AI-Assisted Decision-Making in Long-Term Care: Qualitative Study on Prerequisites for Responsible Innovation.

BACKGROUND: Although the use of artificial intelligence (AI)-based technologies, such as AI-based decision support systems (AI-DSSs), can help sustain and improve the quality and efficiency of care, their deployment creates ethical and social challenges. In recent years, a growing prevalence of high-level guidelines and frameworks for responsible AI innovation has been observed. However, few studies have specified the responsible embedding of AI-based technologies, such as AI-DSSs, in specific contexts, such as the nursing process in long-term care (LTC) for older adults. OBJECTIVE: Prerequisites for responsible AI-assisted decision-making in nursing practice were explored from the perspectives of nurses and other professional stakeholders in LTC. METHODS: Semistructured interviews were conducted with 24 care professionals in Dutch LTC, including nurses, care coordinators, data specialists, and care centralists. A total of 2 imaginary scenarios about AI-DSSs were developed beforehand and used to enable participants articulate their expectations regarding the opportunities and risks of AI-assisted decision-making. In addition, 6 high-level principles for responsible AI were used as probing themes to evoke further consideration of the risks associated with using AI-DSSs in LTC. Furthermore, the participants were asked to brainstorm possible strategies and actions in the design, implementation, and use of AI-DSSs to address or mitigate these risks. A thematic analysis was performed to identify the opportunities and risks of AI-assisted decision-making in nursing practice and the associated prerequisites for responsible innovation in this area. RESULTS: The stance of care professionals on the use of AI-DSSs is not a matter of purely positive or negative expectations but rather a nuanced interplay of positive and negative elements that lead to a weighed perception of the prerequisites for responsible AI-assisted decision-making. Both opportunities and risks were identified in relation to the early identification of care needs, guidance in devising care strategies, shared decision-making, and the workload of and work experience of caregivers. To optimally balance the opportunities and risks of AI-assisted decision-making, seven categories of prerequisites for responsible AI-assisted decision-making in nursing practice were identified: (1) regular deliberation on data collection; (2) a balanced proactive nature of AI-DSSs; (3) incremental advancements aligned with trust and experience; (4) customization for all user groups, including clients and caregivers; (5) measures to counteract bias and narrow perspectives; (6) human-centric learning loops; and (7) the routinization of using AI-DSSs. CONCLUSIONS: The opportunities of AI-assisted decision-making in nursing practice could turn into drawbacks depending on the specific shaping of the design and deployment of AI-DSSs. Therefore, we recommend considering the responsible use of AI-DSSs as a balancing act. Moreover, considering the interrelatedness of the identified prerequisites, we call for various actors, including developers and users of AI-DSSs, to cohesively address the different factors important to the responsible embedding of AI-DSSs in practice.

The evaluation of a decision support system integrating assistive technology for people with dementia at home.

Introduction: With a decreasing workforce of carers and a transition from care homes to home care, people with dementia (PwD) increasingly rely on informal caregivers (ICs) and assistive technologies (ATs). There is growing evidence that ATs in the home environment can reduce workload for formal carers (FCs) and ICs, reduce care costs, and can have a positive influence on quality of life (QoL) for PwD and their caregivers. In practice, using multiple ATs still often implies using different separate point solutions and applications. However, the integral, combined use of the data generated using various applications can potentially enhance the insight into the health and wellbeing status of PwD and can provide decision support for carers. The purpose of the current study was to evaluate the use of a DSS that integrated multiple ATs into one dashboard through a small-scale field study. Methods: The current study presents the formative evaluation of a Decision Support System (DSS) connected to multiple ATs. This DSS has been developed by means of co-creation during an international project. The DSS provides an insight into the physical and cognitive status of a PwD, as well as an insight into sleep activity and general wellbeing. Semi-structured interview sessions were held in three countries (Netherlands, Italy, and Taiwan) with 41 participants to gain insight into the experiences of formal and informal carers and PwD with both the ATs and the DSS Alpha prototype dashboard. Results: The results showed that participants using the DSS were satisfied and perceived added value and a fit with certain care demands from the PwD. In general, ICs and FCs have limited insight into the status of PwD living independently at home, and in these moments, the DSS dashboard and AT bundle can provide valuable insights. Participants experienced the DSS dashboard as well-organized and easy to navigate. The accuracy of the data displayed in the dashboard is important, the context, and (perceived) privacy issues should be tackled according to all users. Furthermore, based in the insight gained during the evaluation a set of design improvements was composed which can be used to further improve the DSS for the Beta evaluation. Discussion and conclusion: The current paper evaluates a possible solution for excess AT usage and how the use of a DSS which integrated multiple AT into one single technology could support caregivers in providing care for PwD. The formative evaluation scrutinized the integration of the developed DSS and the composed bundle of ATs across diverse cultural contexts. Insights from multi-center observations shed light on user experiences, encompassing overall usability, navigational efficacy, and attitudes toward the system. FCs and ICs expressed positivity toward the DSS dashboard's design and functionalities, highlighting its utility in remote monitoring, tracking changes in the person's abilities, and managing urgent situations. There is a need for personalized solutions and the findings contribute to a nuanced understanding of DSS and AT integration, providing insights for future developments and research in the field of DSS for the care of PwD.

Making Co-Design More Responsible: Case Study on the Development of an AI-Based Decision Support System in Dementia Care.

BACKGROUND: Emerging technologies such as artificial intelligence (AI) require an early-stage assessment of potential societal and ethical implications to increase their acceptability, desirability, and sustainability. This paper explores and compares 2 of these assessment approaches: the responsible innovation (RI) framework originating from technology studies and the co-design approach originating from design studies. While the RI framework has been introduced to guide early-stage technology assessment through anticipation, inclusion, reflexivity, and responsiveness, co-design is a commonly accepted approach in the development of technologies to support the care for older adults with frailty. However, there is limited understanding about how co-design contributes to the anticipation of implications. OBJECTIVE: This paper empirically explores how the co-design process of an AI-based decision support system (DSS) for dementia caregivers is complemented by explicit anticipation of implications. METHODS: This case study investigated an international collaborative project that focused on the co-design, development, testing, and commercialization of a DSS that is intended to provide actionable information to formal caregivers of people with dementia. In parallel to the co-design process, an RI exploration took place, which involved examining project members' viewpoints on both positive and negative implications of using the DSS, along with strategies to address these implications. Results from the co-design process and RI exploration were analyzed and compared. In addition, retrospective interviews were held with project members to reflect on the co-design process and RI exploration. RESULTS: Our results indicate that, when involved in exploring requirements for the DSS, co-design participants naturally raised various implications and conditions for responsible design and deployment: protecting privacy, preventing cognitive overload, providing transparency, empowering caregivers to be in control, safeguarding accuracy, and training users. However, when comparing the co-design results with insights from the RI exploration, we found limitations to the co-design results, for instance, regarding the specification, interrelatedness, and context dependency of implications and strategies to address implications. CONCLUSIONS: This case study shows that a co-design process that focuses on opportunities for innovation rather than balancing attention for both positive and negative implications may result in knowledge gaps related to social and ethical implications and how they can be addressed. In the pursuit of responsible outcomes, co-design facilitators could broaden their scope and reconsider the specific implementation of the process-oriented RI principles of anticipation and inclusion.

Sensory, Affective, and Social Experiences with Haptic Devices in Intramural Care Practice.

Previous work has shown that technology can facilitate the communication of emotions, social touch, and social presence through haptic devices, meaning devices that provide a haptic stimulation. However, for special user groups living in long-term care facilities, such as people with dementia, the applications of these haptic devices are not apparent. The aim of this study is to understand how haptic devices can be used in intramural care facilities in times of social isolation, focusing on haptic devices that utilize haptic sensation. Five haptic devices were tested at three care facilities. Insights from this study highlight the potential of haptic devices to enhance sensory, affective, and social experiences during video calling between residents and their relatives. Moreover, the importance of the tactile sensation and form factor of haptic devices in the care context is addressed, along with insights on how to create the appropriate atmosphere during video calling.

Production of eco friendly DME fuel over sonochemically synthesized UiO66 catalyst.

The ultrasound-assisted preparation of UiO-66 was carried out at T = 80-220 °C, and the catalytic performances were evaluated in methanol conversion. Also, physicochemical properties were assessed by XRD, SEM, PSD, FTIR, N2 adsorption-desorption, TG-DTG, and NH3-TPD analysis. The characterization proved that increasing the synthesis temperature positively affected the crystallinity, specific surface area, thermal stability, and acidity of the catalysts. Besides, the catalysts' performance was investigated in the methanol conversion reaction (T = 350-450 °C, P = 1 atm, and WHSV = 5 h-1), leading to the DME (Dimethyl Ether) production. Rising reaction temperature increased the methanol conversion and DME yield. The synthesized sample at 220 °C had the best properties and performance with conversion and yield of about 38% and 51%, respectively. The stability test for the UiO-66-220 (University of Oslo 66) catalyst was performed at 450 °C for 12 h, and the activity remained stable for about 5 h. Furthermore, the used catalyst was characterized via XRD and TG analysis.

Facile synthesis of hierarchically structured MIL-53(Al) with superior properties using an environmentally-friendly ultrasonic method for separating lead ions from aqueous solutions.

The present study aims at investigating sonochemically synthesized MIL-53(Al) and its applications in adsorption lead ions from aqueous solution. XRD, FESEM, BET, and FTIR analyses were employed to identify and characterize MIL-53(Al). The ultrasonic-assisted synthesis procedure results in reducing the synthesis time to 24 h; however, the conventional synthesis of MIL-53(Al) takes 3 days. Applying ultrasonic waves also leads to increase of the specific surface area up to 50% more than that of synthesized by the conventional method, as well as creating the hierarchical MIL-53(Al) structure which reduces the mass transfer limitation of ions into internal micropores. The optimum conditions for removing lead ions are pH of 6, Pb+2 ion concentration of 20 mg/L, contact time of 60 min, adsorbent dose of 0.04 g, and temperature of 318 K with the removal efficiency of 97.63%. The experimental adsorption equilibrium and kinetic data fit the Langmuir isotherm and pseudo-second-order kinetic models, respectively. Moreover, the usage of sonochemically synthesized MIL-53(Al), for the first time as an adsorbent in heavy metal removal points to the great potential of this new environmentally-friendly adsorbent in removing lead ions from aqueous solutions.

Different view of solvent effect on the synthesis methods of zeolitic imidazolate framework-8 to tuning the crystal structure and properties.

One of the important aims in the synthesis of zeolite imidazolate framework-8 is to prepare crystals with predictable structures and valuable properties. It is observed that the properties of ZIF-8 have been directly or indirectly determined by various synthetic factors. Among many synthetic factors, solvents and synthesis methods are unavoidable parameters that control the overall structure of ZIF-8. This article presents a deep understanding of how solvents play their role in the crystallization and structure and therefore the properties of ZIF-8 by considering the polarity, viscosity, interfacial tension and molecular structure and comparing the behaviour of each solvent in every synthesis method. Also, to clearly realize their effect on the formation and final properties of ZIF-8, the crystallization process and mass transfer are discussed.

Catalytic Longevity of Hierarchical SAPO-34/AlMCM-41 Nanocomposite Molecular Sieve In Methanol-to-Olefins Process.

INTRODUCTION: SAPO-34/AlMCM-41, as a hierarchical nanocomposite molecular sieve was prepared by sequential hydrothermal and dry-gel methods studied for catalytic conversion of methanol to light olefins. Pure AlMCM-41, SAPO-34, and their physical mixture were also produced and catalytically compared. Physicochemical properties of materials were mainly investigated using XRD, N2 isothermal adsorption-desorption, FESEM, FT-IR, NH3-TPD, and TG/DTG/DTA techniques. METHODS: Micro-meso hierarchy of prepared composite was demonstrated by XRD and BET analyses. Catalytic performance of materials illustrated that the methanol conversion of the prepared composite was about 98% for 120 min, showing a higher activity than the other catalysts. The initial reaction selectivity to light olefins of the composite was also comparable with those for the other catalysts. Furthermore, the results revealed that SAPO-34/AlMCM-41 preparation decreased the concentration and strength of active acid sites of the catalyst which could beneficially affect the deposition of heavy molecular products on the catalyst. However, as observed, the prepared composite was deactivated in olefins production faster than pure SAPO-34. RESULTS: The small mean pore diameter of composite could be mainly responsible for its pore blockage and higher deactivation rate. Meanwhile, since the SAPO-34 prepared by dry-gel method had inherently high mesoporosity, the AlMCM-41 introduction did not promote the molecular diffusion in the composite structure. CONCLUSION: The coke content was found 15.5% for deactivated composite smaller than that for the SAPO- 34 catalyst which could be due to the pore blockage and deactivation of the composite in a shorter period.

Life Time Improvement of Hierarchically Structured SAPO-34 Nanocatalyst in MTO Reaction via Applying Clinoptilolite: Investigating of Composite Design via RSM.

AIM AND OBJECTIVE: The research focuses on recent progress in the production of light olefins. Hence, as the common catalyst of the reaction (SAPO-34) deactivates quickly because of coke formation, we reorganized the mechanism combining SAPO-34 with a natural zeolite in order to delay the deactivation time. MATERIALS AND METHODS: The synthesis of nanocomposite catalyst was conducted hydrothermally using experimental design. Firstly, Clinoptilolite was modified using nitric acid in order to achieve nano-scaled material. Then, the initial gel of the SAPO-34 was prepared using DEA, aluminum isopropoxide, phosphoric acid and TEOS as the organic template, sources of Aluminum, Phosphor, and Silicate, respectively. Finally, the modified zeolite was combined with SAPO-34's gel. RESULTS: 20 different catalysts due to D-Optimal design were synthesized and the nanocomposite with 50 weight percent of SAPO-34, 4 hours Crystallization and early Clinoptilolite precipitation showed the highest relative crystallinity, partly high BET surface area and hierarchical structure. CONCLUSION: Different analyses illustrated the existence of both components. The most important property alteration of nanocomposite was the increment of pore mean diameters and reduction in pore volumes in comparison with free SAPO-34. Due to the low price of Clinoptilolite, the new catalyst renders the process as economical. Using this composite, according to the formation of multi-sized pores located hierarchically on the surface of the catalyst and increased surface area, significant amounts of Ethylene and Propylene, in comparison with free SAPO-34, were produced, as well as the deactivation time was improved.

Performance analysis of ultrasound-assisted synthesized nano-hierarchical SAPO-34 catalyst in the methanol-to-lights-olefins process via artificial intelligence methods.

The present study has focused on performance analysis of ultrasound-assisted synthesized nano-hierarchical silico-alumino-phosphate-34 (SAPO-34) catalyst during methanol-to-light-olefins (MTO) process. A classical method, i.e., multiple linear regression (MLR) and two intelligent methods, i.e., genetic programming (GP) and artificial neural networks (ANN) were used for modeling of the performance of nano-hierarchical SAPO-34 catalyst. We studied the influence of basic parameters for the sonochemical synthesis of nano-hierarchical SAPO-34 catalyst such as crystallization time, ultrasonic irradiation time, ultrasonic intensity, amount of organic template (diethylamine (DEA) and carbon nanotube (CNT)) on its performance (methanol conversion and light olefins selectivity) in MTO process. The results revealed that the models achieved using the GP method had the highest accuracy for training and test data. Therefore, GP models were used in the following to predict the effect of main parameters for the sonochemical synthesis of nano-hierarchical SAPO-34 catalyst. Finally, an optimal catalyst with the highest yield into light olefins was predicted using the genetic optimization algorithm. The genetic models were employed as an evaluation function in the genetic algorithm (GA). A good agreement between the outputs of GP models for the optimal catalyst and experimental results were obtained. The optimal ultrasound-assisted synthesized nano-hierarchical SAPO-34 was accompanied by light olefins selectivity of 77% and methanol conversion of 94% from the onset of the process after 9 h.

Presenting a new kinetic model for methanol to light olefins reactions over a hierarchical SAPO-34 catalyst using the Langmuir-Hinshelwood-Hougen-Watson mechanism.

In this study, a new kinetic model for methanol to light olefins (MTO) reactions over a hierarchical SAPO-34 catalyst using the Langmuir-Hinshelwood-Hougen-Watson (LHHW) mechanism was presented and the kinetic parameters was obtained using a genetic algorithm (GA) and genetic programming (GP). Several kinetic models for the MTO reactions have been presented. However, due to the complexity of the reactions, most reactions are considered lumped and elementary, which cannot be deemed a completely accurate kinetic model of the process. Therefore, in this study, the LHHW mechanism is presented as kinetic models of MTO reactions. Because of the non-linearity of the kinetic models and existence of many local optimal points, evolutionary algorithms (GA and GP) are used in this study to estimate the kinetic parameters in the rate equations. Via the simultaneous connection of the code related to modelling the reactor and the GA and GP codes in the MATLAB R2013a software, optimization of the kinetic models parameters was performed such that the least difference between the results from the kinetic models and experiential results was obtained and the best kinetic parameters of MTO process reactions were achieved. A comparison of the results from the model with experiential results showed that the present model possesses good accuracy.

Heavy Metal Ions Uptake by AlPO-5 and SAPO-5 Nanoparticles: An Experimental and Modeling Study.

Synthesis of AlPO-5 and SAPO-5 nanoparticles was followed by applying hydrothermal method to use them as adsorbents in the removal of Fe3+, Pb2+, and Cd2+ions.The synthesized products were characterized using powder X-ray diffraction, scanning electron microscope (SEM), FTIR and BET analysis. The adsorption isotherms and kinetics including Langmuir, Freundlich, pseudo-first order, pseudo-second order and intraparticle diffusion models have been employed. The experimental adsorption equilibrium and kinetic data nearly followed the Langmuir isotherm and pseudo-second order kinetic model, respectively. It was found that the existence of the bridging hydroxyl group in the SAPO-5 structure causes chemisorption of Fe3+, Pb2+, and Cd2+ions on SAPO-5 which have greatly improved the performance of this adsorbent against its low external surface area. Using AlPO-5 and SAPO-5 as novel adsorbents in heavy metal adsorption for the first time indicated the great potential of these adsorbents in removal of heavy metal ions from water.

An investigation of the crystallization kinetics of zeotype SAPO-34 crystals synthesized by hydrothermal and sonochemical methods.

The kinetics study of SAPO-34 crystallization from a gel containing morpholine as a structure directing agent (SDA) was investigated by means of X-ray diffraction (XRD) patterns in order to determine the kinetics parameters, i.e. induction times, rate constants, frequency factors, and activation energies for the induction and growth stages. The kinetics data of growth period were determined by using the Avrami-Erofeev nucleation growth model. SAPO-34 molecular sieves were synthesized by using both sonochemical-assisted hydrothermal and conventional hydrothermal heating at temperatures of 180, 200, and 220 °C to elucidate the influence of crystallization method on the crystallization kinetics of SAPO-34. The activation energy values indicated that the crystal growth mechanism was enhanced for samples synthesized sonochemically, whereas the induction energy was not greatly affected by using sonication process. Also, the kinetic compensation effect (KCE) was considered in order to obtain the isokinetic temperature.

Synthesis of hierarchal SAPO-34 nano catalyst with dry gel conversion method in the presence of carbon nanotubes as a hard template.

In this study, the silicoaluminophosphate (SAPO) particles were synthesized based on dry gel conversion method using diethyl amine (DEA) as an organic structure directing agent (SDA). Transport pores were introduced into the crystalline structure of the catalyst using carbon nanotubes (CNT) as a hard template. The significance of molar ratio of CNT in the starting gel and the other synthesis parameters such as crystallization time, gel drying temperature and water content added in the crystallization stage, on crystallinity of SAPO-34, crystal phase, particle size and morphology were studied. The products were characterized by XRD, SEM, TEM, BET and EDX. D-optimal experimental design with four numeric factors including gel drying temperature, crystallization time, water/dry gel mass ratio and mole of CNT in the precursor gel each at three levels was implemented to optimize the experimental parameters by analysis of variance (ANOVA). The Fischer test results showed that, all the parameters have significant effect on the crystallinity of the synthesized samples.