Cognitive Screening for Mild Cognitive Impairment: Clinician Perspectives on Current Practices and Future Directions.

 This study surveyed 51 specialist clinicians for their views on existing cognitive screening tests for mild cognitive impairment and their opinions about a hypothetical remote screener driven by artificial intelligence (AI). Responses revealed significant concerns regarding the sensitivity, specificity, and time taken to administer current tests, along with a general willingness to consider adopting telephone-based screening driven by AI. Findings highlight the need to design screeners that address the challenges of recognizing the earliest stages of cognitive decline and that prioritize not only accuracy but also stakeholder input.

A framework for language technologies in behavioral research and clinical applications: Ethical challenges, implications, and solutions.

Technological advances in the assessment and understanding of speech and language within the domains of automatic speech recognition, natural language processing, and machine learning present a remarkable opportunity for psychologists to learn more about human thought and communication, evaluate a variety of clinical conditions, and predict cognitive and psychological states. These innovations can be leveraged to automate traditionally time-intensive assessment tasks (e.g., educational assessment), provide psychological information and care (e.g., chatbots), and when delivered remotely (e.g., by mobile phone or wearable sensors) promise underserved communities greater access to health care. Indeed, the automatic analysis of speech provides a wealth of information that can be used for patient care in a wide range of settings (e.g., mHealth applications) and for diverse purposes (e.g., behavioral and clinical research, medical tools that are implemented into practice) and patient types (e.g., numerous psychological disorders and in psychiatry and neurology). However, automation of speech analysis is a complex task that requires the integration of several different technologies within a large distributed process with numerous stakeholders. Many organizations have raised awareness about the need for robust systems for ensuring transparency, oversight, and regulation of technologies utilizing artificial intelligence. Since there is limited knowledge about the ethical and legal implications of these applications in psychological science, we provide a balanced view of both the optimism that is widely published on and also the challenges and risks of use, including discrimination and exacerbation of structural inequalities. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

An explainable machine learning model of cognitive decline derived from speech.

INTRODUCTION: Traditional Alzheimer's disease (AD) and mild cognitive impairment (MCI) screening lacks the sensitivity and timeliness required to detect subtle indicators of cognitive decline. Multimodal artificial intelligence technologies using only speech data promise improved detection of neurodegenerative disorders. METHODS: Speech collected over the telephone from 91 older participants who were cognitively healthy (n = 29) or had diagnoses of AD (n = 30) or amnestic MCI (aMCI; n = 32) was analyzed with multimodal natural language and speech processing methods. An explainable ensemble decision tree classifier for the multiclass prediction of cognitive decline was created. RESULTS: This approach was 75% accurate overall-an improvement over traditional speech-based screening tools and a unimodal language-based model. We include a dashboard for the examination of the results, allowing for novel ways of interpreting such data. DISCUSSION: This work provides a foundation for a meaningful change in medicine as clinical translation, scalability, and user friendliness were core to the methodologies. Highlights: Remote assessments and artificial intelligence (AI) models allow greater access to cognitive decline screening.Speech impairments differ significantly between mild AD, amnestic mild cognitive impairment (aMCI), and healthy controls.AI predictions of cognitive decline are more accurate than experts and standard tools.The AI model was 75% accurate in classifying mild AD, aMCI, and healthy controls.

Reflections on the nature of measurement in language-based automated assessments of patients' mental state and cognitive function.

Modern advances in computational language processing methods have enabled new approaches to the measurement of mental processes. However, the field has primarily focused on model accuracy in predicting performance on a task or a diagnostic category. Instead the field should be more focused on determining which computational analyses align best with the targeted neurocognitive/psychological functions that we want to assess. In this paper we reflect on two decades of experience with the application of language-based assessment to patients' mental state and cognitive function by addressing the questions of what we are measuring, how it should be measured and why we are measuring the phenomena. We address the questions by advocating for a principled framework for aligning computational models to the constructs being assessed and the tasks being used, as well as defining how those constructs relate to patient clinical states. We further examine the assumptions that go into the computational models and the effects that model design decisions may have on the accuracy, bias and generalizability of models for assessing clinical states. Finally, we describe how this principled approach can further the goal of transitioning language-based computational assessments to part of clinical practice while gaining the trust of critical stakeholders.

Towards a temporospatial framework for measurements of disorganization in speech using semantic vectors.

Incoherent speech in schizophrenia has long been described as the mind making "leaps" of large distances between thoughts and ideas. Such a view seems intuitive, and for almost two decades, attempts to operationalize these conceptual "leaps" in spoken word meanings have used language-based embedding spaces. An embedding space represents meaning of words as numerical vectors where a greater proximity between word vectors represents more shared meaning. However, there are limitations with word vector-based operationalizations of coherence which can limit their appeal and utility in clinical practice. First, the use of esoteric word embeddings can be conceptually hard to grasp, and this is complicated by several different operationalizations of incoherent speech. This problem can be overcome by a better visualization of methods. Second, temporal information from the act of speaking has been largely neglected since models have been built using written text, yet speech is spoken in real time. This issue can be resolved by leveraging time stamped transcripts of speech. Third, contextual information - namely the situation of where something is spoken - has often only been inferred and never explicitly modeled. Addressing this situational issue opens up new possibilities for models with increased temporal resolution and contextual relevance. In this paper, direct visualizations of semantic distances are used to enable the inspection of examples of incoherent speech. Some common operationalizations of incoherence are illustrated, and suggestions are made for how temporal and spatial contextual information can be integrated in future implementations of measures of incoherence.

Increasing access to cognitive screening in the elderly: Applying natural language processing methods to speech collected over the telephone.

Barriers to healthcare access are widespread in elderly populations, with a major consequence that older people are not benefiting from the latest technologies to diagnose disease. Recent advances in the automated analysis of speech show promising results in the identification of cognitive decline associated with Alzheimer's disease (AD), as well as its purported pre-clinical stage. We utilized automated methods to analyze speech recorded over the telephone in 91 community-dwelling older adults diagnosed with mild AD, amnestic mild cognitive impairment (aMCI) or cognitively healthy. We asked whether natural language processing (NLP) and machine learning could more accurately identify groups than traditional screening tools and be sensitive to subtle differences in speech between the groups. Despite variable recording quality, NLP methods differentiated the three groups with greater accuracy than two traditional dementia screeners and a clinician who read transcripts of their speech. Imperfect speech data collected via a telephone is of sufficient quality to be examined with the latest speech technologies. Critically, these data reveal significant differences in speech that closely match the clinical diagnoses of AD, aMCI and healthy control.

Using automated syllable counting to detect missing information in speech transcripts from clinical settings.

Speech rate and quantity reflect clinical state; thus automated transcription holds potential clinical applications. We describe two datasets where recording quality and speaker characteristics affected transcription accuracy. Transcripts of low-quality recordings omitted significant portions of speech. An automated syllable counter estimated actual speech output and quantified the amount of missing information. The efficacy of this method differed by audio quality: the correlation between missing syllables and word error rate was only significant when quality was low. Automatically counting syllables could be useful to measure and flag transcription omissions in clinical contexts where speaker characteristics and recording quality are problematic.

Natural Language Processing and Psychosis: On the Need for Comprehensive Psychometric Evaluation.

BACKGROUND AND HYPOTHESIS: Despite decades of "proof of concept" findings supporting the use of Natural Language Processing (NLP) in psychosis research, clinical implementation has been slow. One obstacle reflects the lack of comprehensive psychometric evaluation of these measures. There is overwhelming evidence that criterion and content validity can be achieved for many purposes, particularly using machine learning procedures. However, there has been very little evaluation of test-retest reliability, divergent validity (sufficient to address concerns of a "generalized deficit"), and potential biases from demographics and other individual differences. STUDY DESIGN: This article highlights these concerns in development of an NLP measure for tracking clinically rated paranoia from video "selfies" recorded from smartphone devices. Patients with schizophrenia or bipolar disorder were recruited and tracked over a week-long epoch. A small NLP-based feature set from 499 language samples were modeled on clinically rated paranoia using regularized regression. STUDY RESULTS: While test-retest reliability was high, criterion, and convergent/divergent validity were only achieved when considering moderating variables, notably whether a patient was away from home, around strangers, or alone at the time of the recording. Moreover, there were systematic racial and sex biases in the model, in part, reflecting whether patients submitted videos when they were away from home, around strangers, or alone. CONCLUSIONS: Advancing NLP measures for psychosis will require deliberate consideration of test-retest reliability, divergent validity, systematic biases and the potential role of moderators. In our example, a comprehensive psychometric evaluation revealed clear strengths and weaknesses that can be systematically addressed in future research.

Improving the Applicability of AI for Psychiatric Applications through Human-in-the-loop Methodologies.

OBJECTIVES: Machine learning (ML) and natural language processing have great potential to improve efficiency and accuracy in diagnosis, treatment recommendations, predictive interventions, and scarce resource allocation within psychiatry. Researchers often conceptualize such an approach as operating in isolation without much need for human involvement, yet it remains crucial to harness human-in-the-loop practices when developing and implementing such techniques as their absence may be catastrophic. We advocate for building ML-based technologies that collaborate with experts within psychiatry in all stages of implementation and use to increase model performance while simultaneously increasing the practicality, robustness, and reliability of the process. METHODS: We showcase pitfalls of the traditional ML framework and explain how it can be improved with human-in-the-loop techniques. Specifically, we applied active learning strategies to the automatic scoring of a story recall task and compared the results to a traditional approach. RESULTS: Human-in-the-loop methodologies supplied a greater understanding of where the model was least confident or had knowledge gaps during training. As compared to the traditional framework, less than half of the training data were needed to reach a given accuracy. CONCLUSIONS: Human-in-the-loop ML is an approach to data collection and model creation that harnesses active learning to select the most critical data needed to increase a model's accuracy and generalizability more efficiently than classic random sampling would otherwise allow. Such techniques may additionally operate as safeguards from spurious predictions and can aid in decreasing disparities that artificial intelligence systems otherwise propagate.

Cancer-associated MSC drive tumor immune exclusion and resistance to immunotherapy, which can be overcome by Hedgehog inhibition.

We investigated the impact of cancer-associated mesenchymal stem cells (CA-MSCs) on ovarian tumor immunity. In patient samples, CA-MSC presence inversely correlates with the presence of intratumoral CD8+ T cells. Using an immune "hot" mouse ovarian cancer model, we found that CA-MSCs drive CD8+ T cell tumor immune exclusion and reduce response to anti­PD-L1 immune checkpoint inhibitor (ICI) via secretion of numerous chemokines (Ccl2, Cx3cl1, and Tgf-ß1), which recruit immune-suppressive CD14+Ly6C+Cx3cr1+ monocytic cells and polarize macrophages to an immune suppressive Ccr2hiF4/80+Cx3cr1+CD206+ phenotype. Both monocytes and macrophages express high levels of transforming growth factor ß­induced (Tgfbi) protein, which suppresses NK cell activity. Hedgehog inhibitor (HHi) therapy reversed CA-MSC effects, reducing myeloid cell presence and expression of Tgfbi, increasing intratumoral NK cell numbers, and restoring response to ICI therapy. Thus, CA-MSCs regulate antitumor immunity, and CA-MSC hedgehog signaling is an important target for cancer immunotherapy.

Acceptability of collecting speech samples from the elderly via the telephone.

OBJECTIVE: There is a critical need to develop rapid, inexpensive and easily accessible screening tools for mild cognitive impairment (MCI) and Alzheimer's disease (AD). We report on the efficacy of collecting speech via the telephone to subsequently develop sensitive metrics that may be used as potential biomarkers by leveraging natural language processing methods. METHODS: Ninety-one older individuals who were cognitively unimpaired or diagnosed with MCI or AD participated from home in an audio-recorded telephone interview, which included a standard cognitive screening tool, and the collection of speech samples. In this paper we address six questions of interest: (1) Will elderly people agree to participate in a recorded telephone interview? (2) Will they complete it? (3) Will they judge it an acceptable approach? (4) Will the speech that is collected over the telephone be of a good quality? (5) Will the speech be intelligible to human raters? (6) Will transcriptions produced by automated speech recognition accurately reflect the speech produced? RESULTS: Participants readily agreed to participate in the telephone interview, completed it in its entirety, and rated the approach as acceptable. Good quality speech was produced for further analyses to be applied, and almost all recorded words were intelligible for human transcription. Not surprisingly, human transcription outperformed off the shelf automated speech recognition software, but further investigation into automated speech recognition shows promise for its usability in future work. CONCLUSION: Our findings demonstrate that collecting speech samples from elderly individuals via the telephone is well tolerated, practical, and inexpensive, and produces good quality data for uses such as natural language processing.

Extending the usefulness of the verbal memory test: The promise of machine learning.

The evaluation of verbal memory is a core component of neuropsychological assessment in a wide range of clinical and research settings. Leveraging story recall to assay neurocognitive function could be made more useful if it were possible to administer frequently (i.e., would allow for the collection of more patient data over time) and automatically assess the recalls with machine learning methods. In the present study, we evaluated a novel story recall test with 24 parallel forms that was deployed using smart devices in 94 psychiatric inpatients and 80 nonpatient adults. Machine learning and vector-based natural language processing methods were employed to automate test scoring, and performance using these methods was evaluated in their incremental validity, criterion validity (i.e., convergence with trained human raters), and parallel forms reliability. Our results suggest moderate to high consistency across the parallel forms, high convergence with human raters (r values ~ 0.89), and high incremental validity for discriminating between groups. While much work remains, the present findings are critical for implementing an automated, neuropsychological test deployable using remote technologies across multiple and frequent administrations.

Epigenomic Reprogramming toward Mesenchymal-Epithelial Transition in Ovarian-Cancer-Associated Mesenchymal Stem Cells Drives Metastasis.

A role for cancer cell epithelial-to-mesenchymal transition (EMT) in cancer is well established. Here, we show that, in addition to cancer cell EMT, ovarian cancer cell metastasis relies on an epigenomic mesenchymal-to-epithelial transition (MET) in host mesenchymal stem cells (MSCs). These reprogrammed MSCs, termed carcinoma-associated MSCs (CA-MSCs), acquire pro-tumorigenic functions and directly bind cancer cells to serve as a metastatic driver/chaperone. Cancer cells induce this epigenomic MET characterized by enhancer-enriched DNA hypermethylation, altered chromatin accessibility, and differential histone modifications. This phenomenon appears clinically relevant, as CA-MSC MET is highly correlated with patient survival. Mechanistically, mirroring MET observed in development, MET in CA-MSCs is mediated by WT1 and EZH2. Importantly, EZH2 inhibitors, which are clinically available, significantly inhibited CA-MSC-mediated metastasis in mouse models of ovarian cancer.

Applying speech technologies to assess verbal memory in patients with serious mental illness.

Verbal memory deficits are some of the most profound neurocognitive deficits associated with schizophrenia and serious mental illness in general. As yet, their measurement in clinical settings is limited to traditional tests that allow for limited administrations and require substantial resources to deploy and score. Therefore, we developed a digital ambulatory verbal memory test with automated scoring, and repeated self-administration via smart devices. One hundred and four adults participated, comprising 25 patients with serious mental illness and 79 healthy volunteers. The study design was successful with high quality speech recordings produced to 92% of prompts (Patients: 86%, Healthy: 96%). The story recalls were both transcribed and scored by humans, and scores generated using natural language processing on transcriptions were comparable to human ratings (R = 0.83, within the range of human-to-human correlations of R = 0.73-0.89). A fully automated approach that scored transcripts generated by automatic speech recognition produced comparable and accurate scores (R = 0.82), with very high correlation to scores derived from human transcripts (R = 0.99). This study demonstrates the viability of leveraging speech technologies to facilitate the frequent assessment of verbal memory for clinical monitoring purposes in psychiatry.

Validation of the surprise question in gynecologic oncology: A one-question screen to promote palliative care integration and advance care planning.

OBJECTIVE: The "surprise question" ("Would you be surprised if this patient died in the next year?") has been shown to be predictive of 12-month mortality in multiple populations, but has not been studied in gynecologic oncology (GO) patients. We sought to evaluate the prognostic performance of the surprise question in GO patients among physician and non-physician providers. METHODS: GO providers at two tertiary care centers were asked the surprise question about a cohort of their patients undergoing chemotherapy or radiation. Demographic and clinical information was chart abstracted. Mortality data were collected at one year; relative risk of death at one year based on response to the surprise question was then calculated. RESULTS: 32 providers (12 MDs, 7 APPs, 13 RNs) provided 942 surprise question assessments for 358 patients. Fifty-seven % had ovarian cancer and 54% had recurrent disease. Eighty-three (24%) patients died within a year. Patients whose physician answered "No" to the surprise question had a 43% one-year mortality (compared to 10% for "Yes"). Overall RR of 12-month mortality for "No" was 3.76 (95% CI 2.75-5.48); this association remained significant in all provider types. Among statistically significant predictors of 12-month mortality (including recurrent disease and >2 prior lines of chemotherapy), the surprise question had the highest RR. CONCLUSIONS: The surprise question is a simple, one question tool that effectively identifies GO patients increased risk of 12-month mortality. The surprise question could be used to identify patients for early referral to palliative care and initiation advance care planning.

Using Machine Learning in Psychiatry: The Need to Establish a Framework That Nurtures Trustworthiness.

The rapid embracing of artificial intelligence in psychiatry has a flavor of being the current "wild west"; a multidisciplinary approach that is very technical and complex, yet seems to produce findings that resonate. These studies are hard to review as the methods are often opaque and it is tricky to find the suitable combination of reviewers. This issue will only get more complex in the absence of a rigorous framework to evaluate such studies and thus nurture trustworthiness. Therefore, our paper discusses the urgency of the field to develop a framework with which to evaluate the complex methodology such that the process is done honestly, fairly, scientifically, and accurately. However, evaluation is a complicated process and so we focus on three issues, namely explainability, transparency, and generalizability, that are critical for establishing the viability of using artificial intelligence in psychiatry. We discuss how defining these three issues helps towards building a framework to ensure trustworthiness, but show how difficult definition can be, as the terms have different meanings in medicine, computer science, and law. We conclude that it is important to start the discussion such that there can be a call for policy on this and that the community takes extra care when reviewing clinical applications of such models..

Partnering with Panama: Exploring Anthropometrics, Dietary Patterns, and the Built Food Environment of School-aged Children.

Childhood obesity is a global public health concern in developed and developing countries. Approximately 3 in 10 Panamanian children suffer from obesity, and overweight/obesity is responsible for the highest number of premature or avoidable deaths in this country. A formative community assessment and exploration of the built food environment was conducted. Analysis suggests that almost one-third of the children measured were overweight or obese, and the availability of foods recommended for optimal health is limited in this community. Actionable recommendations for intervention and future collaboration were provided, and stakeholders from all groups will continue to explore opportunities.

Cancer antigen 125 is associated with disease status in uterine carcinosarcoma.

Uterine carcinosarcoma is a rare and aggressive tumor with poor outcomes. Cancer antigen 125 is routinely used to track the disease course of ovarian cancer and has been suggested as a biomarker in other aggressive forms of uterine cancer. We sought to characterize cancer antigen 125 as a potential biomarker of disease status in uterine carcinosarcoma. Clinical and pathological data were abstracted for patients who had surgical staging for a pathologically confirmed uterine carcinosarcoma at our institution from January 2000 to March 2014. Non-parametric tests were used to compare changes in cancer antigen 125. Elevated cancer antigen 125 (>35 U/mL) as a predictor of survival was assessed via Kaplan-Meier curves. Among the 153 patients identified, 66 patients had at least one paired measure of cancer antigen 125 drawn preoperatively, post-treatment, or at the time of disease recurrence, and 19 patients had cancer antigen-125 levels at all three time points. Analysis of the 51 patients with both preoperative and post-treatment values found a significant drop in cancer antigen 125 (p < 0.001). Among the 30 patients who had end-of-treatment and recurrence levels, a significant increase was noted (p = 0.001). There was no significant difference in cancer antigen-125 levels preoperatively compared to at recurrence among the 23 patients with levels at both time-points (p = 0.99). Elevated preoperative cancer antigen 125 was not associated with overall survival (p = 0.12); elevated post-treatment cancer antigen 125 was associated with a worse overall survival (p < 0.001). Based on this dataset, there seems to be utility in trending a cancer antigen-125 level in patients with uterine carcinosarcoma. A cancer antigen-125 level could predict recurrence and provide prognostic information regarding survival.

The double edge sword of fibrosis in cancer.

Cancer-associated fibrosis is a critical component of the tumor microenvironment (TME) which significantly impacts cancer behavior. However, there is significant controversy regarding fibrosis as a predominantly tumor promoting or tumor suppressing factor. Cells essential to the generation of tissue fibrosis such as fibroblasts and mesenchymal stem cells (MSCs) have dual phenotypes dependent upon their independence or association with cancer cells. Cancer-associated fibroblasts and cancer-associated MSCs have unique molecular profiles which facilitate cancer cell cross talk, influence extracellular matrix deposition, and direct the immune system to generate a protumorigenic environment. In contrast, normal tissue fibroblasts and MSCs are important in restraining cancer initiation, influencing epithelial cell differentiation, and limiting cancer cell invasion. We propose this apparent dichotomy of function is due to (1) cancer mediated stromal reprogramming; (2) tissue stromal source; (3) unique subtypes of fibrosis; and (4) the impact of fibrosis on other TME elements. First, as cancer progresses, tumor cells influence their surrounding stroma to move from a cancer restraining phenotype into a cancer supportive role. Second, cancer has specific organ tropism, thus stroma derived from preferred metastatic organs support growth while less preferred metastatic tissues do not. Third, there are subtypes of fibrosis which have unique function to support or inhibit cancer growth. Fourth, depleting fibrosis influences other TME components which drive the cancer response. Collectively, this review highlights the complexity of cancer-associated fibrosis and supports a dual function of fibrosis which evolves during the continuum of cancer growth.

Methodology of metal criticality determination.

A comprehensive methodology has been created to quantify the degree of criticality of the metals of the periodic table. In this paper, we present and discuss the methodology, which is comprised of three dimensions: supply risk, environmental implications, and vulnerability to supply restriction. Supply risk differs with the time scale (medium or long), and at its more complex involves several components, themselves composed of a number of distinct indicators drawn from readily available peer-reviewed indexes and public information. Vulnerability to supply restriction differs with the organizational level (i.e., global, national, and corporate). The criticality methodology, an enhancement of a United States National Research Council template, is designed to help corporate, national, and global stakeholders conduct risk evaluation and to inform resource utilization and strategic decision-making. Although we believe our methodological choices lead to the most robust results, the framework has been constructed to permit flexibility by the user. Specific indicators can be deleted or added as desired and weighted as the user deems appropriate. The value of each indicator will evolve over time, and our future research will focus on this evolution. The methodology has proven to be sufficiently robust as to make it applicable across the entire spectrum of metals and organizational levels and provides a structural approach that reflects the multifaceted factors influencing the availability of metals in the 21st century.