Therapist Feedback and Implications on Adoption of an Artificial Intelligence-Based Co-Facilitator for Online Cancer Support Groups: Mixed Methods Single-Arm Usability Study.

BACKGROUND: The recent onset of the COVID-19 pandemic and the social distancing requirement have created an increased demand for virtual support programs. Advances in artificial intelligence (AI) may offer novel solutions to management challenges such as the lack of emotional connections within virtual group interventions. Using typed text from online support groups, AI can help identify the potential risk of mental health concerns, alert group facilitator(s), and automatically recommend tailored resources while monitoring patient outcomes. OBJECTIVE: The aim of this mixed methods, single-arm study was to evaluate the feasibility, acceptability, validity, and reliability of an AI-based co-facilitator (AICF) among CancerChatCanada therapists and participants to monitor online support group participants' distress through a real-time analysis of texts posted during the support group sessions. Specifically, AICF (1) generated participant profiles with discussion topic summaries and emotion trajectories for each session, (2) identified participant(s) at risk for increased emotional distress and alerted the therapist for follow-up, and (3) automatically suggested tailored recommendations based on participant needs. Online support group participants consisted of patients with various types of cancer, and the therapists were clinically trained social workers. METHODS: Our study reports on the mixed methods evaluation of AICF, including therapists' opinions as well as quantitative measures. AICF's ability to detect distress was evaluated by the patient's real-time emoji check-in, the Linguistic Inquiry and Word Count software, and the Impact of Event Scale-Revised. RESULTS: Although quantitative results showed only some validity of AICF's ability in detecting distress, the qualitative results showed that AICF was able to detect real-time issues that are amenable to treatment, thus allowing therapists to be more proactive in supporting every group member on an individual basis. However, therapists are concerned about the ethical liability of AICF's distress detection function. CONCLUSIONS: Future works will look into wearable sensors and facial cues by using videoconferencing to overcome the barriers associated with text-based online support groups. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): RR2-10.2196/21453.

Preparation, characterization, and in vitro evaluation of physostigmine-loaded poly(ortho ester) and poly(ortho ester)/poly(D,L-lactide-co-glycolide) blend microspheres fabricated by spray drying.

The physostigmine-loaded poly(ortho ester) (POE), poly(dl-lactide-co-glycolide) (PLGA) and POE/PLGA blend microspheres were fabricated by a spray drying technique. The in vitro degradation of, and physostigmine release from, the microspheres were investigated. SEM analysis showed that the POE and POE/PLGA blend particles were spherical. They were better dispersed when compared to the pure PLGA microspheres. Two glass transition temperature ( Tg ) values of the POE/PLGA blend microspheres were observed due to the phase separation of POE and PLGA in the blend system. XPS analysis proved that POE dominated the surfaces of POE/PLGA blend microspheres, indicating that the blend microspheres were coated with POE. The encapsulation efficiencies of all the microspheres were more than 95%. The incorporation of physostigmine reduced the Tg value of microspheres. The Tg value of the degrading microspheres increased with the release of physostigmine. For instance, POE blank microspheres and physostigmine-loaded POE microspheres had a Tg value of 67 degrees C and 48 degrees C, respectively. After 19 days in vitro incubation, Tg of the degrading POE microspheres increased to 55 degrees C. Weight loss studies showed that the degradation of the blend microspheres was accelerated with the presence of PLGA because its degradation products catalyzed the degradation of both POE and PLGA. The release rate of physostigmine increased with increase of PLGA content in the blend microspheres. The initial burst release of physostigmine was effectively suppressed by introducing POE to the blend microspheres. However, there was an optimized weight ratio of POE to PLGA (85:15 in weight), below which a high initial burst was induced. The POE/PLGA blend microspheres may make a good drug delivery system.

Double walled POE/PLGA microspheres: encapsulation of water-soluble and water-insoluble proteins and their release properties.

The poly(orthoester) (POE)-poly(D,L-lactide-co-glycolide) (50:50) (PLGA) double-walled microspheres with 50% POE in weight were loaded with hydrophilic bovine serum albumin (BSA) and hydrophobic cyclosporin A (CyA). Most of the BSA and CyA was entrapped within the shell and core, respectively, because of the difference in their hydrophilicity. The morphologies and release mechanisms of proteins-loaded double-walled POE/PLGA microspheres were investigated. Scanning electron microscope studies revealed that the CyA-BSA-loaded double-walled POE/PLGA microspheres yielded a more porous surface and PLGA shell than those without BSA. The neat POE and PLGA yielded slow and incomplete CyA and BSA release. In contrast, nearly complete BSA and more than 95% CyA were released in a sustained manner from the double-walled POE/PLGA microspheres. Both the BSA- and CyA-BSA-loaded POE/PLGA microspheres yielded a sustained BSA release over 5 days. The CyA release pattern of the CyA-loaded double-walled POE/PLGA microspheres was biphasic, characterized by a slow release over 15 days followed by a sustained release over 27 days. However, the CyA-BSA-loaded double-walled POE/PLGA microspheres provided a more constant and faster CyA release due to their more porous shell. In the CyA-BSA-loaded double-walled POE/PLGA microspheres system, the PLGA layer acted as a carrier for BSA and mild reservoir for CyA. During the first 5 days, most BSA was released from the shell but only 14% CyA was left from the microspheres. Subsequently, more than 80% CyA were released in the next 25 days. The distinct structure of double-walled POE/PLGA microspheres would make an interesting device for controlled delivery of therapeutic agents.

POE/PLGA composite microspheres: formation and in vitro behavior of double walled microspheres.

The poly(ortho ester) (POE) and poly(D,L-lactide-co-glycolide) 50:50 (PLGA) composite microspheres were fabricated by a water-in-oil-in-water (w/o/w) double emulsion process. The morphology of the composite microspheres varied depending on POE content. When the POE content was 50, 60 or 70% in weight, the double walled microspheres with a dense core of POE and a porous shell of PLGA were formed. The formation of the double walled POE/PLGA microspheres was analysed. Their in vitro degradation behavior was characterized by scanning electron microscopy, gel permeation chromatography, Fourier-transform infrared microscopy and nuclear magnetic resonance spectroscopy (NMR). It was found that compared to the neat POE or PLGA microspheres, distinct degradation mechanism was achieved in the double walled POE/PLGA microspheres system. The degradation of the POE core was accelerated due to the acidic microenvironment produced by the hydrolysis of the outer PLGA layer. The formation of hollow microspheres became pronounced after the first week in vitro. 1H NMR spectra showed that the POE core was completely degraded after 4 weeks. On the other hand, the outer PLGA layer experienced slightly retarded degradation after the POE core disappeared. PLGA in the double walled microspheres kept more than 32% of its initial molecular weight over a period of 7 weeks.

Development of poly(ortho esters) and their application for bovine serum albumin and bupivacaine delivery.

The preparation of drug delivery devices using solventless fabrication procedures is of significant interest and two such procedures are described. In one such procedure, powdered polymer and micronized protein are intimately mixed and then extruded into 1 mm strands that are cut to the desired length. The polymers used were specifically designed to allow extrusion at temperatures where proteins maintain activity in the dry state. In vitro erosion and BSA release show that BSA release and polymer erosion occur concomitantly indicating an erosion-controlled process. There is a lag-time, but that can be eliminated by the addition to the mixture prior to extrusion small amounts of poly(ethylene glycol) or its methoxy derivatives. The lag-time could also be eliminated by using an AB-block copolymer where A is poly(ortho ester) and B is poly(ethylene glycol). Another means of using solventless fabrication methods is to use a semi-solid material into which drugs can be mixed at room temperature and the semi-solid injected. Data on BSA and bupivacaine release are presented.