The current set of research methods on ictresearchmethods.nl contains only one research method that refers to machine learning: the “Data analytics” method in the “Lab” strategy. This does not reflect the way of working in ML projects, where Data Analytics is not a method to answer one question but the main goal of the project. For ML projects, the Data Analytics method should be divided in several smaller steps, each becoming a method of its own. In other words, we should treat the Data Analytics (or more appropriate ML engineering) process in the same way the software engineering process is treated in the framework. In the remainder of this post I will briefly discuss each of the existing research methods and how they apply to ML projects. The methods are organized by strategy. In the discussion I will give pointers to relevant tools or literature for ML projects.
LINK
To accelerate differentiation between Staphylococcus aureus and Coagulase Negative Staphylococci (CNS), this study aimed to compare six different DNA extraction methods from 2 commonly used blood culture materials, i.e. BACTEC and Bact/ALERT. Furthermore, we analyzed the effect of reduced blood culture times for detection of Staphylococci directly from blood culture material. A real-time PCR duplex assay was used to compare 6 different DNA isolation protocols on two different blood culture systems. Negative blood culture material was spiked with MRSA. Bacterial DNA was isolated with: automated extractor EasyMAG (3 protocols), automated extractor MagNA Pure LC (LC Microbiology Kit MGrade), a manual kit MolYsis Plus, and a combination between MolYsis Plus and the EasyMAG. The most optimal isolation method was used to evaluate reduced bacterial culture times. Bacterial DNA isolation with the MolYsis Plus kit in combination with the specific B protocol on the EasyMAG resulted in the most sensitive detection of S.aureus, with a detection limit of 10 CFU/ml, in Bact/ALERT material, whereas using BACTEC resulted in a detection limit of 100 CFU/ml. An initial S.aureus load of 1 CFU/ml blood can be detected after 5 hours of culture in Bact/ALERT3D by combining the sensitive isolation method and the tuf LightCycler assay.
DOCUMENT
Objectives: To cross-validate the existing peak rate of oxygen consumption (VO2peak) prediction equations in Dutch law enforcement officers and to determine whether these prediction equations can be used to predict VO2peak for groups and in a single individual. A further objective was to report normative absolute and relative VO2peak values of a sample of law enforcement officers in the Netherlands. Material and Methods: The peak rate of oxygen consumption (ml×kg–1×min–1) was measured using a maximal incremental bicycle test in 1530 subjects, including 1068 male and 461 female police officers. Validity of the prediction equations for groups was assessed by comparing predicted VO2peak with measured VO2peak using paired t-tests. For individual differences limits of agreement (LoA) were calculated. Equations were considered valid for individuals when the difference between measured and predicted VO2peak did not exceed ±1 metabolic equivalent (MET) in 95% of individuals. Results: None of the equations met the validity criterion of 95% of individuals having ±1 MET difference or less than the measured value. Limits of agreement (LoAs) were large in all predictions. At the individual level, none of the equations were valid predictors of VO2peak (ml×kg–1×min–1). Normative values for Dutch law enforcement officers were presented. Conclusions: Substantial differences between measured and predicted VO2peak (ml×kg–1×min–1) were found. Most tested equations were invalid predictors of VO2peak at group level and all were invalid at individual levels.
DOCUMENT
Recently, the job market for Artificial Intelligence (AI) engineers has exploded. Since the role of AI engineer is relatively new, limited research has been done on the requirements as set by the industry. Moreover, the definition of an AI engineer is less established than for a data scientist or a software engineer. In this study we explore, based on job ads, the requirements from the job market for the position of AI engineer in The Netherlands. We retrieved job ad data between April 2018 and April 2021 from a large job ad database, Jobfeed from TextKernel. The job ads were selected with a process similar to the selection of primary studies in a literature review. We characterize the 367 resulting job ads based on meta-data such as publication date, industry/sector, educational background and job titles. To answer our research questions we have further coded 125 job ads manually. The job tasks of AI engineers are concentrated in five categories: business understanding, data engineering, modeling, software development and operations engineering. Companies ask for AI engineers with different profiles: 1) data science engineer with focus on modeling, 2) AI software engineer with focus on software development , 3) generalist AI engineer with focus on both models and software. Furthermore, we present the tools and technologies mentioned in the selected job ads, and the soft skills. Our research helps to understand the expectations companies have for professionals building AI-enabled systems. Understanding these expectations is crucial both for prospective AI engineers and educational institutions in charge of training those prospective engineers. Our research also helps to better define the profession of AI engineering. We do this by proposing an extended AI engineering life-cycle that includes a business understanding phase.
LINK
In my previous post on AI engineering I defined the concepts involved in this new discipline and explained that with the current state of the practice, AI engineers could also be named machine learning (ML) engineers. In this post I would like to 1) define our view on the profession of applied AI engineer and 2) present the toolbox of an AI engineer with tools, methods and techniques to defy the challenges AI engineers typically face. I end this post with a short overview of related work and future directions. Attached to it is an extensive list of references and additional reading material.
LINK
The past two years I have conducted an extensive literature and tool review to answer the question: “What should software engineers learn about building production-ready machine learning systems?”. During my research I noted that because the discipline of building production-ready machine learning systems is so new, it is not so easy to get the terminology straight. People write about it from different perspectives and backgrounds and have not yet found each other to join forces. At the same time the field is moving fast and far from mature. My focus on material that is ready to be used with our bachelor level students (applied software engineers, profession-oriented education), helped me to consolidate everything I have found into a body of knowledge for building production-ready machine learning (ML) systems. In this post I will first define the discipline and introduce the terminology for AI engineering and MLOps.
LINK
The prevention and diagnosis of frailty syndrome (FS) in cardiac patients requires innovative systems to support medical personnel, patient adherence, and self-care behavior. To do so, modern medicine uses a supervised machine learning approach (ML) to study the psychosocial domains of frailty in cardiac patients with heart failure (HF). This study aimed to determine the absolute and relative diagnostic importance of the individual components of the Tilburg Frailty Indicator (TFI) questionnaire in patients with HF. An exploratory analysis was performed using machine learning algorithms and the permutation method to determine the absolute importance of frailty components in HF. Based on the TFI data, which contain physical and psychosocial components, machine learning models were built based on three algorithms: a decision tree, a random decision forest, and the AdaBoost Models classifier. The absolute weights were used to make pairwise comparisons between the variables and obtain relative diagnostic importance. The analysis of HF patients’ responses showed that the psychological variable TFI20 diagnosing low mood was more diagnostically important than the variables from the physical domain: lack of strength in the hands and physical fatigue. The psychological variable TFI21 linked with agitation and irritability was diagnostically more important than all three physical variables considered: walking difficulties, lack of hand strength, and physical fatigue. In the case of the two remaining variables from the psychological domain (TFI19, TFI22), and for all variables from the social domain, the results do not allow for the rejection of the null hypothesis. From a long-term perspective, the ML based frailty approach can support healthcare professionals, including psychologists and social workers, in drawing their attention to the nonphysical origins of HF.
DOCUMENT
Background: Although physical activity (PA) has positive effects on health and well-being, physical inactivity is a worldwide problem. Mobile health interventions have been shown to be effective in promoting PA. Personalizing persuasive strategies improves intervention success and can be conducted using machine learning (ML). For PA, several studies have addressed personalized persuasive strategies without ML, whereas others have included personalization using ML without focusing on persuasive strategies. An overview of studies discussing ML to personalize persuasive strategies in PA-promoting interventions and corresponding categorizations could be helpful for such interventions to be designed in the future but is still missing. Objective: First, we aimed to provide an overview of implemented ML techniques to personalize persuasive strategies in mobile health interventions promoting PA. Moreover, we aimed to present a categorization overview as a starting point for applying ML techniques in this field. Methods: A scoping review was conducted based on the framework by Arksey and O’Malley and the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) criteria. Scopus, Web of Science, and PubMed were searched for studies that included ML to personalize persuasive strategies in interventions promoting PA. Papers were screened using the ASReview software. From the included papers, categorized by the research project they belonged to, we extracted data regarding general study information, target group, PA intervention, implemented technology, and study details. On the basis of the analysis of these data, a categorization overview was given. Results: In total, 40 papers belonging to 27 different projects were included. These papers could be categorized in 4 groups based on their dimension of personalization. Then, for each dimension, 1 or 2 persuasive strategy categories were found together with a type of ML. The overview resulted in a categorization consisting of 3 levels: dimension of personalization, persuasive strategy, and type of ML. When personalizing the timing of the messages, most projects implemented reinforcement learning to personalize the timing of reminders and supervised learning (SL) to personalize the timing of feedback, monitoring, and goal-setting messages. Regarding the content of the messages, most projects implemented SL to personalize PA suggestions and feedback or educational messages. For personalizing PA suggestions, SL can be implemented either alone or combined with a recommender system. Finally, reinforcement learning was mostly used to personalize the type of feedback messages. Conclusions: The overview of all implemented persuasive strategies and their corresponding ML methods is insightful for this interdisciplinary field. Moreover, it led to a categorization overview that provides insights into the design and development of personalized persuasive strategies to promote PA. In future papers, the categorization overview might be expanded with additional layers to specify ML methods or additional dimensions of personalization and persuasive strategies.
DOCUMENT
Background: To avoid overexertion in critically ill patients, information on the physical demand, i.e., metabolic load, of daily care and active exercises is warranted. Objective: The objective of this study was toassess the metabolic load during morning care activities and active bed exercises in mechanically ventilated critically ill patients. Methods: This study incorporated an explorative observational study executed in a university hospital intensive care unit. Oxygen consumption (VO2) was measured in mechanically ventilated (≥48 h) critically ill patients during rest, routine morning care, and active bed exercises. We aimed to describe and compare VO2 in terms of absolute VO2 (mL) defined as the VO2 attributable to the activity and relative VO2 in mL per kilogram bodyweight, per minute (mL/kg/min). Additional outcomes achieved during the activity were perceived exertion, respiratory variables, and the highest VO2 values. Changes in VO2 and activity duration were tested using paired tests. Results: Twenty-one patients were included with a mean (standard deviation) age of 59 y (12). Median (interquartile range [IQR]) durations of morning care and active bed exercises were 26 min (21–29) and 7 min (5–12), respectively. Absolute VO2 of morning care was significantly higher than that of active bed exercises (p = 0,009). Median (IQR) relative VO2 was 2.9 (2.6–3.8) mL/kg/min during rest; 3.1 (2.8–3.7) mL/kg/min during morning care; and 3.2 (2.7–4) mL/kg/min during active bed exercises. The highest VO2 value was 4.9 (4.2–5.7) mL/kg/min during morning care and 3.7 (3.2–5.3) mL/kg/min during active bed exercises. Median (IQR) perceived exertion on the 6–20 Borg scale was 12 (10.3–14.5) during morning care (n = 8) and 13.5 (11–15) during active bed exercises (n = 6). Conclusion: Absolute VO2 in mechanically ventilated patients may be higher during morning care than during active bed exercises due to the longer duration of the activity. Intensive care unit clinicians should be aware that daily-care activities may cause intervals of high metabolic load and high ratings of perceived exertion.
DOCUMENT
An ELISA was set up using polyvinylchloride microtiter plates coated with rabbit anti-UK IgG's and affino-purified goat anti-UK IgG's as second antibody. Detection occurred with rabbit anti-goat IgG antibodies conjugated with alkaline phosphatase. The assay is specific for urokinase (UK) with a detection limit of 100 pg/ml sample. Tissue-type plasminogen activator, up to concentrations of 100 ng/ml, does not interfere. The assay measures the antigen of the inactive zymogen pro-UK, the active enzyme UK and the UK-inhibitor complex with equal efficiency and gives the total UK antigen present, irrespective of its molecular form. Culture media of fibroblasts, endothelial- and kidney cells showed, despite the absence of active UK, antigen levels of 1.2, 23 and 65 ng/ml, respectively. In human plasma the UK concentration was found to be 3.5 +/- 1.4 ng/ml (mean +/- SD, n = 54). The inter- and intra-assay variations were 20% and 6%, respectively.
DOCUMENT
