Nurse-Implemented Music Therapy to Reduce Anxiety in Community-Dwelling Individuals with Severe Mental Illness: A Pilot Study.

Anxiety is an important and recurrent problem in people with severe mental illness (SMI). The aim of this work is to measure the effectiveness of the Music Therapy nursing intervention in reducing anxiety in outpatients diagnosed with SMI (bipolar disorder and schizophrenia). The intervention was structured over five weeks (ten 1-h sessions, twice weekly). Objective measures (blood pressure, heart rate, and respiratory rate) and subjective measures (anxiety response and the subjective perception of relaxation) were taken before and after every session. Our results show that this nursing intervention entails an objective reduction of the respiratory rate ((-4.5, -0.5) breaths per minute), the heart rate ((-5.80, -2.13) bpm), and it evidences a reduction in the subjective perception of anxiety (16.08% mean reduction in state anxiety). Considering all the sessions, the subjective perception of relaxation increased 97.33% of the time. This study provides evidence that the Music Therapy intervention can effectively promote relaxation and reduce anxiety symptoms in people with SMI. This study was retrospectively registered at Clinical Trials with Protocol Identifier NCT06315049.

Maternal outcomes using delayed pushing versus immediate pushing in the second stage of labour: An umbrella review.

INTRODUCTION: Different systematic reviews have been developed in the last decades about maternal risks of immediate pushing and delayed pushing, depending on the duration of the second stage of labour, but they do not provide conclusive evidence. AIM: The main aim of this overview of systematic reviews was to assess the maternal outcomes using delayed pushing and immediate pushing in the second stage of labour in women receiving epidural analgesia. METHODS: We searched systematically in PubMed (Medline), EMBASE, CINAHL, and Scopus (October 26th, 2023). Methodological quality was analysed using AMSTAR and ROBIS scales, and the strength of evidence was established according to the guidelines advisory committee grading criteria. The outcome measures were the duration of the second stage of labour, duration of active pushing, caesarean section, instrumental vaginal birth, spontaneous vaginal birth, fatigue score, perineal lacerations, postpartum haemorrhage, and rate of episiotomy. Seven systematic reviews with and without meta-analysis were included. RESULTS: Results showed that delayed pushing increases the total time of the second stage of labour, although delayed pushing decreases the duration of active pushing with moderate quality of evidence. Mixed results were found with respect to the variables instrumental vaginal birth, spontaneous vaginal birth, and fatigue score although the results favour delayed pushing or show no statistically significant differences with respect to immediate pushing. No favourable results were ever found for immediate pushing with respect to delayed pushing, with a limited quality of evidence. Even so, delayed pushing seems to be associated with a significant increase in spontaneous vaginal birth rates. The results found no significant differences between the immediate pushing and delayed pushing groups in the caesarean section rates, perineal lacerations, postpartum haemorrhage, and episiotomy ratio, with a limited quality of evidence. CONCLUSIONS: This study shows that delayed pushing during the second stage of labour produces at least the same maternal outcomes as immediate pushing, although we note that delayed pushing produces an increase of the duration of the second stage of labour, a shorter duration of the active pushing and a tendency to increase spontaneous vaginal birth and to reduce the instrumental vaginal birth rates and fatigue scores. This should be considered clinically. This review was registered in the International Prospective Register of Systematic Reviews PROSPERO (CRD42023397616).

Antlion larvae localize long distant preys by a mechanism based on time difference.

Pit building antlions Euroleon nostras have been submitted to artificial cues in order to delineate their faculty to localize a prey. Series of propagating pulses in sand have been created from an extended source made of 10 piezoelectric transducers equally spaced on a line and located at a large distance from the pit. The envelope of each pulse encompasses six oscillations at a carrier frequency of 1250 Hz and up to eight oscillations at 1666 Hz. In one set of experiments, the first wave front is followed by similar wave fronts and the antlions respond to the cue by throwing sand in the opposite direction of the wave front propagation direction. In another set of experiments, the first wave front is randomly spatially structured while the propagation of the wave fronts inside the envelope of the pulse are not. In that case, the antlions respond less to the cue by throwing sand, and when they do, their sand throwing is more randomly distributed in direction. The finding shows that the localization of vibration signal by antlions are based on the equivalent for hearing animals of interaural time difference in which the onset has more significance than the interaural phase difference.

Evidence synthesis on coercion in mental health: An umbrella review.

Coercion in mental healthcare is ubiquitous and affects the physical health, recovery and psychological and emotional well-being of those who experience it. Numerous studies have explored different issues related to coercion, and the present umbrella review aims to gather, evaluate and synthesise the evidence found across systematic reviews. The protocol, registered in the International Prospective Register of Systematic Reviews (PROSPERO registration number: CRD42020196713), included 46 systematic reviews and meta-analyses of primary studies whose main theme was coercion and which were obtained from databases (Medline/PubMed, PsycINFO, EMBASE and CINAHL) and repositories of systematic reviews following the Preferred Reporting Items for Systematic reviews and Meta-Analyses guidelines. All the reviews were subjected to independent assessment of quality and risk of bias and were grouped in two categories: (1) evidence on specific coercive measures (including Community Treatment Orders, forced treatment, involuntary admissions, seclusion and restriction and informal coercion), taking into account their prevalence, related factors, effectiveness, harmful effects and alternatives to reduce their use; and (2) experiences, perceptions and attitudes concerning coercion of professionals, mental health service users and their caregivers or relatives. This umbrella review can be useful to professionals and users in addressing the wide variety of aspects encompassed by coercion and the implications for professionals' daily clinical practice in mental health units. This research received funding from two competitive calls.

Evaluation of mass media campaign of early cancer diagnosis, targeting older adults in Northern Ireland: a cross-sectional study.

BACKGROUND: Cancer Research UK ran a mass-media campaign for 6 weeks from Sept 1, 2022, to Sept 13, 2022, targeted to people aged 50 years and older and from a lower social-grade (C2DE) in Northern Ireland. The campaign was developed to target barriers to help-seeking for the target audience. With this evaluation, we aimed to compare reported barriers and self-reported help-seeking before and after the campaign to assess changes potentially related to the campaign. METHODS: We ran cross-sectional surveys that collected data from independent participants before the campaign (wave 1; n=1262; July 18-Aug 31, 2022) and after the campaign (wave 2; n=1250; Oct 3-Nov 3, 2022; N=2512). A recruitment agency recruited participants to be representative of Northern Ireland by age, gender, and social grade (Office for National Statistics, 2011; quota sampling). After wave 2, age range was 16-94 years (mean 51 years) and gender breakdown was 46% male (n=1152), 54% female (n=1356), and <1% other (n=3). Participants gave written informed consent, and the survey was administered using Computer Assisted Personal Interviewing (CAPI) at waves 1 and 2, and Computer Assisted Telephone Interviewing (CATI) at wave 1. Ethics approval was given by Queens University Belfast. Data were analysed in SPSS. FINDINGS: 78% of the targeted audience (354/451) reported remembering the TV campaign. Of people who reported no symptoms, more reported "nothing would put them off or delay seeking medical attention" at wave 2 (447 [41%] of 1084 participants) than at wave 1 (221 [24%] of 936 participants), and this difference was significant (t(939.796)=2·243, p=0·025; 95% CI 0·083 to 1·244). Participants who reported experiencing a symptom (wave 1 n=186; wave 2 103) were less likely to report that they did not seek help from their GP or doctor in wave 2 (n=63 [61%]) than in wave 1 (n=157 [85%]); however, this difference was not significant (t(214.167)=1·133, p=0·258, 95% CI -0·051 to 0·188). INTERPRETATION: Decreases in barriers reported "nothing putting them off seeking help" and decreases in not seeking help from a GP or doctor to help seeking for actual symptoms experienced suggests this campaign might have resulted in some positive shifts in self-reported help-seeking behaviours for actual symptoms. However, these findings should be interpreted in light of the limitations of this research. Although this was a large sample, additional consideration should be given to the use of independent samples (rather than repeated surveys with the same population), self-reported data, and different data collection methods. FUNDING: Community Foundation for Northern Ireland through the Department of Health Cancer Charities Fund.

Inactivation of Salmonella Enteritidis on Hatchery and Table Eggs Using a Gas-phase Hydroxyl-Radical Process.

Eggs represent a significant vehicle for Salmonella Enteritidis with the pathogen being transferred to chicks in the hatchery, or to consumers via table eggs. In the following, the efficacy of a gas-phase hydroxyl-radical process for decontaminating hatchery and table eggs was evaluated. Recovery of Salmonella was maximized through holding eggs in tryptic soy broth containing 20% w/v glycerol for 1 h prior to plating. By using this technique, it was possible to recover 63% of the theoretical Salmonella inoculated onto eggs. The continuous hydroxyl-radical reactor consisted of a bank of UV-C lamps (254 nm) that generated hydroxyl-radicals from the degradation of hydrogen peroxide (H2O2) mist and ozone gas. The optimal treatment was defined as that which supports a 5 log CFU/egg reduction of Salmonella without negatively affecting egg quality or leaving H2O2 residues. A process of 2% v/v H2O2 delivered at 30 mL/min with a UV-C dose of 19 mJ/cm2 and ozone (20 ppm) with a total treatment time of 10s was selected. The egg quality metrics (Haugh value, yolk index, albumin pH, yolk pH) did not negatively differ over a 35-day shelf-life at 4 or 25℃ compared to washed eggs or nontreated controls. The cuticle layer of eggs remained intact following hydroxyl-radical treatment. Fertilized eggs (n = 61) treated with the hydroxyl-radicals exhibited the same hatchery rate (75%) as nontreated controls (71-79%) with no defects (unhealed navels or red hocks) being observed. The same hydroxyl-radical treatment could be applied to table eggs to support >5 log CFU/egg reduction of Salmonella and was compatible with egg washing regimes practiced in industry. In comparison, the egg washing process based on sodium hydroxide and chlorine supported a 2.76 ± 0.38 log CFU/egg reduction of Salmonella. The hydroxyl-radical treatment represents a preventative control step to reduce the carriage of Salmonella on hatchery and table eggs.

Using COVID-19 Vaccine Attitudes Found in Tweets to Predict Vaccine Perceptions in Traditional Surveys: Infodemiology Study.

BACKGROUND: Traditionally, surveys are conducted to answer questions related to public health but can be costly to execute. However, the information that researchers aim to extract from surveys could potentially be retrieved from social media, which possesses data that are highly accessible and lower in cost to collect. OBJECTIVE: This study aims to evaluate whether attitudes toward COVID-19 vaccines collected from the Household Pulse Survey (HPS) could be predicted using attitudes extracted from Twitter (subsequently rebranded X). Ultimately, this study aimed to determine whether Twitter can provide us with similar information to that observed in traditional surveys or whether saving money comes at the cost of losing rich data. METHODS: COVID-19 vaccine attitudes were extracted from the HPS conducted between January 6 and May 25, 2021. Twitter's streaming application programming interface was used to collect COVID-19 vaccine tweets during the same period. A sentiment and emotion analysis of tweets was conducted to examine attitudes toward the COVID-19 vaccine on Twitter. Generalized linear models and generalized linear mixed models were used to evaluate the ability of COVID-19 vaccine attitudes on Twitter to predict vaccine attitudes in the HPS. RESULTS: The results revealed that vaccine perceptions expressed on Twitter performed well in predicting vaccine perceptions in the survey. CONCLUSIONS: These findings suggest that the information researchers aim to extract from surveys could potentially also be retrieved from a more accessible data source, such as Twitter. Leveraging Twitter data alongside traditional surveys can provide a more comprehensive and nuanced understanding of COVID-19 vaccine perceptions, facilitating evidence-based decision-making and tailored public health strategies.

Urinary Metabolite Profiling to Non-Invasively Monitor the Omega-3 Index: An Exploratory Secondary Analysis of a Randomized Clinical Trial in Young Adults.

The Omega-3 Index (O3I) reflects eicosapentaenoic acid (EPA) and docosahexaenoic acid (DHA) content in erythrocytes. While the O3I is associated with numerous health outcomes, its widespread use is limited. We investigated whether urinary metabolites could be used to non-invasively monitor the O3I in an exploratory analysis of a previous placebo-controlled, parallel arm randomized clinical trial in males and females (n = 88) who consumed either ~3 g/d olive oil (OO; control), EPA, or DHA for 12 weeks. Fasted blood and first-void urine samples were collected at baseline and following supplementation, and they were analyzed via gas chromatography and multisegment injection-capillary electrophoresis-mass spectrometry (MSI-CE-MS), respectively. We tentatively identified S-carboxypropylcysteamine (CPCA) as a novel urinary biomarker reflecting O3I status, which increased following both EPA and DHA (p < 0.001), but not OO supplementation, and was positively correlated to the O3I (R = 0.30, p < 0.001). Additionally, an unknown dianion increased following DHA supplementation, but not EPA or OO. In ROC curve analyses, CPCA outperformed all other urinary metabolites in distinguishing both between OO and EPA or DHA supplementation groups (AUC > 80.0%), whereas the unknown dianion performed best in discriminating OO from DHA alone (AUC = 93.6%). Candidate urinary biomarkers of the O3I were identified that lay the foundation for a non-invasive assessment of omega-3 status.

A fairness assessment of mobility-based COVID-19 case prediction models.

In light of the outbreak of COVID-19, analyzing and measuring human mobility has become increasingly important. A wide range of studies have explored spatiotemporal trends over time, examined associations with other variables, evaluated non-pharmacologic interventions (NPIs), and predicted or simulated COVID-19 spread using mobility data. Despite the benefits of publicly available mobility data, a key question remains unanswered: are models using mobility data performing equitably across demographic groups? We hypothesize that bias in the mobility data used to train the predictive models might lead to unfairly less accurate predictions for certain demographic groups. To test our hypothesis, we applied two mobility-based COVID infection prediction models at the county level in the United States using SafeGraph data, and correlated model performance with sociodemographic traits. Findings revealed that there is a systematic bias in models' performance toward certain demographic characteristics. Specifically, the models tend to favor large, highly educated, wealthy, young, and urban counties. We hypothesize that the mobility data currently used by many predictive models tends to capture less information about older, poorer, less educated and people from rural regions, which in turn negatively impacts the accuracy of the COVID-19 prediction in these areas. Ultimately, this study points to the need of improved data collection and sampling approaches that allow for an accurate representation of the mobility patterns across demographic groups.

Impaired aldehyde detoxification exacerbates motor deficits in an alpha-synuclein mouse model of Parkinson's disease.

INTRODUCTION: The discovery of biogenic aldehydes in the postmortem parkinsonian brain and the ability of these aldehydes to modify and cross-link proteins has called attention to their possible role in Parkinson's disease. For example, many in vitro studies have found that the aldehyde metabolite of dopamine, 3,4-dihydroxyphenylacetaldehyde (DOPAL), induces the formation of stable, neurotoxic alpha-synuclein oligomers. METHODS: To study this in vivo, mice deficient in the two aldehyde dehydrogenase enzymes (Aldh1a1 and Aldh2, DKO) primarily responsible for detoxification of DOPAL in the nigrostriatal pathway were crossed with mice that overexpress human wild-type alpha-synuclein. DKO overexpressing human wild-type alpha-synuclein (DKO/ASO) offspring were evaluated for impairment on motor tasks associated with Parkinsonism. RESULTS: DKO/ASO mice developed severe motor deficits greater than that of mice overexpressing human wild-type alpha-synuclein alone. CONCLUSION: These results provide evidence to support the idea that biogenic aldehydes such as DOPAL interact with human wild-type alpha-synuclein, directly or indirectly, in vivo to exacerbate locomotor deficits in Parkinson's disease.

Using COVID-19 Vaccine Attitudes on Twitter to Improve Vaccine Uptake Forecast Models in the United States: Infodemiology Study of Tweets.

BACKGROUND: Since the onset of the COVID-19 pandemic, there has been a global effort to develop vaccines that protect against COVID-19. Individuals who are fully vaccinated are far less likely to contract and therefore transmit the virus to others. Researchers have found that the internet and social media both play a role in shaping personal choices about vaccinations. OBJECTIVE: This study aims to determine whether supplementing COVID-19 vaccine uptake forecast models with the attitudes found in tweets improves over baseline models that only use historical vaccination data. METHODS: Daily COVID-19 vaccination data at the county level was collected for the January 2021 to May 2021 study period. Twitter's streaming application programming interface was used to collect COVID-19 vaccine tweets during this same period. Several autoregressive integrated moving average models were executed to predict the vaccine uptake rate using only historical data (baseline autoregressive integrated moving average) and individual Twitter-derived features (autoregressive integrated moving average exogenous variable model). RESULTS: In this study, we found that supplementing baseline forecast models with both historical vaccination data and COVID-19 vaccine attitudes found in tweets reduced root mean square error by as much as 83%. CONCLUSIONS: Developing a predictive tool for vaccination uptake in the United States will empower public health researchers and decisionmakers to design targeted vaccination campaigns in hopes of achieving the vaccination threshold required for the United States to reach widespread population protection.

Mental health initiatives: Providing stress management, wellness, and mindfulness workshops on college campuses.

Objective: College students experience stressors that can increase the risk for mental health concerns and negatively impact retention rates. It is crucial for practitioners working on college campuses to find creative ways to meet the needs of their students and cultivate a campus culture that is dedicated to bolstering mental health. The purpose of this study was to explore if implementing 1-h mental health workshops covering stress management, wellness, mindfulness, and SMART goals was feasible and advantageous for students. Participants: Researchers hosted 1-h workshops in 13 classrooms. Participants included 257 students who completed the pretest and 151 students who completed the post-test. Methods: A quasi-experimental 1-group pre- and post-test design was utilized. Results: Means and standard deviations were utilized to examine knowledge, attitudes, and intentions in each domain. Results indicated statistically significant improvements in each. Conclusion: Implications and interventions are provided for mental health practitioner working on college campuses.

Experience of coercion among nursing professionals in a medium-stay mental health unit: A qualitative study in Spain.

WHAT IS KNOWN ON THE SUBJECT?: Coercive measures represent an ethical conflict because they limit the person's freedom, compromising their personal autonomy, self-determination and fundamental rights. The reduction of the use of coercive measures implies not only regulations and mental health systems, but also cultural aspects, such as societal beliefs, attitudes, and values. There is evidence about the professionals' views on coercion in acute mental health care units and community settings, but they remain unexplored in inpatient rehabilitation units. WHAT THE PAPER ADDS TO EXISTING KNOWLEDGE?: The knowledge about coercion varied from not knowing at all the meaning of the word, to a proper description of the phenomenon. Coercive measures are considered a necessary evil or normalized in mental health care and considered implicit to daily practice. WHAT ARE THE IMPLICATIONS FOR PRACTICE?: The perceptions and attitudes towards coercion might be influenced by the knowledge about the phenomenon. Training of mental health nursing staff in non-coercive practice could help professionals to detect, be conscious towards, and question coercive measures, thus orienting them to the effective implementation of interventions or programmes with evidenced effectiveness to reduce them. ABSTRACT: INTRODUCTION: Creating a therapeutic and safe milieu with the minimum coercive measures requires knowing professionals' perceptions and attitudes towards coercion, but they remain unexplored in medium and long-stay inpatient psychiatric rehabilitation units. AIM: To explore the knowledge, perception and experience of coercion among nursing staff at a rehabilitation medium-stay mental health unit (MSMHU) in Eastern Spain. METHOD: Qualitative phenomenological study including 28 face-to-face, semi-structured interviews based on a script. Data were analysed using content analysis. RESULTS: Two main themes were found: (1) therapeutic relationship and treatment in the MSMHU, which included three subthemes: qualities of the professionals for building the therapeutic relationship; perceptions about the persons admitted to the MSMHU; views of the therapeutic relationship and treatment in the MSMHU; (2) Coercion at the MSMHU, comprising five subthemes: professional knowledge; general aspects; emotional impact of coercion; opinions; alternatives. DISCUSSION: Coercive measures are often normalized in mental health care and considered implicit to daily practice. A proportion of participants who did not know what coercion is. IMPLICATIONS FOR PRACTICE: Knowledge about coercion might influence attitudes towards coercion. Mental health nursing staff could benefit from formal training in non-coercive practice, facilitating the operative implementation of effective interventions or programmes.

All I missed in the therapeutic relationship: The lived experience narrative of a mental health nurse receiving mental healthcare.

WHAT IS KNOWN ON THE SUBJECT?: The therapeutic relationship is crucial for mental health practice, especially to practice that is recovery-orientated. WHAT THE PAPER ADDS TO EXISTING KNOWLEDGE?: This lived experience suggests that mental health professionals can be a long way from knowing the service users' feelings and their precise needs. The narrative reveals how mental health professionals maintain stereotypes and prejudices against people with mental health conditions and how these are reflected in their practice through lack of respect and users' dignity. WHAT ARE THE IMPLICATIONS FOR MENTAL HEALTH NURSING?: This lived experience narrative highlights the need to humanize care. ABSTRACT: INTRODUCTION: The therapeutic relationship is not always functional in clinical practice due to various factors, such as lack of time, lack of job motivation, exhaustion and rejection towards the person cared for. AIM: The aim of this study is to illustrate to professionals the needs of the persons they care for and how they see the world. METHOD: The aim was achieved through the development of a lived experience narrative. RESULTS: This lived experience narrative describes the experience of a mental health nurse since her first psychotic symptoms and her perceptions of the therapeutic relationship with mental health staff in her trajectory from the first psychiatric appointment until her last contact with the community mental health services. DISCUSSION: This narrative suggests that mental health professionals are sometimes far from discovering what service users are feeling and their precise needs. This highlights the need to humanize mental healthcare.

The Effect of Online Supervised Exercise throughout Pregnancy on the Prevention of Gestational Diabetes in Healthy Pregnant Women during COVID-19 Pandemic: A Randomized Clinical Trial.

(1) Background: to examine the effect of an online supervised exercise program during pregnancy on the prevention of GDM, and on maternal and childbirth outcomes. (2) Methods: we conducted a randomized clinical trial (NCT04563065) in 260 pregnant women without obstetric contraindications who were randomized into two study groups: intervention group (IG, N = 130) or control group (CG, N = 130). An online supervised exercise program was conducted from 8-10 to 38-39 weeks of pregnancy. (3) Results: no significant differences were found at baseline in maternal characteristics; nevertheless, certain outcomes showed a favorable trend towards the IG. A lower number and percentage of GDM cases were found in the IG compared to the CG (N = 5/4.9% vs. N = 17/16.8%, p = 0.006). Similarly, fewer cases of excessive maternal weight gain (N = 12/11.8% vs. N = 31/30.7%, p = 0.001) were found in the IG, and a lower percentage of instrumental deliveries (N = 8/11.3% vs. N = 13/15.1%) and c-sections (N = 7/9.9% vs. N = 20/23.3%, p = 0.046). (4) Conclusions: an online supervised exercise program can be a preventative tool for GDM in healthy pregnant women.

Perceived mental health and emotional trajectories of long-term family caregivers of persons with mental conditions: A mixed-methods study.

AIMS AND OBJECTIVES: To explore the emotional experience and the perceived mental health of experienced family caregivers of people with mental disorders. BACKGROUND: Family caregiving for individuals with mental disorders differs from other health conditions, as it implies a burden, deterioration in physical and mental health, stigma and a perceived lack of support from mental health services. METHODS: A mixed-method study was undertaken with family caregivers of people diagnosed with mental disorders. RESULTS: A total of 13 experienced family caregivers were included in the study. The qualitative data were classified into two major themes: emotions and perceived mental health. Emotions included five categories: irritability, painful emotions, pressure, emotions orientated towards coping, and positive emotions. The perceived mental health status embraced five categories: anxiety, burden and exhaustion, needing psychological or psychiatric treatment, insomnia and suicidal thoughts. An emotional path could be constructed from their discourses, starting with lack of control or irritation that evolved towards resignation, peace or satisfaction. The quantitative analysis partially replicated the qualitatively reported anxiety, depressive symptoms and insomnia. CONCLUSION: Past and present emotions related to caregiving described by experienced family caregivers were identified. Their emotional trajectories converged in that negative emotions gave way to emotions towards coping, which in turn were followed by positive emotions. The participants' descriptions about their mental status were partially reflected through objective mental health measurements. RELEVANCE TO CLINICAL PRACTICE: More support from mental health services could help caregivers to progress in their emotional trajectory towards coping, and improve their caregiving knowledge and skills. Mental health nurses have a role in patients and caregivers education and in the promotion of caregivers' psychological wellbeing.

Enhancing short-term crime prediction with human mobility flows and deep learning architectures.

Place-based short-term crime prediction models leverage the spatio-temporal patterns of historical crimes to predict aggregate volumes of crime incidents at specific locations over time. Under the umbrella of the crime opportunity theory, that suggests that human mobility can play a role in crime generation, increasing attention has been paid to the predictive power of human mobility in place-based short-term crime models. Researchers have used call detail records (CDR), data from location-based services such as Foursquare or from social media to characterize human mobility; and have shown that mobility metrics, together with historical crime data, can improve short-term crime prediction accuracy. In this paper, we propose to use a publicly available fine-grained human mobility dataset from a location intelligence company to explore the effects of human mobility features on short-term crime prediction. For that purpose, we conduct a comprehensive evaluation across multiple cities with diverse demographic characteristics, different types of crimes and various deep learning models; and we show that adding human mobility flow features to historical crimes can improve the F1 scores for a variety of neural crime prediction models across cities and types of crimes, with improvements ranging from 2% to 7%. Our analysis also shows that some neural architectures can slightly improve the crime prediction performance when compared to non-neural regression models by at most 2%.

Using Social Media to Predict Food Deserts in the United States: Infodemiology Study of Tweets.

BACKGROUND: The issue of food insecurity is becoming increasingly important to public health practitioners because of the adverse health outcomes and underlying racial disparities associated with insufficient access to healthy foods. Prior research has used data sources such as surveys, geographic information systems, and food store assessments to identify regions classified as food deserts but perhaps the individuals in these regions unknowingly provide their own accounts of food consumption and food insecurity through social media. Social media data have proved useful in answering questions related to public health; therefore, these data are a rich source for identifying food deserts in the United States. OBJECTIVE: The aim of this study was to develop, from geotagged Twitter data, a predictive model for the identification of food deserts in the United States using the linguistic constructs found in food-related tweets. METHODS: Twitter's streaming application programming interface was used to collect a random 1% sample of public geolocated tweets across 25 major cities from March 2020 to December 2020. A total of 60,174 geolocated food-related tweets were collected across the 25 cities. Each geolocated tweet was mapped to its respective census tract using point-to-polygon mapping, which allowed us to develop census tract-level features derived from the linguistic constructs found in food-related tweets, such as tweet sentiment and average nutritional value of foods mentioned in the tweets. These features were then used to examine the associations between food desert status and the food ingestion language and sentiment of tweets in a census tract and to determine whether food-related tweets can be used to infer census tract-level food desert status. RESULTS: We found associations between a census tract being classified as a food desert and an increase in the number of tweets in a census tract that mentioned unhealthy foods (P=.03), including foods high in cholesterol (P=.02) or low in key nutrients such as potassium (P=.01). We also found an association between a census tract being classified as a food desert and an increase in the proportion of tweets that mentioned healthy foods (P=.03) and fast-food restaurants (P=.01) with positive sentiment. In addition, we found that including food ingestion language derived from tweets in classification models that predict food desert status improves model performance compared with baseline models that only include socioeconomic characteristics. CONCLUSIONS: Social media data have been increasingly used to answer questions related to health and well-being. Using Twitter data, we found that food-related tweets can be used to develop models for predicting census tract food desert status with high accuracy and improve over baseline models. Food ingestion language found in tweets, such as census tract-level measures of food sentiment and healthiness, are associated with census tract-level food desert status.