Autism Research in the Big Data Era. Marco Esposito, Università La Sapienza
1. Dr. Marco Esposito
Psicologo, Data Analyst & Counselor
Studia presso il Dipartimento di Scienze Statistiche «La Sapienza»
Facoltà di Ingegneria dell’Informazione, Informatica e Statistica
Supervisore presso i centri di ricerca e di trattamento sull’autismo «Una breccia nel muro»
marco.esposito@unabreccianelmuro.org
Autism Research in
the Big Data Era
Alcune immagini sono estratte da lezioni del Master in Big Data dell’università Sapienza
4. BIG DATA
in Computer Science are specified by the V’s
VOLUME, VELOCITY & VARIETY
of information assets that require new form of processing for decision-making
(Gartner, 2012)
4
7. DATA NEVER SLEEP
Information: identity, address, nationality, behaviors, preferences, likes,
political choices, relationships, treatments, time, events, reactions …
8.
9. Big Data = information + error (measurement)
Hard Data Compression (Data mining)
Taxonomy (science of classification)
Clustering to identify typologies of objects,
variables, occasions
Data Compression Statistical Modelling
21. Numerous diseases have preventable risk factors or at least
indicators of risk. Elucidating these disease characteristics may
help in personalized healthcare, and help reduce disease
burden. (p.4) …personalized healthcare requires ...aggregate
and integrate big data, …about patient similarities and
connections, and provide personalized disease risk profiles for
each individual patient, derived from not only the electronic
medical record information of that patient, but also from
similarities of that patient to millions of other patients… (p.5)
Currently, the focus on personalized healthcare is based on
genomic revolution. (p.6);
Can we develop a patient-centered model for personalized care
to answer questions such as:
22. 1. WHAT DISEASES AM I AT RISK FOR DEVELOPING?
2. HOW SHOULD I MANAGE THEM?
3. WHAT WELLNESS STRATEGIES
MAY BEST WORK FOR ME? (P.8)
24. Sources
Il Fascicolo Sanitario Elettronico (FSE), Decreto del Presidente del
Consiglio dei Ministri del 29 settembre 2015, n. 178,
contiene la storia clinica del paziente rappresentata da un insieme
di dati e documenti.
IL NUCLEO MINIMO DEL FASCICOLO SANITARIO ELETTRONICO:
dati identificativi e amministrativi dell'assistito;
referti;
verbali pronto soccorso;
lettere di dimissione;
profilo sanitario sintetico;
dossier farmaceutico;
consenso o diniego alla donazione degli organi e tessuti.
25. I DATI E DOCUMENTI DI TIPO INTEGRATIVO DEL FASCICOLO,
E QUINDI NON OBBLIGATORI:
prescrizioni (specialistiche, farmaceutiche, ecc.);
prenotazioni (specialistiche, di ricovero, ecc.);
cartelle cliniche; bilanci di salute;
assistenza domiciliare: scheda, programma e cartella clinico‐assistenziale;
piani diagnostico‐terapeutici;
assistenza residenziale e semiresidenziale: scheda multidimensionale di valutazione;
erogazione farmaci; vaccinazioni;
prestazioni di assistenza specialistica;
prestazioni di emergenza urgenza (118 e pronto soccorso);
prestazioni di assistenza ospedaliera in regime di ricovero;
certificati medici; taccuino personale dell'assistito;
relazioni relative alle prestazioni erogate dal servizio di continuità assistenziale;
autocertificazioni; partecipazione a sperimentazioni cliniche;
esenzioni; prestazioni di assistenza protesica;
dati a supporto delle attività di telemonitoraggio; …
26.
27. Efficacy of interventions for
children with autism?
OUTCOMES
CHILDREN'S
PROFILES
(Age, Comorbidity,
skills…)
ENVIRONMENT
(school, family,
community, sport…)
TREATMENT
(intensity, approach,
training, supervision)
34. 2016
we analyzed online queries posed by parents who were concerned that their child
might have ASD and categorized the warning signs they mentioned according to ASD-
specific and non-ASD–specific domains. We then used the data to test the efficacy
with which a trained machine learning tool classified the degree of ASD risk.
Yahoo Answers, a social site for posting queries and finding answers, was mined for
queries of parents asking the community whether their child has ASD.
A total of 195 queries were sampled for this study (mean child age=38.0 months; 84.7%
[160/189] boys). Content text analysis of the queries aimed to categorize the types of
symptoms described and obtain clinical judgment of the child’s ASD-risk level.
35. When testing whether an automatic classifier (decision tree) could predict if a
query was medium- or high-risk based on the text of the query and the coded
symptoms, performance reached an area under the receiver operating curve
(ROC) curve of 0.67 (CI 95% 0.50-0.78), whereas predicting from the text and
the coded signs resulted in an area under the curve of 0.82 (0.80-0.86).
36. In the present work, we performed an automated extraction of genes
associated with ASD and its comorbid disorders, and found 1031
genes involved in ASD, among which 262 are involved in ASD only,
with the remaining 779 involved in ASD and at least one comorbid
disorder.
2016
40. HAS SURVEY RESEARCH’S TIME COME TO AN END?
There are many who suggest that the glory days of surveys are
behind us, and we face a future of marginalization if not
redundancy (see, e.g., Savage and Burrows, 2007).
41. AUTISM RESEARCH IN
THE BIG DATA ERA
Grazie mille della vostra attenzione!!!
marco.esposito@unabreccianelmuro.org
OPPURE
ALLA
NOIA!