scholarly journals Values and inductive risk in machine learning modelling: the case of binary classification models

2021 ◽  
Vol 11 (4) ◽  
Author(s):  
Koray Karaca
Keyword(s):  
Machine Learning ◽  
Social Values ◽  
Binary Classification ◽  
Social Value ◽  
Classification Models ◽  
Value Judgments ◽  
Philosophical Debate ◽  
Inductive Risk ◽  
The Social ◽  
Error Costs

AbstractI examine the construction and evaluation of machine learning (ML) binary classification models. These models are increasingly used for societal applications such as classifying patients into two categories according to the presence or absence of a certain disease like cancer and heart disease. I argue that the construction of ML (binary) classification models involves an optimisation process aiming at the minimization of the inductive risk associated with the intended uses of these models. I also argue that the construction of these models is underdetermined by the available data, and that this makes it necessary for ML modellers to make social value judgments in determining the error costs (associated with misclassifications) used in ML optimization. I thus suggest that the assessment of the inductive risk with respect to the social values of the intended users is an integral part of the construction and evaluation of ML classification models. I also discuss the implications of this conclusion for the philosophical debate concerning inductive risk.

scholarly journals Machine-Learning-Based Radiomics MRI Model for Survival Prediction of Recurrent Glioblastomas Treated with Bevacizumab

Diagnostics ◽  
2021 ◽  
Vol 11 (7) ◽  
pp. 1263
Author(s):  
Samy Ammari ◽  
Raoul Sallé de Chou ◽  
Tarek Assi ◽  
Mehdi Touat ◽  
Emilie Chouzenoux ◽  
...  
Keyword(s):  
Machine Learning ◽  
Therapeutic Option ◽  
Binary Classification ◽  
Progression Free Survival ◽  
Recurrent Glioblastoma ◽  
Machine Learning Algorithms ◽  
Survival Prediction ◽  
Classification Models ◽  
Angiogenic Therapy ◽  
Recurrent Gbm

Anti-angiogenic therapy with bevacizumab is a widely used therapeutic option for recurrent glioblastoma (GBM). Nevertheless, the therapeutic response remains highly heterogeneous among GBM patients with discordant outcomes. Recent data have shown that radiomics, an advanced recent imaging analysis method, can help to predict both prognosis and therapy in a multitude of solid tumours. The objective of this study was to identify novel biomarkers, extracted from MRI and clinical data, which could predict overall survival (OS) and progression-free survival (PFS) in GBM patients treated with bevacizumab using machine-learning algorithms. In a cohort of 194 recurrent GBM patients (age range 18–80), radiomics data from pre-treatment T2 FLAIR and gadolinium-injected MRI images along with clinical features were analysed. Binary classification models for OS at 9, 12, and 15 months were evaluated. Our classification models successfully stratified the OS. The AUCs were equal to 0.78, 0.85, and 0.76 on the test sets (0.79, 0.82, and 0.87 on the training sets) for the 9-, 12-, and 15-month endpoints, respectively. Regressions yielded a C-index of 0.64 (0.74) for OS and 0.57 (0.69) for PFS. These results suggest that radiomics could assist in the elaboration of a predictive model for treatment selection in recurrent GBM patients.

EVIDENCE, VALUES, AND DECISION MAKING

2014 ◽  
Vol 30 (2) ◽  
pp. 233-238 ◽  
Author(s):  
Michael D. Rawlins
Keyword(s):  
Decision Making ◽  
Cost Effectiveness ◽  
Observational Study ◽  
Social Values ◽  
Clinical Excellence ◽  
Health Technology ◽  
Evidence Base ◽  
Social Value ◽  
Value Judgments ◽  
Study Designs

Background: The evidence supporting the use of new, or established, interventions may be derived from either (or both) experimental or observational study designs. Although a rigorous examination of the evidence base for clinical and cost-effectiveness is essential, it is never sufficient, and those undertaking a health technology assessment (HTA) also have to exercise judgments.Methods: The basis for this discussion is largely from the author's experience as chairman of the national Institute for Health and Clinical Excellence (NICE).Results: The judgments necessary for HTA to make are twofold. Scientific judgments relate to the interpretation of the science. Social value judgments are concerned with the ethical principles, preferences, culture, and aspirations of society.Conclusions: How scientific and social value judgments might be most appropriately captured is a challenge for all HTA agencies. Although competent HTA bodies should be able to exercise scientific judgments they have no legitimacy to impose their own social values. These must ultimately be informed by the general public.

scholarly journals Social Values Reflected in "Batu Dara Muning" An Oral Literature of Dayak Keninjal Tribe

2018 ◽  
Vol 3 (1) ◽  
pp. 34
Author(s):  
Martono Martono
Keyword(s):  
Cultural Heritage ◽  
Character Education ◽  
Social Values ◽  
Social Value ◽  
Local Culture ◽  
Oral Literature ◽  
Sociology Of Literature ◽  
The People ◽  
The Social

Oral literature has an important function in life because it can reflect people's lives and instil a sense of love for their own culture. Oral literature is a cultural heritage of the region passed down from generation to generation which is narrated from mouth to mouth and has a noble value. The noble value contained in oral literature reflects the local culture of the tribe. Certain noble values must be continuously preserved and implemented in the life of society and state. The noble value as a form of character education, such as social values. Therefore, positive social values must be maintained. The social values as many ancestral riches are also found in Dayak Keninjal oral literature titled Batu Dara Muning. The social value that can be found in oral literature entitled Batu Dara Muning is the value of a mother's love for a child, obedient to parents, forbidden marriage, obedience to customs. To analyze oral literature Batu Dara Muning used an approach of a sociology of literature. The reason literature is a mirror of the lives of the people who own the story. Stories or events expressed in oral literature are sourced from events in society with the narrator's imagination. The character used in oral literature is not the name of the character in his tribe, but the name made by the narrator.

scholarly journals Social values influence the adequacy conditions of scientific theories: beyond inductive risk

2015 ◽  
Vol 45 (3) ◽  
pp. 326-356 ◽  
Author(s):  
Ingo Brigandt
Keyword(s):  
Human Evolution ◽  
Scientific Explanation ◽  
Social Values ◽  
Social Consequences ◽  
Epistemic Values ◽  
Inductive Risk ◽  
The Social ◽  
Philosophical Framework ◽  
Theory Acceptance ◽  
The Impact

The ‘death of evidence’ issue in Canada raises the spectre of politicized science, and thus the question of what role social values may have in science and how this meshes with objectivity and evidence. I first criticize philosophical accounts that have to separate different steps of research to restrict the influence of social and other non-epistemic values. A prominent account that social values may play a role even in the context of theory acceptance is the argument from inductive risk. It maintains that the more severe the social consequences of erroneously accepting a theory would be, the more evidence is needed before the theory may be accepted. However, an implication of this position is that increasing evidence makes the impact of social values converge to zero; and I argue for a stronger role for social values. On this position, social values (together with epistemic values and other empirical considerations) may determine a theory's conditions of adequacy, which among other things can include considerations about what makes a scientific account unbiased and complete. I illustrate this based on recent theories of human evolution and the social behaviour of non-human primates, where some of the social values implicated are feminist values. While many philosophical accounts (both arguments from inductive risk and from underdetermination) conceptualize the relevance of social values in terms of making inferences from evidence, I argue for the need for a broader philosophical framework, which is also motivated by issues pertaining to scientific explanation.

Toward Valuing With Critical Systems Heuristics

2017 ◽  
Vol 39 (2) ◽  
pp. 201-220 ◽  
Author(s):  
Emily F. Gates
Keyword(s):  
Systems Thinking ◽  
Social Value ◽  
Critical Systems ◽  
Practical Application ◽  
Value Judgments ◽  
Critical Systems Heuristics ◽  
Evaluation Practice ◽  
Clear Cut ◽  
Central Task ◽  
The Social

Evaluation is defined by its central task of valuing—the process and product of judging the merit, worth, or significance of a policy or program. However, there are no clear-cut ways to consider values and render value judgments in evaluation practice. There remains contention in the evaluation field about whether and how to make value judgments. No approach to valuing eliminates the uncertainty, plurality, and potential for conflict that comes with considering values. This article explores what critical systems heuristics (CSH), an area of applied systems thinking, might contribute to four long-standing issues regarding valuing: envisioning the social value of evaluation, framing the evaluand and evaluation, selecting and justifying criteria, and determining the roles of the evaluator(s) and stakeholders in valuing. CSH contributes concepts and tools that, in theory, support more reflective, responsible valuing although further practical application is needed.

scholarly journals Predicting pulmonary function from the analysis of voice: a machine learning approach

2021 ◽  
Author(s):  
Md. Zahangir Alam ◽  
Albino Simonetti ◽  
Rafaelle Billantino ◽  
Nick Tayler ◽  
Chris Grainge ◽  
...  
Keyword(s):  
Machine Learning ◽  
Lung Function ◽  
Predictive Models ◽  
Binary Classification ◽  
Support Vector ◽  
Learning Approach ◽  
Classification Models ◽  
Special Equipment ◽  
Self Monitoring ◽  
Machine Learning Approach

Providing proper timely treatment of asthma, self-monitoring can play a vital role in disease control. Existing methods (such as peak flow meter, smart spirometer) requires special equipment and are not always used by the patient. Using voice recording as surrogate measures of lung function can be used to assess asthma, which has good potential to self-monitor asthma and could be integrated into telehealth platforms. This study aims to apply machine learning approach to predict lung functions from recorded voice for asthma patients. A threshold-based mechanism was designed to separate speech and breathing from recordings (323 recordings from 26 participants) and features extracted from these were combined with biological attributes and lung function (percentage predicted forced expiratory volume in 1 second, FEV1%). Three predictive models were developed: (a) regression models to predict lung function, (b) multi-class classification models to predict the severity, and (c) binary classification models to predict abnormality. Random Forest (RF), Support Vector Machine (SVM), and Linear Regression (LR) algorithms were implemented to develop these predictive models. Training and test samples were separated (70%:30% using balanced portioning). Features were normalised and 10-fold cross-validation used to measure the model's training performances on the training samples. Models were then run on the test samples to measure the final performances. The RF based regression model performed better with lowest root mean square error = 10.86, and mean absolute score = 11.47, as compared to other models. In predicting the severity of lung function, the SVM based model performed better with 73.20% accuracy. The RF based model performed better in binary classification models for predicting abnormality of lung function (accuracy = 0.85, F1-score = 0.84, and area under the receiver operating characteristic curve = 0.88). The proposed machine learning approach can predict lung function (in terms of FEV1%), from the recorded voice files, better than other published approaches. These models can be extended to predict both the severity and abnormality of lung function with reasonable accuracies. This technique could be used to develop future telehealth solutions including smartphone-based applications which have potential to aid decision making and self-monitoring in asthma.

scholarly journals Towards an Explanation of the Social Value of Health Systems: An Interpretive Synthesis

2020 ◽  
Author(s):  
Eleanor Beth Whyle ◽  
Jill Olivier
Keyword(s):  
Health Systems ◽  
Social Values ◽  
Social Systems ◽  
The State ◽  
Social Value ◽  
Explanatory Theory ◽  
Systems Research ◽  
The Social ◽  
The Relationship ◽  
Value Of Health

Background: Health systems are complex social systems, and values constitute a central dimension of their complexity. Values are commonly understood as key drivers of health system change, operating across all health systems components and functions. Moreover, health systems are understood to influence and generate social values, presenting an opportunity to harness health systems to build stronger, more cohesive societies. However, there is little investigation (theoretical, conceptual, or empirical) on social values in health policy and systems research (HPSR), particularly regarding the capacity of health systems to influence and generate social values. This study develops an explanatory theory for the ‘social value of health systems.’ Methods: We present the results of an interpretive synthesis of HPSR literature on social values, drawing on a qualitative systematic review, focusing on claims about the relationship between ‘health systems’ and ‘social values.’ We combined relational claims extracted from the literature under a common framework in order to generate new explanatory theory. Results: We identify four mechanisms by which health systems are considered to contribute social value to society: Health systems can: (1) offer a unifying national ideal and build social cohesion, (2) influence and legitimise popular attitudes about rights and entitlements with regard to healthcare and inform citizen’s understanding of state responsibilities, (3) strengthen trust in the state and legitimise state authority, and (4) communicate the extent to which the state values various population groups. Conclusion: We conclude that, using a systems-thinking and complex adaptive systems perspective, the above mechanisms can be explained as emergent properties of the dynamic network of values-based connections operating within health systems. We also demonstrate that this theory accounts for how HPSR authors write about the relationship between health systems and social values. Finally, we offer lessons for researchers and policy-makers seeking to bring about values-based change in health systems.

scholarly journals SOCIAL VALUES IN ANANTA TOER’S NOVEL BUMI MANUSIA

2020 ◽  
Vol 3 (1) ◽  
pp. 1-6
Author(s):  
Feny Aisyah ◽  
M. Manugeren ◽  
Purwarno Purwarno
Keyword(s):  
Cultural Revolution ◽  
Research Finding ◽  
Qualitative Method ◽  
Social Values ◽  
Social Value ◽  
The Novel ◽  
Moral Value ◽  
Aesthetic Value ◽  
Analysis Technique ◽  
The Social

This research focused on the types of social values reflected in Ananta Toer’s novel entitled Bumi Manusia. This novel successfully describes not only the cultural revolution in a colonized country but also an objection against the absolute supremacy of cultural and social values. The research was aimed at revealing the kinds of social values in the novel. The data were in the forms of sentences, paragraphs and dialogues referring to social values such as positive and negative social values. The method used in this research is descriptive qualitative method with content analysis technique that is by analyzing the letters, words, sentences and verses that can explain some social values in this novel. Based on the research finding and discussion, as well as the theory of social values proposed by Notonegoro (2014), the social values are divided into Value of truth, Aesthetic value, Moral value and Religious value. The results show that there are four types of social value in the novel, i.e. Value of truth (Justice), Aesthetic value (love), Moral value (encouraging kinship and politeness) and Religious value (patience and faith).

scholarly journals METODE PENANAMAN NILAI SOSIAL PADA SANTRI DI PONDOK PESANTREN SALAFIYAH DAN IMPLEMENTASINYA DALAM KEGIATAN MASYARAKAT PULUTAN LOR RW 02 KECAMATAN SIDOREJO KOTA SALATIGA TAHUN 2018

2018 ◽  
Vol 13 (2) ◽  
pp. 1
Author(s):  
Jamasri Jamasri ◽  
Yosaphat Haris Nusarastriya
Keyword(s):  
Social Values ◽  
Boarding School ◽  
Social Value ◽  
Research Subjects ◽  
Mutual Cooperation ◽  
Community Activities ◽  
Study Committee ◽  
The Social ◽  
Qualitative Descriptive ◽  
Method Of Planting

<p><em>This study is titled the method of planting social value in santri at the Salafiyah Islamic Boarding School RW 02, Sidorejo sub-district, Salatiga city in 2018. This type of research is a qualitative descriptive study with 45 research subjects as kyai and santri. Data was collected by observation, interviews, documentation, and questionnaires. Data analysis using qualitative descriptive techniques. The results showed that the method of planting social values used was the Sorogan and Bandongan methods. The embedded social values include discipline, empathy, respect, caring, and tolerance. The implementation of the social values of santri in community activities is to become a TPA worker, a large study committee and mutual cooperation.</em></p><p> </p><p><strong><em>Keywords:</em></strong><strong>  </strong><em>social values, santri, islamic boarding schools, community activities</em></p>

scholarly journals Social Values Perceptions of Fourth Grade Primary School Students

2017 ◽  
Vol 13 (19) ◽  
pp. 88
Author(s):  
Hakan Cetin ◽  
Ozlem Kaf
Keyword(s):  
Social Values ◽  
Fourth Grade ◽  
Education Level ◽  
Social Value ◽  
Primary School Students ◽  
School Students ◽  
Value Perceptions ◽  
The Social ◽  
Significant Difference ◽  
Fourth Grade Students

This study was conducted with the aim of determining the perceptions of social values of fourth grade primary school students. The research is a descriptive study based on survey model. The study sample group is composed of 451 fourth grade students studying in four different schools in Siirt city center selected via convenience sampling method. The Perception Scale for Social Values developed by Bakaç (2013) was used as data collection instrument. There are a total of 23 five-point likert-type items on The Perception Scale for Social Values, of which 19 items are designed to measure positive perceptions and 4 items are designed to measure negative perceptions. Cronbach-Alpha reliability coefficients of the scale are .88 for the first sub-scale, .72 for the second sub- scale and .86 for the total scale. Descriptive statistics, Mann-Whitney U-Test and Kruskal Wallis methods were used for data analysis. The findings of the study indicate that the social value perceptions of fourth grade students show no significant difference with regard to gender or education level of mother. Whereas it was concluded that the social value perceptions of fourth grade students show a significant difference with regard to place of residence and education level of father

Sign in / Sign up

Export Citation Format

Share Document