MyMedR

Displaying publications 81 - 100 of 445 in total

Abstract:

Sort:

Similar non-random processes maintain diversity in two tropical rainforests

Wills C, Condit R

Proc Biol Sci, 1999 Jul 22;266(1427):1445-52.
PMID: 10457617

Quadrat-based analysis of two rainforest plots of area 50 ha, one in Panama (Barro Colorado Island, BCI) and the other in Malaysia (Pasoh), shows that in both plots recruitment is in general negatively correlated with both numbers and biomass of adult trees of the same species in the same quadrat. At BCI, this effect is not significantly influenced by treefall gaps. In both plots, recruitment of individual species is negatively correlated with the numbers of trees of all species in the quadrats, but not with overall biomass. These observations suggest, but do not prove, widespread frequency-dependent effects produced by pathogens and seed-predators that act most effectively in quadrats crowded with trees. Within-species correlations of mortality with numbers or biomass are not found in either plot, indicating that most frequency-dependent mortality takes place before the trees reach 1 cm in diameter. Stochastic effects caused by BCI's more rapid tree turnover may contribute to a larger variance in diversity from quadrat to quadrat at BCI, although they are not sufficient to explain why BCI has fewer than half as many tree species as Pasoh. Finally, in both plots quadrats with low diversity show a significant increase in diversity over time, and this increase is stronger at BCI. This process, like the frequency-dependence, will tend to maintain diversity over time. In general, these non-random forces that should lead to the maintenance of diversity are slightly stronger at BCI, even though the BCI plot is less diverse than the Pasoh plot.

Matched MeSH terms: Trees/physiology*
Fulltext Imaging spectroscopy reveals the effects of topography and logging on the leaf chemistry of tropical forest canopy trees

Swinfield T, Both S, Riutta T, Bongalov B, Elias D, Majalap-Lee N, et al.

Glob Chang Biol, 2020 02;26(2):989-1002.
PMID: 31845482 DOI: 10.1111/gcb.14903

Logging, pervasive across the lowland tropics, affects millions of hectares of forest, yet its influence on nutrient cycling remains poorly understood. One hypothesis is that logging influences phosphorus (P) cycling, because this scarce nutrient is removed in extracted timber and eroded soil, leading to shifts in ecosystem functioning and community composition. However, testing this is challenging because P varies within landscapes as a function of geology, topography and climate. Superimposed upon these trends are compositional changes in logged forests, with species with more acquisitive traits, characterized by higher foliar P concentrations, more dominant. It is difficult to resolve these patterns using traditional field approaches alone. Here, we use airborne light detection and ranging-guided hyperspectral imagery to map foliar nutrient (i.e. P, nitrogen [N]) concentrations, calibrated using field measured traits, over 400 km2 of northeastern Borneo, including a landscape-level disturbance gradient spanning old-growth to repeatedly logged forests. The maps reveal that canopy foliar P and N concentrations decrease with elevation. These relationships were not identified using traditional field measurements of leaf and soil nutrients. After controlling for topography, canopy foliar nutrient concentrations were lower in logged forest than in old-growth areas, reflecting decreased nutrient availability. However, foliar nutrient concentrations and specific leaf area were greatest in relatively short patches in logged areas, reflecting a shift in composition to pioneer species with acquisitive traits. N:P ratio increased in logged forest, suggesting reduced soil P availability through disturbance. Through the first landscape scale assessment of how functional leaf traits change in response to logging, we find that differences from old-growth forest become more pronounced as logged forests increase in stature over time, suggesting exacerbated phosphorus limitation as forests recover.

Matched MeSH terms: Trees*
Fulltext Topography shapes the structure, composition and function of tropical forest landscapes

Jucker T, Bongalov B, Burslem DFRP, Nilus R, Dalponte M, Lewis SL, et al.

Ecol Lett, 2018 07;21(7):989-1000.
PMID: 29659115 DOI: 10.1111/ele.12964

Topography is a key driver of tropical forest structure and composition, as it constrains local nutrient and hydraulic conditions within which trees grow. Yet, we do not fully understand how changes in forest physiognomy driven by topography impact other emergent properties of forests, such as their aboveground carbon density (ACD). Working in Borneo - at a site where 70-m-tall forests in alluvial valleys rapidly transition to stunted heath forests on nutrient-depleted dip slopes - we combined field data with airborne laser scanning and hyperspectral imaging to characterise how topography shapes the vertical structure, wood density, diversity and ACD of nearly 15 km2 of old-growth forest. We found that subtle differences in elevation - which control soil chemistry and hydrology - profoundly influenced the structure, composition and diversity of the canopy. Capturing these processes was critical to explaining landscape-scale heterogeneity in ACD, highlighting how emerging remote sensing technologies can provide new insights into long-standing ecological questions.

Matched MeSH terms: Trees
Fulltext Allometric equations for integrating remote sensing imagery into forest monitoring programmes

Jucker T, Caspersen J, Chave J, Antin C, Barbier N, Bongers F, et al.

Glob Chang Biol, 2017 Jan;23(1):177-190.
PMID: 27381364 DOI: 10.1111/gcb.13388

Remote sensing is revolutionizing the way we study forests, and recent technological advances mean we are now able - for the first time - to identify and measure the crown dimensions of individual trees from airborne imagery. Yet to make full use of these data for quantifying forest carbon stocks and dynamics, a new generation of allometric tools which have tree height and crown size at their centre are needed. Here, we compile a global database of 108753 trees for which stem diameter, height and crown diameter have all been measured, including 2395 trees harvested to measure aboveground biomass. Using this database, we develop general allometric models for estimating both the diameter and aboveground biomass of trees from attributes which can be remotely sensed - specifically height and crown diameter. We show that tree height and crown diameter jointly quantify the aboveground biomass of individual trees and find that a single equation predicts stem diameter from these two variables across the world's forests. These new allometric models provide an intuitive way of integrating remote sensing imagery into large-scale forest monitoring programmes and will be of key importance for parameterizing the next generation of dynamic vegetation models.

Matched MeSH terms: Trees
Impacts of selective logging on the oxidative status of tropical understorey birds

Messina S, Edwards DP, AbdElgawad H, Beemster GTS, Tomassi S, Benedick S, et al.

J Anim Ecol, 2020 10;89(10):2222-2234.
PMID: 32535926 DOI: 10.1111/1365-2656.13280

Selective logging is the dominant form of human disturbance in tropical forests, driving changes in the abundance of vertebrate and invertebrate populations relative to undisturbed old-growth forests. A key unresolved question is understanding which physiological mechanisms underlie different responses of species and functional groups to selective logging. Regulation of oxidative status is thought to be one major physiological mechanism underlying the capability of species to cope with environmental changes. Using a correlational cross-sectional approach, we compared a number of oxidative status markers among 15 understorey bird species in unlogged and selectively logged forest in Borneo in relation to their feeding guild. We then tested how variation of markers between forest types was associated with that in population abundance. Birds living in logged forests had a higher activity of the antioxidant enzyme superoxide dismutase and a different regulation of the glutathione cycle compared to conspecific birds in unlogged forest. However, neither oxidative damage nor oxidized glutathione differed between forest types. We also found that omnivores and insectivores differed significantly in all markers related to the key cellular antioxidant glutathione irrespective of the forest type. Species with higher levels of certain antioxidant markers in a given type of forest were less abundant in that forest type compared to the other. Our results suggest that there was little long-term effect of logging (last logging rotation occurred ~15 years prior to the study) on the oxidative status of understorey bird species. However, it is unclear if this was owing to plasticity or evolutionary change. Our correlative results also point to a potential negative association between some antioxidants and population abundance irrespective of the forest type.

Matched MeSH terms: Trees
Lignans from barks of Hernandia nymphaefolia and H. peltata

Rahmani M, Toia RF, Croft KD

Planta Med, 1995 Oct;61(5):487-8.
PMID: 7480216
Matched MeSH terms: Trees/chemistry*
Fulltext Late-spring frost risk between 1959 and 2017 decreased in North America but increased in Europe and Asia

Zohner CM, Mo L, Renner SS, Svenning JC, Vitasse Y, Benito BM, et al.

Proc Natl Acad Sci U S A, 2020 06 02;117(22):12192-12200.
PMID: 32393624 DOI: 10.1073/pnas.1920816117

Late-spring frosts (LSFs) affect the performance of plants and animals across the world's temperate and boreal zones, but despite their ecological and economic impact on agriculture and forestry, the geographic distribution and evolutionary impact of these frost events are poorly understood. Here, we analyze LSFs between 1959 and 2017 and the resistance strategies of Northern Hemisphere woody species to infer trees' adaptations for minimizing frost damage to their leaves and to forecast forest vulnerability under the ongoing changes in frost frequencies. Trait values on leaf-out and leaf-freezing resistance come from up to 1,500 temperate and boreal woody species cultivated in common gardens. We find that areas in which LSFs are common, such as eastern North America, harbor tree species with cautious (late-leafing) leaf-out strategies. Areas in which LSFs used to be unlikely, such as broad-leaved forests and shrublands in Europe and Asia, instead harbor opportunistic tree species (quickly reacting to warming air temperatures). LSFs in the latter regions are currently increasing, and given species' innate resistance strategies, we estimate that ∼35% of the European and ∼26% of the Asian temperate forest area, but only ∼10% of the North American, will experience increasing late-frost damage in the future. Our findings reveal region-specific changes in the spring-frost risk that can inform decision-making in land management, forestry, agriculture, and insurance policy.

Matched MeSH terms: Trees/growth & development*
Malaysia plans 'red book' in its attempts to go green

Cyranoski D

Nature, 2005 Jul 21;436(7049):313.
PMID: 16034382
Matched MeSH terms: Trees/physiology
Swamp row bogs down Singapore's bid to reclaim land

Cyranoski D

Nature, 2003 Dec 11;426(6967):592.
PMID: 14668824
Matched MeSH terms: Trees/physiology
Fulltext A dataset of tree heights in mangrove and non-mangrove trees in Malaysia derived from multiple measurement methods

Saliu IS, Wolswijk G, Satyanarayana B, Fisol MAB, Decannière C, Lucas R, et al.

Data Brief, 2020 Dec;33:106386.
PMID: 33102654 DOI: 10.1016/j.dib.2020.106386

The dataset contains tree height data collected in 200 mangrove and non-mangrove trees sampled in various sites in Malaysia. Different height measurement methods were performed, including visual measurements (stick, thumb rule) and precision field instruments (clinometer, laser rangefinder and altimeter), which were compared against benchmark values obtained using an unmanned aerial vehicle (UAV) and a Leica distometer. The core data have been analysed and interpreted in the paper by Saliu et al. ''An accuracy analysis of mangrove tree height mensuration using forestry techniques, hypsometers and UAVs '' [1], in which the accuracy of each method for tree height measurement was discussed.

Matched MeSH terms: Trees
Fulltext Leaf Anatomy and Micromorphology Characteristics of Ketum [Mitragyna speciosa (Korth.) Havil.] (Rubiaceae)

Ghazalli MN, Md Sah MS, Mat M, Awang K, Jaafar MA, Mirad R, et al.

Trop Life Sci Res, 2021 Mar;32(1):107-117.
PMID: 33936554 DOI: 10.21315/tlsr2021.32.1.7

Mitragyna speciosa (Korth.) Havil. or locally known as ketum/daun sebiak/biak-biak belongs to Rubiaceae family and generally occurs in secondary forest or disturbed areas in tropical and subtropical region. This research enumerated the characterisation of Mitragyna speciosa leaf anatomy and micromorphology features which is still not well documented. This medium to large sized tree species characterised with opposite arrangement, ovate-acuminate leaf and with 12-17 pairs of veins. Transverse sections of petioles showed that this species has petiole outlines with slightly convex at the middle of the adaxial part and 'U'-shaped on abaxial side. Results also showed that this species has paracytic and hypostomatic stomata, combination of non-glandular (majority) and glandular trichomes (minority), with observation on the secretory cells present in petiole and midrib parenchyma cells. Cuticle on the abaxial and adaxial epidermal surfaces showed the presence granule and wax films with periclinal and anticlinal walls can be differentiated clearly. The results obtained in this study can be used to providing additional systematics information of Mitragyna speciosa with the documentation of the leaf anatomy and micromorphology characters.

Matched MeSH terms: Trees
Phylogenetic turnover along local environmental gradients in tropical forest communities

Baldeck CA, Kembel SW, Harms KE, Yavitt JB, John R, Turner BL, et al.

Oecologia, 2016 10;182(2):547-57.
PMID: 27337965 DOI: 10.1007/s00442-016-3686-2

While the importance of local-scale habitat niches in shaping tree species turnover along environmental gradients in tropical forests is well appreciated, relatively little is known about the influence of phylogenetic signal in species' habitat niches in shaping local community structure. We used detailed maps of the soil resource and topographic variation within eight 24-50 ha tropical forest plots combined with species phylogenies created from the APG III phylogeny to examine how phylogenetic beta diversity (indicating the degree of phylogenetic similarity of two communities) was related to environmental gradients within tropical tree communities. Using distance-based redundancy analysis we found that phylogenetic beta diversity, expressed as either nearest neighbor distance or mean pairwise distance, was significantly related to both soil and topographic variation in all study sites. In general, more phylogenetic beta diversity within a forest plot was explained by environmental variables this was expressed as nearest neighbor distance versus mean pairwise distance (3.0-10.3 % and 0.4-8.8 % of variation explained among plots, respectively), and more variation was explained by soil resource variables than topographic variables using either phylogenetic beta diversity metric. We also found that patterns of phylogenetic beta diversity expressed as nearest neighbor distance were consistent with previously observed patterns of niche similarity among congeneric species pairs in these plots. These results indicate the importance of phylogenetic signal in local habitat niches in shaping the phylogenetic structure of tropical tree communities, especially at the level of close phylogenetic neighbors, where similarity in habitat niches is most strongly preserved.

Matched MeSH terms: Trees
Fulltext Rainfall seasonality and pest pressure as determinants of tropical tree species' distributions

Baltzer JL, Davies SJ

Ecol Evol, 2012 Nov;2(11):2682-94.
PMID: 23170205 DOI: 10.1002/ece3.383

Drought and pests are primary abiotic and biotic factors proposed as selective filters acting on species distributions along rainfall gradients in tropical forests and may contribute importantly to species distributional limits, performance, and diversity gradients. Recent research demonstrates linkages between species distributions along rainfall gradients and physiological drought tolerance; corresponding experimental examinations of the contribution of pest pressure to distributional limits and potential interactions between drought and herbivory are limited. This study aims to quantitate differential performance and herbivory as a function of species range limits across a climatic and floristic transition in Southeast Asia. Khao Chong Botanical Garden, Thailand and Pasoh Forest Reserve, Malaysia straddle the Kangar-Pattani Line. A reciprocal transplantation across a seasonality gradient was established using two groups of species ("widespread" taxa whose distributions include seasonally dry forests and "aseasonal" taxa whose distributions are limited to aseasonal forests). Growth, biomass allocation, survival, and herbivory were monitored for 19 months. Systematic differences in performance were a function of species distribution in relation to rainfall seasonality. In aseasonal Pasoh, aseasonal species had both greater growth and survivorship than widespread species. These differences were not a function of differential herbivory as widespread and aseasonal species experienced similar damage in the aseasonal forest. In seasonally dry Khao Chong, widespread species showed higher survivorship than aseasonal species, but these differences were only apparent during drought. We link this differential performance to physiological mechanisms as well as differential tolerance of biotic pressure during drought stress. Systematic decreases in seedling survival in aseasonal taxa during drought corresponded with previously documented physiological differences and may be exacerbated by herbivore damage. These results have important implications for tropical diversity and community composition in light of predicted increases in the frequency and severity of drought in hyperdiverse tropical forests.

Matched MeSH terms: Trees
Fulltext Crown damage and the mortality of tropical trees

Arellano G, Medina NG, Tan S, Mohamad M, Davies SJ

New Phytol, 2019 01;221(1):169-179.
PMID: 30067290 DOI: 10.1111/nph.15381

What causes individual tree death in tropical forests remains a major gap in our understanding of the biology of tropical trees and leads to significant uncertainty in predicting global carbon cycle dynamics. We measured individual characteristics (diameter at breast height, wood density, growth rate, crown illumination and crown form) and environmental conditions (soil fertility and habitat suitability) for 26 425 trees ≥ 10 cm diameter at breast height belonging to 416 species in a 52-ha plot in Lambir Hills National Park, Malaysia. We used structural equation models to investigate the relationships among the different factors and tree mortality. Crown form (a proxy for mechanical damage and other stresses) and prior growth were the two most important factors related to mortality. The effect of all variables on mortality (except habitat suitability) was substantially greater than expected by chance. Tree death is the result of interactions between factors, including direct and indirect effects. Crown form/damage and prior growth mediated most of the effect of tree size, wood density, fertility and habitat suitability on mortality. Large-scale assessment of crown form or status may result in improved prediction of individual tree death at the landscape scale.

Matched MeSH terms: Trees/physiology*
Wildlife disturbances as a source of conspecific negative density-dependent mortality in tropical trees

Luskin MS, Johnson DJ, Ickes K, Yao TL, Davies SJ

Proc Biol Sci, 2021 03 10;288(1946):20210001.
PMID: 33653133 DOI: 10.1098/rspb.2021.0001

Large vertebrates are rarely considered important drivers of conspecific negative density-dependent mortality (CNDD) in plants because they are generalist consumers. However, disturbances like trampling and nesting also cause plant mortality, and their impact on plant diversity depends on the spatial overlap between wildlife habitat preferences and plant species composition. We studied the impact of native wildlife on a hyperdiverse tree community in Malaysia. Pigs (Sus scrofa) are abnormally abundant at the site due to food subsidies in nearby farmland and they construct birthing nests using hundreds of tree saplings. We tagged 34 950 tree saplings in a 25 ha plot during an initial census and assessed the source mortality by recovering tree tags from pig nests (n = 1672 pig-induced deaths). At the stand scale, pigs nested in flat dry habitats, and at the local neighbourhood scale, they nested within clumps of saplings, both of which are intuitive for safe and efficient nest building. At the stand scale, flat dry habitats contained higher sapling densities and higher proportions of common species, so pig nesting increased the weighted average species evenness across habitats. At the neighbourhood scale, pig-induced sapling mortality was associated with higher heterospecific and especially conspecific sapling densities. Tree species have clumped distributions due to dispersal limitation and habitat filtering, so pig disturbances in sapling clumps indirectly caused CNDD. As a result, Pielou species evenness in 400 m2 quadrats increased 105% more in areas with pig-induced deaths than areas without disturbances. Wildlife induced CNDD and this supported tree species evenness, but they also drove a 62% decline in sapling densities from 1996 to 2010, which is unsustainable. We suspect pig nesting is an important feature shaping tree composition throughout the region.

Matched MeSH terms: Trees*
Decelerating growth in tropical forest trees

Feeley KJ, Joseph Wright S, Nur Supardi MN, Kassim AR, Davies SJ

Ecol Lett, 2007 Jun;10(6):461-9.
PMID: 17498145

The impacts of global change on tropical forests remain poorly understood. We examined changes in tree growth rates over the past two decades for all species occurring in large (50-ha) forest dynamics plots in Panama and Malaysia. Stem growth rates declined significantly at both forests regardless of initial size or organizational level (species, community or stand). Decreasing growth rates were widespread, occurring in 24-71% of species at Barro Colorado Island, Panama (BCI) and in 58-95% of species at Pasoh, Malaysia (depending on the sizes of stems included). Changes in growth were not consistently associated with initial growth rate, adult stature, or wood density. Changes in growth were significantly associated with regional climate changes: at both sites growth was negatively correlated with annual mean daily minimum temperatures, and at BCI growth was positively correlated with annual precipitation and number of rainfree days (a measure of relative insolation). While the underlying cause(s) of decelerating growth is still unresolved, these patterns strongly contradict the hypothesized pantropical increase in tree growth rates caused by carbon fertilization. Decelerating tree growth will have important economic and environmental implications.

Matched MeSH terms: Trees/growth & development*
Damage to living trees contributes to almost half of the biomass losses in tropical forests

Zuleta D, Arellano G, McMahon SM, Aguilar S, Bunyavejchewin S, Castaño N, et al.

Glob Chang Biol, 2023 Jun;29(12):3409-3420.
PMID: 36938951 DOI: 10.1111/gcb.16687

Accurate estimates of forest biomass stocks and fluxes are needed to quantify global carbon budgets and assess the response of forests to climate change. However, most forest inventories consider tree mortality as the only aboveground biomass (AGB) loss without accounting for losses via damage to living trees: branchfall, trunk breakage, and wood decay. Here, we use ~151,000 annual records of tree survival and structural completeness to compare AGB loss via damage to living trees to total AGB loss (mortality + damage) in seven tropical forests widely distributed across environmental conditions. We find that 42% (3.62 Mg ha-1 year-1 ; 95% confidence interval [CI] 2.36-5.25) of total AGB loss (8.72 Mg ha-1 year-1 ; CI 5.57-12.86) is due to damage to living trees. Total AGB loss was highly variable among forests, but these differences were mainly caused by site variability in damage-related AGB losses rather than by mortality-related AGB losses. We show that conventional forest inventories overestimate stand-level AGB stocks by 4% (1%-17% range across forests) because assume structurally complete trees, underestimate total AGB loss by 29% (6%-57% range across forests) due to overlooked damage-related AGB losses, and overestimate AGB loss via mortality by 22% (7%-80% range across forests) because of the assumption that trees are undamaged before dying. Our results indicate that forest carbon fluxes are higher than previously thought. Damage on living trees is an underappreciated component of the forest carbon cycle that is likely to become even more important as the frequency and severity of forest disturbances increase.

Matched MeSH terms: Trees*
Fulltext Investments on Pro-poor Development Projects on Goats: Ensuring Success for Improved Livelihoods

Devendra C

Asian-Australas J Anim Sci, 2013 Jan;26(1):1-18.
PMID: 25049700 DOI: 10.5713/ajas.2013.r.01

The elements that determine the success of development projects on goats and the prerequisites for ensuring this are discussed in the context of the bewildering diversity of goat genetic resources, production systems, multifunctionality, and opportunities for responding to constraints for productivity enhancement. Key determinants for the success of pro-poor projects are the imperatives of realistic project design, resolution of priorities and positive impacts to increase investments and spur agricultural growth, and appropriate policy. Throughout the developing world, there exist 97% of the total world population of 921 million goats across all agro-ecological zones (AEZs), including 570 breeds and 64% share of the breeds. They occupy a very important biological and socio-economic niche in farming systems making significant multifunctional contributions especially to food, nutrition and financial security, stability of farm households, and survival of the poor in the rural areas. Definitions are given of successful and failed projects. The analyses highlighted in successful projects the value of strong participatory efforts with farmers and climate change. Climate change effects on goats are inevitable and are mediated through heat stress, type of AEZ, water availability, quantity and quality of the available feed resources and type of production system. Within the prevailing production systems, improved integrated tree crops - ruminant systems are underestimated and are an important pathway to enhance C sequestration. Key development strategies and opportunities for research and development (R and D) are enormous, and include inter alia defining a policy framework, resolution of priority constraints using systems perspectives and community-based participatory activities, application of yield-enhancing technologies, intensification, scaling up, and impacts. The priority for development concerns the rainfed areas with large concentrations of ruminants in which goats, with a capacity to cope with heat tolerance, can be the entry point for development. Networks and networking are very important for the diffusion of information and can add value to R and D. Well formulated projects with clear priority setting and participatory R and D ensure success and the realisation of food security, improved livelihoods and self-reliance in the future.

Matched MeSH terms: Trees
Fulltext Impact of climate change on animal production in Asia: coping with challenges for agricultural R&D

Devendra, C.

ASM Science Journal, 2011;5(2):139-150.
MyJurnal

The effects of anticipated climate change and the potential impact on animal production are discussed in the context of varying biophysical features, agro-ecological zones (AEZs), ecosystems, land use, and responses in animal genetic diversity and production. The AEZs in Asia have great diversity in their links to food production in crop-animal small farm systems, the poverty complex and livelihoods of the poor. In these environments. climate change effects on animals were mediated through heat stress, water availability, quantity and quality of the available feed resources, type of production system and productivity. The responses to heat stress are tabulated and they vary according to species, breeds within-species, AEZs, physiological and nutritional status, genetic potential and multifunctionality. Among ruminant production systems, dairy production was especially vulnerable to heat stress. Interestingly in India, buffalo numbers owned largely by the landless and small farmers in the semi-arid and arid regions have grown twice as fast as the buffalo population in the irrigated areas. The implications and strategies to cope with climate change involve mitigation, adaptation and policy. The principal strategy is targetting to the reduce on in greenhouse gas (GHG) emission from the agricultural sector from enteric fermentation and manure, and ways to intensify C sequestration. An important link is that of breeding and conserving indigenous animal genetic resources as a means to mitigate climate change, with associated benefits to the trade of live animals and animal products. Improved integrated tree crops-ruminant systems are an important pathway to enhance C sequestration. The opportunities for research and development (R&D) are enormous and they would need policy support and large investments to provide improved understanding of ways to ensure sustainable animal production systems. Coping with the totality of the effects and impact of climate change constitutes the challenges for agricultural R&D and the improved livelihood of the resource-poor in the future.

Matched MeSH terms: Trees
Fulltext Predicting factors for survival of breast cancer patients using machine learning techniques

Ganggayah MD, Taib NA, Har YC, Lio P, Dhillon SK

BMC Med Inform Decis Mak, 2019 03 22;19(1):48.
PMID: 30902088 DOI: 10.1186/s12911-019-0801-4

BACKGROUND: Breast cancer is one of the most common diseases in women worldwide. Many studies have been conducted to predict the survival indicators, however most of these analyses were predominantly performed using basic statistical methods. As an alternative, this study used machine learning techniques to build models for detecting and visualising significant prognostic indicators of breast cancer survival rate.
METHODS: A large hospital-based breast cancer dataset retrieved from the University Malaya Medical Centre, Kuala Lumpur, Malaysia (n = 8066) with diagnosis information between 1993 and 2016 was used in this study. The dataset contained 23 predictor variables and one dependent variable, which referred to the survival status of the patients (alive or dead). In determining the significant prognostic factors of breast cancer survival rate, prediction models were built using decision tree, random forest, neural networks, extreme boost, logistic regression, and support vector machine. Next, the dataset was clustered based on the receptor status of breast cancer patients identified via immunohistochemistry to perform advanced modelling using random forest. Subsequently, the important variables were ranked via variable selection methods in random forest. Finally, decision trees were built and validation was performed using survival analysis.
RESULTS: In terms of both model accuracy and calibration measure, all algorithms produced close outcomes, with the lowest obtained from decision tree (accuracy = 79.8%) and the highest from random forest (accuracy = 82.7%). The important variables identified in this study were cancer stage classification, tumour size, number of total axillary lymph nodes removed, number of positive lymph nodes, types of primary treatment, and methods of diagnosis.
CONCLUSION: Interestingly the various machine learning algorithms used in this study yielded close accuracy hence these methods could be used as alternative predictive tools in the breast cancer survival studies, particularly in the Asian region. The important prognostic factors influencing survival rate of breast cancer identified in this study, which were validated by survival curves, are useful and could be translated into decision support tools in the medical domain.

Matched MeSH terms: Decision Trees*

Filters

Please provide feedback to Administrator (afdal@afpm.org.my)

External Links