Psychosocial Stressors and Postpartum Depressive Symptoms Are Linked to Postpartum Contraceptive Use.

Background: Postpartum contraception plays a critical role in reducing the occurrence of rapid subsequent pregnancy, offering individuals reproductive choice, and promoting overall reproductive planning and well-being. In this study, we investigated the relationship between psychosocial stress during pregnancy, postpartum depressive symptoms (PDS), and postpartum contraceptive use. Materials and Methods: We analyzed data from the Pregnancy Risk Assessment Monitoring System (2012-2019), which included comprehensive information about maternal experiences, views, and needs before, during, and after pregnancy from four states and a large city, with a total sample size of N = 36,356. We conducted descriptive analyses as well as adjusted multivariable logistic regression models. Main Findings: Our findings demonstrate significant negative associations between partner-related (adjusted odds ratio [aOR] = 0.82, 95% confidence interval [95% CI]: 0.76-0.89, p ≤ 0.001) and trauma-related (aOR = 0.83, 95% CI: 0.75-0.92, p ≤ 0.001) stressors and postpartum contraceptive use. Additionally, we observed a negative association between PDS and postpartum contraceptive use (OR = 0.88, 95% CI: 0.80-0.97, p ≤ 0.01), indicating that individuals experiencing PDS are less likely to utilize contraception after giving birth. Furthermore, our study highlights racial/ethnic, socioeconomic, and parity postpartum contraceptive use disparities. Conclusions: Our findings emphasize the importance of incorporating psychosocial stressors and mental health into the promotion of effective postpartum contraception practices. These results have valuable implications for health care providers, policymakers, and researchers as they can guide the development of targeted interventions and support systems to contribute to improved reproductive health outcomes.

The 2023 Addiction Health Services Research Conference: Back in Person and Taking a Bite of the Big Apple.

The Addiction Health Services Research (AHSR) Conference has been held since 2002. This Conference brings together researchers, graduate students, policymakers, and treatment providers to focus improving the organization, distribution, and financing of healthcare resources for prevention/care of SUD. The AHSR 2023 Conference took place in New York City, October 18-20th, and was hosted by the Center for Health Economics of Treatment Interventions for Substance Use Disorder, HCV, and HIV (CHERISH; cherishresearch.org). Attended by more than 300 participants, the Conference comprised several themes relating to the latest research on addiction health services delivery, financing, and impact. The agenda also included pre-conference workshops, distinguished plenary speakers, a multitude of networking opportunities, and career support for early-stage and minority investigators. AHSR 2023 featured 3 plenary sessions, 120 oral presentations, and 143 poster presentations from academics throughout the world. Overall, AHSR 2023 provided numerous opportunities to advance the field of addiction health services research. The state-of-the-art techniques and insights gained by attending scholars will position them to be change-agents in the addiction field going forward.

Racial Differences in Self-Report of Mental Illness and Mental Illness Treatment in the Community: An Analysis of Jail Intake Data.

Jails and prisons in the United States house people with elevated rates of mental health and substance use disorders. The goal of this cross-sectional study was to evaluate the frequency of racial/ethnic differences in the self-report of mental illness and psychiatric medication use at jail entry. Our sample included individuals who had been incarcerated between 2016 and 2020 at the Middlesex Jail & House of Correction, located in Billerica, MA. We used data from the "Offender Management System," the administrative database used by the jail containing data on people who are incarcerated, and COREMR, the electronic medical record (EMR) used in the Middlesex Jail & House of Correction. We evaluated two primary outcomes (1) self-reported mental illness history and (2) self-reported use of psychiatric medication, with the primary indicator of interest as race/ethnicity. At intake, over half (57%) of the sample self-reported history of mental illness and 20% reported the use of psychiatric medications. Among people who self-reported a history of mental illness, Hispanic (AOR: 0.73, 95% CI: 0.60-0.90), Black (AOR: 0.52, 95% CI: 0.43-0.64), Asian/Pacific Islander (Non-Hispanic) people (AOR: 0.31, 95% CI: 0.13-0.74), and people from other racial/ethnic groups (AOR: 0.33, 95% CI: 0.11-0.93) all had decreased odds of reporting psychiatric medications. Mental illness was reported in about one-half of people who entered jail, but only 20% reported receiving medications in the community prior to incarceration. Our findings build on the existing literature on jail-based mental illness and show racial disparities in self-report of psychiatric medications in people who self-reported mental illness. The timing, frequency, and equity of mental health services in both the community and the jail setting deserves further research, investment, and improvement.

Environmental equity and COVID-19 experiences in the United States: Results from three survey waves of a nationally representative study conducted between 2020-2022.

Certain environmental exposures, such as air pollution, are associated with COVID-19 incidence and mortality. To determine whether environmental context is associated with other COVID-19 experiences, we used data from the nationally representative Tufts Equity in Health, Wealth, and Civic Engagement Study data (n=1785; three survey waves 2020-2022). Environmental context was assessed using self-reported climate stress and county-level air pollution, greenness, toxic release inventory site, and heatwave data. Self-reported COVID-19 experiences included willingness to vaccinate against COVID-19, health impacts from COVID-19, receiving assistance for COVID-19, and provisioning assistance for COVID-19. Self-reported climate stress in 2020 or 2021 was associated with increased COVID-19 vaccination willingness by 2022 (odds ratio [OR] = 2.35; 95% confidence interval [CI] = 1.47, 3.76), even after adjusting for political affiliation (OR = 1.79; 95% CI = 1.09, 2.93). Self-reported climate stress in 2020 was also associated with increased likelihood of receiving COVID-19 assistance by 2021 (OR = 1.89; 95% CI = 1.29, 2.78). County-level exposures (i.e., less greenness, more toxic release inventory sites, more heatwaves) were associated with increased vaccination willingness. Air pollution exposure in 2020 was positively associated with likelihood of provisioning COVID-19 assistance in 2020 (OR = 1.16 per µg/m3; 95% CI = 1.02, 1.32). Associations between certain environmental exposures and certain COVID-19 outcomes were stronger among those who identify as a race/ethnicity other than non-Hispanic White and among those who reported experiencing discrimination; however, these trends were not consistent. A latent variable representing a summary construct for environmental context was associated with COVID-19 vaccination willingness. Our results add to the growing body of literature suggesting that intersectional equity issues affecting likelihood of exposure to adverse environmental conditions are also associated with health-related outcomes.

Homelessness and Gender: Differences in Characteristics and Comorbidity of Substance Use Disorders at Admission to Services.

Background: Substance use disorders and homelessness are two closely related behavioral health issues. This study examines associations between homelessness and severity of substance use disorder (SUD) characteristics (inclusive of alcohol and other legal and illegal drugs) and presence of mental health comorbidity among individuals entering treatment for SUD. We also examine differences in SUD and mental health comorbidity by gender within a sample of clients experiencing homelessness upon admission to treatment. Methods: Using the 2017 Treatment Episodes Data Set, we used logistic regression models to examine the association between homelessness and indicators of severity (e.g., frequency of use, route of transmission) and the presence of mental health conditions, and to examine the association between gender and these dependent variables among only individuals experiencing homelessness at treatment admission. Results: After controlling for covariates, homelessness is significantly associated with increased odds of cocaine and methamphetamine use compared to all other substances, higher frequency of use, younger age of first use, use of more substances, injection drug use, and co-occurring mental health conditions. Female gender is inversely associated with younger age at first use and highly associated with co-occurring mental health conditions among those experiencing homelessness at admission to treatment. Conclusions: Individuals experiencing homelessness enter substance use services with different characteristics of substance use disorders, different patterns of use, and with higher rates of mental health comorbidity. Within homeless admissions, women have significant differences in substance use and higher likelihood of mental health comorbidity than men. Future research should focus on the specific treatment needs of individuals experiencing homelessness, and how the combination of homelessness and gender affects barriers and challenges to treatment.

Hospitalizations for Alcohol and Opioid Use Disorders in Older Adults: Trends, Comorbidities, and Differences by Gender, Race, and Ethnicity.

Background: The prevalence of substance use disorders (SUDs) among adults ages 65 and older has been increasing at a notably high rate in recent years, yet little information exists on hospitalizations for SUDs among this age group. In this study we examined trends in hospitalizations for alcohol use disorders (AUDs) and opioid use disorders (OUDs) among adults 65 and older in the United States, including differences by gender and race/ethnicity. Methods: We used Medicare claims data for years 2007-2014 from beneficiaries ages 65 and older. We abstracted hospitalization records with an ICD-9 diagnostic code for an AUD or OUD. Hospitalization rates were calculated using population estimates from the United States Census. We examined trends in quarterly hospitalization rates for hospitalizations with AUD/OUD as primary diagnoses, and separately for those with these disorders as secondary diagnoses. We also examined comorbidities for those with a primary diagnosis of AUD/OUD. Analyses were conducted for all hospitalizations with AUD/OUD diagnoses, and separately by gender and race/ethnicity. Results: Between the last quarter of 2007 and the third quarter of 2014, AUD hospitalization rates increased from 485 to 579 per million (19%), and OUD hospitalization rates from 46 to 101 per million (120%) and varied by gender (for AUD) and race/ethnicity (for both AUD and OUD). Hospitalization rates were particularly high for Black older adults, as was the increase in hospitalization rates. The increase in hospitalization rates was substantially higher for hospitalizations with AUD (84%) and OUD (269%) as secondary diagnoses. Conclusions: Hospitalizations for AUDs and OUDs among older adults increased at an alarming rate during the observation period, and disparities existed in hospitalization rates for these conditions. Interventions focusing on the needs of older adults with AUD and/or OUD are needed, particularly to address the needs of a growing racially/ethnically diverse older adult population.

Beneficios del uso del hierro parenteral como alternativa eficaz en el manejo de la anemia gestacional en Colombia / Benefits of the Use of Parenteral Iron as an Efficient Alternative in the Management of Gestational Anemia in Colombia / Benefícios do uso de ferro parenteral como alternativa eficaz no manejo da anemia gestacional na Colômbia

Introducción. La Organización Mundial de la Salud (OMS) estima que más del 40% de las mujeres embarazadas a nivel mundial tienen anemia, y la mitad de estas padecen deficiencia de hierro. La prevalencia en América Latina es del 40% y en Colombia del 44.7%. Fisiológicamente en el embarazo se produce una mal llamada "anemia dilucional", existen condiciones en la embarazada que la predisponen a tener una anemia patológica. Esta última es causada principalmente por un déficit de hierro, de allí la importancia de diagnosticar a tiempo esta entidad e iniciar el manejo. La administración de hierro es la base del tratamiento de la anemia por deficiencia de hierro. Puede ser administrado por vía oral, la cual es la preferida en la mayoría de las pacientes; sin embargo, cuando este no es posible administrarlo, es esencial recurrir al hierro parenteral. No obstante, el hierro parenteral es poco usado como primera línea en el manejo de la anemia gestacional. El presente artículo tiene como objetivo realizar una revisión que permita identificar la terapia con hierro parenteral como una alternativa eficaz de manejo para la anemia gestacional, teniendo en cuenta las características farmacológicas, la administración y el uso entre las diferentes moléculas disponibles en Colombia. Metodología. Corresponde a un estudio de revisión de literatura en bases de datos y bibliotecas electrónicas, los criterios que se tuvieron en cuenta fueron textos publicados entre 1996 y 2020, en español e inglés. Se obtuvo un resultado de 95 artículos, de los cuales se seleccionaron 49. Las palabras clave para su búsqueda fueron fisiología, hierro parenteral, anemia gestacional, déficit de hierro, complicaciones del embarazo, compuestos de hierro, farmacocinética, diagnóstico y tratamiento. División de temas tratados. Fisiología; ayudas diagnósticas; características farmacológicas del hierro parenteral; ventajas, indicaciones y contraindicaciones del hierro parenteral; efectos secundarios y forma de aplicación. Conclusiones. El hierro parenteral es un tratamiento seguro y eficaz para manejar la anemia en el embarazo, se debe tener en cuenta las indicaciones y la farmacología de las moléculas para elegir la más adecuada. Además, repone más rápidamente las reservas de hierro y los niveles de hemoglobina.

Introduction. The World Health Organization (WHO) estimates that more than 40% of pregnant women worldwide have anemia, and that half of them suffer from iron deficiency. The prevalence of this in Latin America is 40%, and in Colombia, 44.7%. Physiologically, a problem called "dilutional anemia" occurs during pregnancy. There are conditions in pregnant women that predispose them to suffering from pathological anemia. The latter is mainly caused by iron deficiency, hence the importance of diagnosing this entity on time and starting treatment. Iron administration is the basis of treatment of anemia caused by iron deficiency. It can be administered orally, which is the preferred option in the majority of patients. However, when this is not possible, parenteral iron must be used. However, parenteral iron is rarely used as the first line of treatment of gestational anemia. The objective of this article is to carry out a review that allows for the identification of therapy with parenteral iron as an efficient alternative for the treatment for gestational anemia, considering the pharmacological characteristics, administration, and use among the different molecules available in Colombia. Methodology. We carried out a search in databases and electronic libraries. The criteria considered were texts published between 1996 and 2020 in Spanish and English. 95 articles were obtained, of which 49 were selected. The keywords for their search were physiology, parenteral iron, gestational anemia, iron deficit, pregnancy complications, iron compounds, pharmacokinetics, diagnosis, and treatment. Division of Covered Topics. Physiology; diagnostic aids; pharmacological characteristics of parenteral iron; advantages, indications, and contraindications of parenteral iron; secondary effects and application method. Conclusions. Parenteral iron is a safe and efficient treatment to handle anemia during pregnancy. The indications and pharmacology of the molecules must be considered to choose the most appropriate option. In addition, it replaces iron reserves and hemoglobin levels more quickly.

Introdução. A Organização Mundial de Saúde (OMS) estima que mais de 40% das mulheres grávidas em todo o mundo são anêmicas, e metade delas sofre de deficiência de ferro. A prevalência na América Latina é de 40% e na Colômbia de 44.7%. Fisiologicamente na gravidez ocorre a chamada "anemia dilucional", e existem condições na gestante que a predispõem a ter uma anemia patológica. Esta última é causada principalmente por deficiência de ferro, daí a importância de diagnosticar esta entidade a tempo e iniciar o manejo. A administração de ferro é a base do tratamento da anemia por deficiência de ferro. Pode ser administrado por via oral, o que é preferido pela maioria das pacientes; porém, quando não for possível administrá-lo dessa forma, é imprescindível recorrer ao ferro parenteral. No entanto, o ferro parenteral é raramente usado como primeira linha no manejo da anemia gestacional. O objetivo deste artigo é realizar uma revisão que permita identificar a terapia com ferro parenteral como uma alternativa eficaz de tratamento da anemia gestacional, levando em consideração as características farmacológicas, administração e uso entre as diferentes moléculas disponíveis na Colômbia. Metodologia. Foi realizada uma busca em bases de dados e bibliotecas eletrônicas, os critérios levados em consideração foram textos publicados entre 1996 e 2020, em espanhol e inglês. Foi obtido um total de 95 artigos, dos quais 49 foram selecionados. As palavras-chave para a busca foram fisiologia, ferro parenteral, anemia gestacional, deficiência de ferro, complicações na gravidez, compostos de ferro, farmacocinética, diagnóstico e tratamento. Divisão dos temas abordados. Fisiologia; auxiliares de diagnóstico; características farmacológicas do ferro parenteral; vantagens, indicações e contraindicações do ferro parenteral; efeitos colaterais e método de aplicação. Conclusões. O ferro parenteral é um tratamento seguro e eficaz para o manejo da anemia na gravidez, as indicações e farmacologia das moléculas devem ser levadas em consideração a fim de escolher a mais adequada. Além disso, reabastece mais rapidamente as reservas de ferro e os níveis de hemoglobina.

Experiences with and impacts of the COVID-19 pandemic by substance use disorder in the early phase of pandemic in the United States: A cross-sectional survey, 2020.

INTRODUCTION: The coronavirus disease 2019 (COVID-19) pandemic could disproportionately affect individuals who have a substance use disorder (SUD). However, little information exists on COVID-19-related experiences among individuals with a SUD. We examined whether individuals with a SUD differ from other individuals with regard to COVID-19 testing, susceptibility, and employment-related vulnerability. METHODS: We used data from a U.S. nationally representative survey (n = 1,208). Using logistic regressions, we examined whether individuals with SUDs differ from other individuals regarding underlying health conditions, COVID-19 testing, access to paid sick leave, and loss of employment. Data were collected in late May-early June, 2020. RESULTS: Four percent of participants reported that a healthcare professional had told them they had a SUD. We found that, compared to those without SUDs, respondents with SUDs had higher odds of having lost their job due to the pandemic (adjusted odds ratio [AOR]:5.17, 95% confidence interval [CI]:2.28-11.74). Among individuals who were employed prior to the pandemic, people with SUDs had lower odds of having paid sick leave (AOR:0.26, 95% CI:0.09-0.74). CONCLUSION: Our study indicates that individuals with SUDs could be disproportionately affected by COVID-19 economically, which might worsen SUD and racial/ethnic health disparities.

Signo de Chilaiditi, diagnóstico tomográfico / Chilaiditi Sign, Tomographic Diagnosis / Sinal de Chilaiditi, diagnóstico tomográfico

Figura 1. Tomografía Computarizada de tórax (corte coronal). Se observan ambos campos pulmonares y las cavidades cardiacas. La flecha roja señala el área hipodensa ovalada correspondiente al aire dentro de un asa de colon interpuesta entre el hemidiafragma derecho (línea hiperdensa arriba) y el borde superior del hígado (abajo), causando una depresión del borde superior del hígado. Fuente: tomada de la historia clínica, previa autorización del paciente.

Figure 1. Chest Computed Tomography Scan (coronal plane) Both lung fields and cardiac chambers are observed. The red arrow indicates the oval hypodense area corresponding to the air inside the loop of colon interposed between the right hemidiaphragm (hyperdense line up) and superior border of the liver (down), causing a depression of the superior border of the liver. Source: taken with authorization from the patient's medical record.

Figura 1. Tomografia Computadorizada de tórax (corte coronal). Observam-se ambos os campos pulmonares e as cavidades cardíacas. A seta vermelha aponta para a área hipodensa oval correspondente ao ar dentro de uma alça do cólon interposta entre o hemidiafragma direito (linha hiperdensa acima) e a borda superior do fígado (abaixo), causando uma depressão da borda superior do fígado. Fonte: obtida com permissão do histórico clínico do paciente.

Associations among political voting preference, high-risk health status, and preventative behaviors for COVID-19.

BACKGROUND: We investigate the relationships among political preferences, risk for COVID-19 complications, and complying with preventative behaviors, such as social distancing, quarantine, and vaccination, as they remain incompletely understood. Since those with underlying health conditions have the highest mortality risk, prevention strategies targeting them and their caretakers effectively can save lives. Understanding caretakers' adherence is also crucial as their behavior affects the probability of transmission and quality of care, but is understudied. Examining the degree to which adherence to prevention measures within these populations is affected by their health status vs. voting preference, a key predictor of preventative behavior in the U. S, is imperative to improve targeted public health messaging. Knowledge of these associations could inform targeted COVID-19 campaigns to improve adherence for those at risk for severe consequences. METHODS: We conducted a nationally-representative online survey of U.S. adults between May-June 2020 assessing: 1) attempts to socially-distance; 2) willingness/ability to self-quarantine; and 3) intention of COVID-19 vaccination. We estimated the relationships between 1) political preferences 2) underlying health status, and 3) being a caretaker to someone with high-risk conditions and each dependent variable. Sensitivity analyses examined the associations between political preference and dependent variables among participants with high-risk conditions and/or obesity. RESULTS: Among 908 participants, 75.2% engaged in social-distancing, 94.4% were willing/able to self-quarantine, and 60.1% intended to get vaccinated. Compared to participants intending to vote for Biden, participants who intended to vote for Trump were significantly less likely to have tried to socially-distance, self-quarantine, or intend to be vaccinated. We observed the same trends in analyses restricted to participants with underlying health conditions and their caretakers Underlying health status was independently associated with social distancing among individuals with obesity and another high-risk condition, but not other outcomes. CONCLUSION: Engagement in preventative behavior is associated with political voting preference and not individual risk of severe COVID-19 or being a caretaker of a high-risk individual. Community based strategies and public health messaging should be tailored to individuals based on political preferences especially for those with obesity and other high-risk conditions. Efforts must be accompanied by broader public policy.

Atypical lymphoid cells circulating in blood in COVID-19 infection: morphology, immunophenotype and prognosis value.

AIMS: Atypical lymphocytes circulating in blood have been reported in COVID-19 patients. This study aims to (1) analyse if patients with reactive lymphocytes (COVID-19 RL) show clinical or biological characteristics related to outcome; (2) develop an automatic system to recognise them in an objective way and (3) study their immunophenotype. METHODS: Clinical and laboratory findings in 36 COVID-19 patients were compared between those showing COVID-19 RL in blood (18) and those without (18). Blood samples were analysed in Advia2120i and stained with May Grünwald-Giemsa. Digital images were acquired in CellaVisionDM96. Convolutional neural networks (CNNs) were used to accurately recognise COVID-19 RL. Immunophenotypic study was performed throughflow cytometry. RESULTS: Neutrophils, D-dimer, procalcitonin, glomerular filtration rate and total protein values were higher in patients without COVID-19 RL (p<0.05) and four of these patients died. Haemoglobin and lymphocyte counts were higher (p<0.02) and no patients died in the group showing COVID-19 RL. COVID-19 RL showed a distinct deep blue cytoplasm with nucleus mostly in eccentric position. Through two sequential CNNs, they were automatically distinguished from normal lymphocytes and classical RL with sensitivity, specificity and overall accuracy values of 90.5%, 99.4% and 98.7%, respectively. Immunophenotypic analysis revealed COVID-19 RL are mostly activated effector memory CD4 and CD8 T cells. CONCLUSION: We found that COVID-19 RL are related to a better evolution and prognosis. They can be detected by morphology in the smear review, being the computerised approach proposed useful to enhance a more objective recognition. Their presence suggests an abundant production of virus-specific T cells, thus explaining the better outcome of patients showing these cells circulating in blood.

Why are some people reluctant to be vaccinated for COVID-19? A cross-sectional survey among U.S. Adults in May-June 2020.

Understanding reasons for COVID-19 vaccine hesitancy is necessary to ensure maximum uptake, needed for herd immunity. We conducted a cross-sectional online survey between May 29-June 20, 2020 among a national sample of U.S. adults ages 18 years and over to assess cognitive, attitudinal and normative beliefs associated with not intending to get a COVID-19 vaccine. Of 1219 respondents, 17.7% said that they would not get a vaccine and 24.2% were unsure. In multivariable analyses controlled for gender, age, income, education, religious affiliation, health insurance coverage, and political party affiliation, those who reported that they were unwilling be vaccinated (versus those who were willing) were less likely to agree that vaccines are safe/effective (Relative Risk Ratio (RRR): 0.45, 95% confidence interval (CI): 0.31, 0.66), that everyone has a responsibility to be vaccinated (RRR: 0.39, 95% CI: 0.30, 0.52), that public authorities should be able to mandate vaccination (RRR: 0.75, 95% CI: 0.58, 0.98), and more likely to believe that if everyone else were vaccinated they would not need a vaccine (RRR: 1.36, 95% CI: 1.04, 1.78). Our results suggest that health messages should emphasize the safety and efficacy of vaccines, as well as the fact that vaccinating oneself is important, even if the level of uptake in the community is high.

Automatic identification of malaria and other red blood cell inclusions using convolutional neural networks.

Malaria is a serious disease responsible for thousands of deaths each year. Many efforts have been made to aid in the diagnosis of malaria using machine learning techniques, but to date, the presence of other elements that may interfere with the recognition of malaria has not been considered. We have developed the first deep learning model using convolutional neural networks capable of differentiating malaria-infected red blood cells from not only normal erythrocytes but also erythrocytes with other types of inclusions. 6415 images of red blood cells were segmented from digital images of 53 peripheral blood smears using thresholding and watershed transformation techniques. These images were used to train a VGG-16 architecture using transfer learning. Using an independent test set of 23 smears, this model was 99.5% accurate in classifying malaria parasites and other red blood cell inclusions. This model also exhibited sensitivity and specificity values of 100% and 91.7%, respectively, classifying a complete smear as infected or not infected. Our model represents a promising advance for automation in the identification of malaria-infected patients. The differentiation between malaria parasites and other red blood cell inclusions demonstrates the potential utility of our model in a real work environment.

A new convolutional neural network predictive model for the automatic recognition of hypogranulated neutrophils in myelodysplastic syndromes.

BACKGROUND: Dysplastic neutrophils commonly show at least 2/3 reduction of the content of cytoplasmic granules by morphologic examination. Recognition of less granulated dysplastic neutrophils by human eyes is difficult and prone to inter-observer variability. To tackle this problem, we proposed a new deep learning model (DysplasiaNet) able to automatically recognize the presence of hypogranulated dysplastic neutrophils in peripheral blood. METHODS: Eight models were generated by varying convolutional blocks, number of layer nodes and fully connected layers. Each model was trained for 20 epochs. The five most accurate models were selected for a second stage, being trained again from scratch for 100 epochs. After training, cut-off values were calculated for a granularity score that discerns between normal and dysplastic neutrophils. Furthermore, a threshold value was obtained to quantify the minimum proportion of dysplastic neutrophils in the smear to consider that the patient might have a myelodysplastic syndrome (MDS). The final selected model was the one with the highest accuracy (95.5%). RESULTS: We performed a final proof of concept with new patients not involved in previous steps. We reported 95.5% sensitivity, 94.3% specificity, 94% precision, and a global accuracy of 94.85%. CONCLUSIONS: The primary contribution of this work is a predictive model for the automatic recognition in an objective way of hypogranulated neutrophils in peripheral blood smears. We envision the utility of the model implemented as an evaluation tool for MDS diagnosis integrated in the clinical laboratory workflow.

A deep learning model (ALNet) for the diagnosis of acute leukaemia lineage using peripheral blood cell images.

BACKGROUND AND OBJECTIVES: Morphological differentiation among blasts circulating in blood in acute leukaemia is challenging. Artificial intelligence decision support systems hold substantial promise as part of clinical practise in detecting haematological malignancy. This study aims to develop a deep learning-based system to predict the diagnosis of acute leukaemia using blood cell images. METHODS: A set of 731 blood smears containing 16,450 single-cell images was analysed from 100 healthy controls, 191 patients with viral infections and 148 with acute leukaemia. Training and testing sets were arranged with 85% and 15% of these smears, respectively. To find the best architecture for acute leukaemia classification VGG16, ResNet101, DenseNet121 and SENet154 were evaluated. Fine-tuning was implemented to these pre-trained CNNs to adapt their layers to our data. Once the best architecture was chosen, a system with two modules working sequentially was configured (ALNet). The first module recognised abnormal promyelocytes among other mononuclear blood cell images, such as lymphocytes, monocytes, reactive lymphocytes and blasts. The second distinguished if blasts were myeloid or lymphoid lineage. The final strategy was to predict patients' initial diagnosis of acute leukaemia lineage using the blood smear review. ALNet was assessed with smears of the testing set. RESULTS: ALNet provided the correct diagnostic prediction of all patients with promyelocytic and myeloid leukaemia. Sensitivity, specificity and precision values of 100%, 92.3% and 93.7%, respectively, were obtained for myeloid leukaemia. Regarding lymphoid leukaemia, a sensitivity of 89% and specificity and precision values of 100% were obtained. CONCLUSIONS: ALNet is a predictive model designed with two serially connected convolutional networks. It is proposed to assist clinical pathologists in the diagnosis of acute leukaemia during the blood smear review. It has been proved to distinguish neoplastic (leukaemia) and non-neoplastic (infections) diseases, as well as recognise the leukaemia lineage.

Impact of the Medicare Shared Savings Program on utilization of mental health and substance use services by eligibility and race/ethnicity.

OBJECTIVE: To assess the impact of the Medicare Shared Savings Program (MSSP) ACOs on mental health and substance use services utilization and racial/ethnic disparities in care for these conditions. DATA SOURCES: Five percent random sample of Medicare claims from 2009 to 2016. STUDY DESIGN: We compared Medicare beneficiaries in MSSP ACOs to non-MSSP beneficiaries, stratifying analyses by Medicare eligibility (disability vs age 65+). We estimated difference-in-difference models of MSSP ACOs on mental health and substance use visits (outpatient and inpatient), medication fills, and adequate care for depression adjusting for age, sex, race/ethnicity, region, and chronic medical and behavioral health conditions. To examine the differential impact of MSSP on our outcomes by race/ethnicity, we used a difference-in-difference-in-differences (DDD) design. DATA COLLECTION/EXTRACTION METHODS: Not applicable. PRINCIPAL FINDINGS: MSSP ACOs were associated with small reductions in outpatient mental health (Coeff: -0.012, P < .001) and substance use (Coeff: -0.001, P < .01) visits in the disability population, and in adequate care for depression for both the disability- and age-eligible populations (Coeff: -0.028, P < .001; Coeff: -0.012, P < .001, respectively). MSSP ACO's were also associated with increases in psychotropic medications (Coeff: 0.007 and Coeff: 0.0213, for disability- and age-eligible populations, respectively, both P < .001) and reductions in inpatient mental health stays (Coeff:-0.004, P < .001, and Coeff:-0.0002, P < .01 for disability- and age-eligible populations, respectively) and substance use-related stays for disability-eligible populations (Coeff:-0.0005, P<.05). The MSSP effect on disparities varied depending on type of service. CONCLUSIONS: We found small reductions in outpatient and inpatient stays and in rates of adequate care for depression associated with MSSP ACOs. As MSSP ACOs are placed at more financial risk for population-based treatment, it will be important to include more robust behavioral health quality measures in their contracts and to monitor disparities in care.

Barriers, facilitators, and disparities in retention for adolescents in treatment for substance use disorders: a qualitative study with treatment providers.

BACKGROUND: Retention in substance use treatment is one of the strongest predictors of improved outcomes among adolescents, making retention an important goal of treatment. We examined treatment providers' perspectives on barriers and facilitators to treatment retention among adolescents, and their views on contributors to racial/ethnic disparities in retention including ways to address disparities. METHODS: Semi-structured interviews were conducted with 19 providers at state-licensed detoxification, residential, and outpatient facilities serving adolescents for substance use disorders in Massachusetts. Interviews were coded by at least two independent coders. RESULTS: Providers identified barriers and facilitators at the policy/systems, facility, family, and client levels. Some of the barriers included insurance limits on sessions/length of stay and low reimbursement (policy/systems), staff turnover (facility), low family engagement (family), and low internal motivation (client). Some facilitators mentioned were support from state's substance use agency (policy/systems), flexibility with meeting location (facility), family participation (family), and high internal motivation and presence of external motivators (client). Barriers that contributed to racial/ethnic disparities included lower socio-economic status, language barriers, and mistrust. Having bilingual/bicultural staff and multi-lingual materials, and facilitating transportation were identified as strategies for reducing disparities in treatment retention. CONCLUSIONS: It is critical that adolescents who access substance use services remain and complete treatment and that there is equity in treatment retention. Provider perspectives in factors associated with retention can inform the development of comprehensive interventions and policies to help improve retention and reduce disparities.

A dataset of microscopic peripheral blood cell images for development of automatic recognition systems.

This article makes available a dataset that was used for the development of an automatic recognition system of peripheral blood cell images using convolutional neural networks [1]. The dataset contains a total of 17,092 images of individual normal cells, which were acquired using the analyzer CellaVision DM96 in the Core Laboratory at the Hospital Clinic of Barcelona. The dataset is organized in the following eight groups: neutrophils, eosinophils, basophils, lymphocytes, monocytes, immature granulocytes (promyelocytes, myelocytes, and metamyelocytes), erythroblasts and platelets or thrombocytes. The size of the images is 360 × 363 pixels, in format jpg, and they were annotated by expert clinical pathologists. The images were captured from individuals without infection, hematologic or oncologic disease and free of any pharmacologic treatment at the moment of blood collection. This high-quality labelled dataset may be used to train and test machine learning and deep learning models to recognize different types of normal peripheral blood cells. To our knowledge, this is the first publicly available set with large numbers of normal peripheral blood cells, so that it is expected to be a canonical dataset for model benchmarking.

Sequential classification system for recognition of malaria infection using peripheral blood cell images.

AIMS: Morphological recognition of red blood cells infected with malaria parasites is an important task in the laboratory practice. Nowadays, there is a lack of specific automated systems able to differentiate malaria with respect to other red blood cell inclusions. This study aims to develop a machine learning approach able to discriminate parasitised erythrocytes not only from normal, but also from other erythrocyte inclusions, such as Howell-Jolly and Pappenheimer bodies, basophilic stippling as well as platelets overlying red blood cells. METHODS: A total of 15 660 erythrocyte images from 87 smears were segmented using histogram thresholding and watershed techniques, which allowed the extraction of 2852 colour and texture features. Dataset was split into a training and assessment sets. Training set was used to develop the whole system, in which several classification approaches were compared with obtain the most accurate recognition. Afterwards, the recognition system was evaluated with the assessment set, performing two steps: (1) classifying each individual cell image to assess the system's recognition ability and (2) analysing whole smears to obtain a malaria infection diagnosis. RESULTS: The selection of the best classification approach resulted in a final sequential system with an accuracy of 97.7% for the six groups of red blood cell inclusions. The ability of the system to detect patients infected with malaria showed a sensitivity and specificity of 100% and 90%, respectively. CONCLUSIONS: The proposed method achieves a high diagnostic performance in the recognition of red blood cell infected with malaria, along with other frequent erythrocyte inclusions.

Race/Ethnicity, Community of Residence, and DUI Arrest After Beginning Treatment for an Alcohol Use Disorder.

The purpose of this study was to examine whether racial/ethnic disparities in post-treatment arrests for driving under the influence (DUI) exist among clients receiving outpatient treatment for an alcohol use disorder (AUD) and to assess whether community characteristics were associated with this outcome. The sample included adults with an AUD entering publicly funded outpatient treatment in Washington State in 2012. Treatment data were linked with criminal justice and US Census data. Multilevel time-to-event analysis was employed to answer the research questions. Key independent variables included client race/ethnicity, community-level economic disadvantage, and racial/ethnic composition of the community. Latino clients and clients residing in communities with a higher proportion of Black residents had higher hazards of a DUI arrest post-treatment admission. Future research should examine whether disparities in DUI arrests are related to differences in treatment effectiveness or other factors (e.g., inequities in law enforcement) so that these disparities can be addressed.