This would naturally lend a more scientific flavor to cultural studies in general, and post-colonial studies in particular.

Sliding Window Optimal Transport for Open World Artifact Detection in Histopathology.

Histological images are frequently impaired by local artifacts from scanner malfunctions or iatrogenic processes - caused by preparation - impacting the performance of Deep Learning models. Models often struggle with the slightest out-of-distribution shifts, resulting in compromised performance. Detecting artifacts and failure modes of the models is crucial to ensure open-world applicability to whole slide images for tasks like segmentation or diagnosis. We introduce a novel technique for out-of-distribution detection within whole slide images, compatible with any segmentation or classification model. Our approach tiles multi-layer features into sliding window patches and leverages optimal transport to align them with recognized in-distribution samples. We average the optimal transport costs over tiles and layers to detect out-of-distribution samples. Notably, our method excels in identifying failure modes that would harm downstream performance, surpassing contemporary out-of-distribution detection techniques. We evaluate our method for both natural and synthetic artifacts, considering distribution shifts of various sizes and types. The results confirm that our technique outperforms alternative methods for artifact detection. We assess our method components and the ability to negate the impact of artifacts on the downstream tasks. Finally, we demonstrate that our method can mitigate the risk of performance drops in downstream tasks, enhancing reliability by up to 77%. In testing 7 annotated whole slide images with natural artifacts, our method boosted the Dice score by 68%, highlighting its real open-world utility.

Decoding the best automated segmentation tools for vascular white matter hyperintensities in the aging brain: a clinician's guide to precision and purpose.

White matter hyperintensities of vascular origin (WMH) are commonly found in individuals over 60 and increase in prevalence with age. The significance of WMH is well-documented, with strong associations with cognitive impairment, risk of stroke, mental health, and brain structure deterioration. Consequently, careful monitoring is crucial for the early identification and management of individuals at risk. Luckily, WMH are detectable and quantifiable on standard MRI through visual assessment scales, but it is time-consuming and has high rater variability. Addressing this issue, the main aim of our study is to decipher the utility of quantitative measures of WMH, assessed with automatic tools, in establishing risk profiles for cerebrovascular deterioration. For this purpose, first, we work to determine the most precise WMH segmentation open access tool compared to clinician manual segmentations (LST-LPA, LST-LGA, SAMSEG, and BIANCA), offering insights into methodology and usability to balance clinical precision with practical application. The results indicated that supervised algorithms (LST-LPA and BIANCA) were superior, particularly in detecting small WMH, and can improve their consistency when used in parallel with unsupervised tools (LST-LGA and SAMSEG). Additionally, to investigate the behavior and real clinical utility of these tools, we tested them in a real-world scenario (N = 300; age > 50 y.o. and MMSE > 26), proposing an imaging biomarker for moderate vascular damage. The results confirmed its capacity to effectively identify individuals at risk comparing the cognitive and brain structural profiles of cognitively healthy adults above and below the resulted threshold.

Distributed real-time pricing of smart grid considering individual differences

The utility function that characterizes customers’ satisfaction with electricity consumption plays an important and irreplaceable role in the real-time pricing mechanism based on the social welfare maximization model. Without the accurate quantification of customers’ utility, the real-time pricing will deviate from the reality. In fact, the utility functions of different types of customers in different regions should be obtained by fitting a large amount of historical data over a long period of time based on insight into the relationship between factors and utility. Based on the consideration of customers’ individual differences, a new utility function is proposed, which enriches the form of the utility function and provides a reference for fitting a real and accurate utility function. Further, based on this proposed utility function, a real-time pricing model of social welfare maximization is developed to obtain the fair electricity price between customers and the power supplier. On the basis of the separable structure of variables, we design distributed algorithms with global convergence for the pricing model and estimate a worst-case convergence rate. Numerical simulations verify the feasibility and effectiveness of our algorithms and the rationality of the new utility function, i.e., the electricity price based on the proposed utility function is more robust than the existing ones.

Use of recommendation models to provide support to dyslexic students

Dyslexia is the most widespread specific learning disorder and significantly impair different cognitive domains. This, in turn, negatively affects dyslexic students during their learning path. Therefore, specific support must be given to these students. In addition, such a support must be highly personalized, since the problems generated by the disorder can be very different from one to another. In this work, we explored the possibility of using AI to suggest the most suitable supporting tools for dyslexic students, so as to provide a targeted help that can be of real utility. To do this, we relied on recommendation algorithms, which are a branch of machine learning, that aim to detect personal preferences and provide the most suitable suggestions. We hence implemented and trained three collaborative-filtering recommendation models, namely an item-based, a user-based and a weighted-hybrid model, and studied their performance on a large database of 1237 students’ information, collected with a self-evaluating questionnaire regarding all the most used supporting strategies and digital tools. Each recommendation model was tested with three different similarity metrics, namely Pearson correlation, Euclidean distance and Cosine similarity. The obtained results showed that a recommendation system is highly effective in suggesting the optimal help tools/strategies for everyone, with an error less then 12%. As a further evidence of the effectiveness of the implemented system, its precision was 0.85 and its recall was 0.83. The best performing filter was the hybrid one, when Pearson’s correlation is used to measure the distance among users and/or items. In addition, in a final testing performed on 50 students, dyslexic students who used the recommendation algorithm increased their academic scores of almost 1 point in a 1 to 10 scale, showing higher learning performance compared to students who did not use it. This demonstrates that the proposed approach is successful and can be used as a new and effective methodology to support students with dyslexia.

P565 Capillary blood based self-collection device for infliximab therapeutic drug monitoring

Abstract Background Patient friendly new devices may improve therapeutic drug monitoring (TDM) in inflammatory bowel disease (IBD). Our objective was to evaluate an infliximab (IFX) precision guided dosing tool from capillary blood collected using an upper-arm self-collection device amongst IBD patients and compare its performances to gold standard venous blood collected using venipuncture. Methods Patients under maintenance therapy with IFX were recruited from a single IBD center and enrolled in the BEST (Bayesian Estimates Sustaining Trough) study. BEST is a prospective real world evidence clinical utility study to establish the value of an IFX Bayesian forecasting tool in the optimal management of IBD. Blood specimens were collected prospectively, at midcycle or at trough. Capillary blood specimens were collected using an upper arm self-collection device (Tasso Inc., Seattle, WA) connected to a serum separator tube. Paired venous blood was collected using venipuncture. IFX concentrations and antibodies to IFX (ATI) status were measured using drug tolerant homogenous mobility shift assay, albumin levels were measured using nephelometry. IFX Clearance was calculated using nonlinear mixed effect model with Bayesian priors. Statistical analysis consisted of Deming regression. Results Overall, 27 patients (n=9 with UC, mean age=37 years, weight=79 Kg) were enrolled. Median IFX dosing was 10 mg/Kg, and median dosing frequency every 6 weeks. A total of n=58 serum pairs isolated from capillary and venous blood were tested. PK profiles measured from venous blood were optimal during maintenance with no immune response detected (ATI < 3.1 U/mL) and most patients had IFX concentration at trough above 5 µg/mL (98%, median 15.4 µg/mL IQR: 10.9-28.0 µg/mL) and low Clearance (< 0.294 L/day: 89%; median 0.200 L/day IQR: 0.170-0.248 L/day). IFX concentrations and Clearance levels were comparable between venous and capillary blood with high correlation (R2= 0.975; slope =0.928; and R2=0.978; slope =1.035, respectively) (figure). In capillary blood specimens collected at midcycle (median 14 days before the next infusion, n=12 pairs), median IFX concentration was 38.3 µg/mL (IQR: 31.2-64.7 µg/mL) and declined to 21.9 µg/mL (IQR: 14.1-44.5 µg/mL) at trough. There was a high correlation between forecasted and measured trough concentrations in capillary blood (R2=0.925; Deming’s slope=1.093). Similar results were observed with venous blood pairs (R2=0.983; Deming’s slope=1.024). Conclusion IFX therapeutic drug monitoring using patient self-collection of capillary blood performed as well as standard venous blood measurement. This collection method may facilitate the implementation of point of care TDM in clinical practice.

Design of a real prototype of a hybrid fuel cell suv: Vehicle "Hércules"

Hydrogen is becoming one of the most feasible energy vectors to succeed gasoline as fuel. It has the potential to be obtained from renewable energy sources, having almost a null impact on contamination. Oil wells are drying up and oil does not fulfil the ZEV (zero emission vehicle) program of contamination. These reasons lead to think that oil will pass the baton to hydrogen as the next energetic vector for automotive applications. In addition, hydrogen has the advantage of being used directly in fuel cells which have higher efficiency than internal combustion engines (ICE). Project Hércules consists of the construction of a real sport utility vehicle (SUV) prototype of a fuel cell vehicle (FCV) based in the model Santana 350. It will be fuelled by hydrogen obtained totally renewably by using an electrolyser fed by solar energy. This paper shows, in this framework, all the steps that are needed to be covered to specify the power of the fuel cell, battery and electric motor using the simulation tool ADVISORTM to match the desired specifications.

Real World Utility of Next-Generation Sequencing in Neuro-oncology Patients

Real World Utility of Next-Generation Sequencing in Neuro-oncology Patients

Value Stacking of a Customer-Sited BESS for Distribution Grid Support: A Utility Case

This paper proposes a value stacking strategy for a utility-owned, customer-sited battery energy storage system for distribution grid support. The proposed strategy includes three steps: application identification, performance evaluation, and battery system planning. Outage mitigation, non-wires-alternative solution, and voltage support are identified as the primary, secondary, and tertiary applications for the proposed storage system. Reliability performance and economic benefit are calculated and compared for each application in five locations in the Commonwealth of Virginia. Planning results including placement, sizing and scheduling of the battery system are presented with real utility experience and constraints. This work contributes to providing a general and ready-to-use planning methodology for distribution system planners to deploy battery storage systems within service territories, strengthen system reliability performance, and achieve sustainability goals.

Modeling, Integration and Simulation of the Photovoltaic Power Plant Considering LVRT Capability and Transient Voltage Stability

This paper investigates how high photovoltaic energy penetration impacts dynamic performance and voltage regulation of the modified IEEE-9 bus grid. The transmission power system was modeled and simulated using PSCAD-EMTDC software to conduct the study. Load flow analysis is implemented to explore the power system’s capability to incorporate the desired photovoltaic power. Moreover, the study is based on time response simulations to grid disturbances. The supply and control of reactive power from solar power generation plants are becoming critical issues to study because they can facilitate the integration of PV in power grids under different operating conditions. Network-related faults like a PV solar power plant event outage, a three-phase short-circuit at a conventional bus, and a voltage dip at the PV solar power plant have been considered. The results will help identify the protective devices and strategies needed to maintain the stability and reliability of the system operation and transient analysis of the network under external power network fault and recovery operation. Thus, it has practical significance for real utility studies. Moreover, this comprehensive study will be a valuable guide for assessing and improving the grid’s performance under the study of any other grids, which also gives the vast potential and need for solar energy penetration into the grid systems.

The effect of water pollution regulation on prices: Evidence from Wisconsin's phosphorus rule and sewer utility bills

In this paper, we estimate the consumer impacts of Wisconsin's “phosphorus rule”, which created the most stringent statewide water quality and effluent standards for phosphorus in the country. We examine how compliance with the rule affects real billing rates at sewer utilities in Wisconsin, providing the first empirical estimates of water pollution regulation on utility billing rates. We find that compliance with the phosphorous rule increases the average real sewer utility bill in our sample by 7–12%. Our results imply that sewer utilities pass through approximately $65.8 million to residential sewer rate payers annually, which is roughly ⅔ of the total sewer utility compliance costs of the rule. State government subsidies cover an additional ¼ of the sewer utility compliance costs.

Real World Experience and Clinical Utility of Esoguard® - Interim Data from the Lucid Registry

Background: Barrett’s Esophagus (BE) is the only known precursor to esophageal adenocarcinoma (EAC), but historically, screening rates have been low, likely influenced by limitations of upper endoscopy (UE) as the traditional screening modality. EsoGuard® (EG) is a DNA biomarker assay, and EsoCheck® (EC) a noninvasive, swallowable capsule device designed to collect cells from a targeted region of the esophagus. EG and EC in combination offers a well-tolerated, in-office triage test to facilitate BE detection in patients with multiple risk factors. The Lucid Registry captures real-world data from commercial use of EC with EG; we present an interim review of clinical utility data from the first 517 subjects. Methods: Multicenter, prospective, registry capturing data from patients undergoing EC/EG in the commercial setting. This snapshot includes subjects enrolled from registry initiation (April 14, 2023) through August 16, 2023. The primary measure of clinical utility was provider decision impact, namely agreement between EG results and physician decision on whether to refer for subsequent UE. The relationship between BE/EAC risk factors and EG positivity rates was also assessed. Results: Average age was 47.9±14.3 years, 47.2% had history of gastroesophageal reflux disease (GERD), and 63.8% had ≥3 traditional BE/EAC risk factors. 58.8% of subjects were firefighters; when firefighting was treated as an additional BE/EAC risk factor, 81.2% of the study population had ≥3. EG positivity was 14.1%. 437 subjects were followed to the clinical utility endpoint: agreement between EG (+) results and referral for UE was 100%; agreement between EG (-) results and non-referral for UE was 99.4%; concordance between EG results and UE referral was 97.9%. Conclusions: Experience from the Lucid Registry demonstrates that physicians who have adopted EC/EG in the commercial setting are reliably utilizing EG as a triage test to inform decisions on which patients to refer for further endoscopic evaluation of BE.

Validation of a low-cost model for training laparoscopic ovary-sparing surgery (LOSS) in ovarian mature teratomas

BackgroundMature ovarian teratoma is the most common ovarian neoplasm in pediatrics. Laparoscopic ovary sparing surgery (LOSS) is effective and safe. Due to the expansion of this technique in recent years, education-based surgical simulation is a useful tool for skills development. AimTo validate a low-cost model for training LOSS in pediatric ovarian teratomas. MethodsWe developed a low-cost model, incorporated into Hands-On courses since 2018. After academic lectures, and surgical strategies video demonstration, all participants performed the procedure in pairs, in our pediatric gruyer-like-training-box, under supervision. Time and critical maneuvers were assessed. A Likert-type scale was used to evaluate: previous experience, anatomical appearance of the model, surgical anatomy compared to a real patient and utility as a training method. Statistical analysis was performed with R-Studio®. Results75 % considered the model as good or high degree of similarity in relation to the anatomical characteristics; and 91.3 % in relation to surgical anatomy. 78.8 % believe the model improves the majority of skills. Correlation in time assessment for 81 participants with different levels of experience was statistically significative (p<0.01*). Emphasis was placed on preserving the capsule and ovarian tissue without causing any injury to adjacent tissues, resulting in a homogeneous performance. ConclusionWe saw a correlation between the previous experience of the surgeon and their performance in the model. Introducing this model in a simulation curricula would improve the learning curve. A decrease in surgical technique complications is to be expected, and should be demonstrated in future studies.

Applications of navigation in full-endoscopic spine surgery.

Advancement in all surgery continues to progress towards more minimally invasive surgical (MIS) approaches. One of the platform technologies which has helped drive this trend within spine surgery is the development of endoscopy; however, the limited anatomic view experienced when performing endoscopic spine surgery requires a significant learning curve. The use of intraoperative navigation has been adapted for endoscopic spine surgery, as this provides computer-reconstructed visual data presented in three dimensions, which can increase feasibility of this technique to more surgeons. This paper will describe the principles, technical considerations, and applications of stereotactic navigation-guided endoscopic spine surgery. Full-endoscopic spine surgery has advanced in recent years such that it can be utilized in both decompressive and fusion surgeries. One of the major pitfalls to any minimally invasive surgery (including endoscopic) is that the limited surgical view can often complicate the surgery or confuse the surgeon, leading to longer operative times, higher risks, among others. This is the real utility to using navigation in conjunction with the endoscope-when registered correctly and utilized appropriately, navigated endoscopic spine surgery can take some of the guesswork out of the minimally invasive approach. Using navigation with endoscopy in spine surgery can potentially expand this technique to surgeons who have yet to master endoscopy as the assistance provided by the navigation can alleviate some of the complexities with anatomic understanding and surgical planning.

Weight estimation models for commercial Pinus radiata wood in small felling stands based on UAV-LiDAR data

Uncrewed Aerial Vehicles (UAVs) equipped with Light Detection and Ranging (LiDAR) scanners have been adopted as an effective tool for conducting forest inventories, reducing field work and associated costs. These studies are based on obtaining information on volume, height and diameter at breast height (DBH). However, in the timber sector in Galicia (Spain)the variable used as the unit of purchase/sale is "weight". Therefore, this paper sets out to test different machine learning algorithms, such as multiple linear regression (MLR), MLR log-transformed (MRL-LT), Principal Component Analysis (PCA) and Random Forest (RF) to obtain a methodology applicable in the study area and replicable in other areas, with real utility in the forestry industry for determining the weight of Pinus radiata wood. These models are based on 73 observations and 19 predictors and have been developed and applied to a total of 33 Forest Cuts (FC) divided into 5204 tesserae. The models are validated by Fold Cross-Validation, with RMSE (relative root mean square error), R2 and MAE (mean absolute error) values being calculated. Of the four models studied, the PCA model performs best (R2=0.85, RMSE=1.84, MAE=1.46), followed by the MRL-LT which gives a value of R2=0.82 (RMSE=1.84, MAE=1.46). The actual figure for total Pinus radiata timber harvested was 35,440.54 t The PCA model estimated a total of 35,913.53 t (r = 0.98, R2=0.97, εr=9.35 %), while the MRL-LT model calculated 35,847.92 t (r = 0.99, R2=0.98, εr=8.85 %). On the other hand, the weight was underestimated by the MLR model and overestimated by the RF. The plain MLR model underestimated the "weight" of the wood, while the MRL-LT model provided the best result, with errors of less than 10 % in 72 % of the FCs. In conclusion, this study provides a powerful tool that will enable stakeholders in the community timber industry to accurately estimate the weight of timber in Pinus radiata stands, enhancing a more highly automated forest inventory that can optimise the number of field operations to be performed.