Home > database > ensemble_summary_subject_stats.m

ensemble_summary_subject_stats

PURPOSE ^

SYNOPSIS ^

function outData = ensemble_summary_subject_stats(inData)

DESCRIPTION ^

 Function that reports summary subject statistics of a given experiment
 such as gender count and ages.

 INPUT
   a cell array of 2 structs: session_info and subject_info, as returned 
   by ensemble_load_expinfo. This function will be called from within
   ensemble_load_expinfo, so there shouldn't normally be a need to call
   this function explicitly. However, in the event that we have data 
   from an old analysis that didn't include the output from this function, 
   it can be called easily by passing this information.
  
 OUTPUT
   An ensemble data struct with the following variables:
      nsubs -                    The number of subjects that were included in the analysis
      mean_age -                 The mean age of included subjects
      std_age  -                 The standard deviation of ages included in analysis
      age_range -                The minumum and maximum ages of included subs
      num_female -               The number of subjects that reported female gender
      num_male   -               The number of subjects that reported male gender
      num_gender_no_report -     The number of subjects that didn't report gender
      sessions_per_sub -         The number of sessions per subject. If the number of
                                 sessions for all subjects is not equal, the minumum 
                                 and maximum will be reported.
      mean_session_dur_minutes - The mean session duration in minutes. If
                                 there are multiple sessions per subject, 
                                 the mean for each session order
                                 will be reported (e.g. if 4 sessions/subject, 
                                 then 4 values are reported).

 Nov 3, 2009 - Stefan Tomic, First Version
 May 8, 2010 - S.T. fixed handling of anon_<hash> subIDs, which don't exist in
               subject table. Loops by subject ID retrieved in sessInfo
 May 22, 2010  PJ - added searching on type=session_info, and
               type=subject_info when search for these variables in name field
               fails. Fixed handling of age=0.

CROSS-REFERENCE INFORMATION ^

This function calls: This function is called by:

SOURCE CODE ^

0001 function outData = ensemble_summary_subject_stats(inData)
0002 %
0003 % Function that reports summary subject statistics of a given experiment
0004 % such as gender count and ages.
0005 %
0006 % INPUT
0007 %   a cell array of 2 structs: session_info and subject_info, as returned
0008 %   by ensemble_load_expinfo. This function will be called from within
0009 %   ensemble_load_expinfo, so there shouldn't normally be a need to call
0010 %   this function explicitly. However, in the event that we have data
0011 %   from an old analysis that didn't include the output from this function,
0012 %   it can be called easily by passing this information.
0013 %
0014 % OUTPUT
0015 %   An ensemble data struct with the following variables:
0016 %      nsubs -                    The number of subjects that were included in the analysis
0017 %      mean_age -                 The mean age of included subjects
0018 %      std_age  -                 The standard deviation of ages included in analysis
0019 %      age_range -                The minumum and maximum ages of included subs
0020 %      num_female -               The number of subjects that reported female gender
0021 %      num_male   -               The number of subjects that reported male gender
0022 %      num_gender_no_report -     The number of subjects that didn't report gender
0023 %      sessions_per_sub -         The number of sessions per subject. If the number of
0024 %                                 sessions for all subjects is not equal, the minumum
0025 %                                 and maximum will be reported.
0026 %      mean_session_dur_minutes - The mean session duration in minutes. If
0027 %                                 there are multiple sessions per subject,
0028 %                                 the mean for each session order
0029 %                                 will be reported (e.g. if 4 sessions/subject,
0030 %                                 then 4 values are reported).
0031 %
0032 % Nov 3, 2009 - Stefan Tomic, First Version
0033 % May 8, 2010 - S.T. fixed handling of anon_<hash> subIDs, which don't exist in
0034 %               subject table. Loops by subject ID retrieved in sessInfo
0035 % May 22, 2010  PJ - added searching on type=session_info, and
0036 %               type=subject_info when search for these variables in name field
0037 %               fails. Fixed handling of age=0.
0038   
0039 
0040 fParams.name = 'session_info';
0041 an_idx = ensemble_find_analysis_struct(inData,fParams);
0042 
0043 % if searching on name field failed, try searching on type field
0044 if isempty(an_idx)
0045   fParams = struct('type','session_info');
0046   an_idx = ensemble_find_analysis_struct(inData,fParams);
0047 end
0048 if isempty(an_idx)
0049   fprintf('Failed to find session_info\n')
0050   return
0051 end
0052 
0053 sessInfo = inData{an_idx};
0054 sessInfoCols = set_var_col_const(sessInfo.vars);
0055 
0056 fParams.name = 'subject_info';
0057 an_idx = ensemble_find_analysis_struct(inData,fParams);
0058 % if searching on name field failed, try searching on type field
0059 if isempty(an_idx)
0060   fParams = struct('type','subject_info');
0061   an_idx = ensemble_find_analysis_struct(inData,fParams);
0062 end
0063 if isempty(an_idx)
0064   fprintf('Failed to find subject_info\n')
0065   return
0066 end
0067 subInfo = inData{an_idx};
0068 subInfoCols = set_var_col_const(subInfo.vars);
0069 
0070 subids = unique(sessInfo.data{sessInfoCols.subject_id});
0071 nsubs = length(subids);
0072 nFemales = 0;
0073 nMales = 0;
0074 nGenderNoReport = 0;
0075 
0076 for isub = 1:nsubs
0077   
0078   thisSubID  = subids{isub};
0079   
0080   [subInSubTable,subInfoIdx] = ismember(thisSubID,subInfo.data{subInfoCols.subject_id});
0081   
0082   if(subInSubTable)
0083     subDOB = subInfo.data{subInfoCols.dob}{subInfoIdx};
0084   
0085     if(~isnan(subDOB))
0086       dobDatenum = datenum(subDOB,'yyyy-mm-dd');
0087     else
0088       dobDatenum = NaN;
0089     end
0090       
0091     subGender = subInfo.data{subInfoCols.gender}{subInfoIdx};
0092     
0093     switch(subGender)
0094      case 'F'
0095       nFemales = nFemales +1;
0096      case 'M'
0097       nMales = nMales+1;
0098      otherwise
0099       nGenderNoReport = nGenderNoReport + 1;
0100     end
0101     
0102   else
0103     subDOB = NaN;
0104     dobDatenum = NaN;
0105     nGenderNoReport = nGenderNoReport + 1;
0106   end
0107     
0108   sessionIdxs = strmatch(thisSubID,sessInfo.data{sessInfoCols.subject_id},'exact');
0109   nSess(isub) = length(sessionIdxs);
0110   
0111   sessDatenums = sessInfo.data{sessInfoCols.date_time}(sessionIdxs);
0112   sessEndDatenums = sessInfo.data{sessInfoCols.end_datetime}(sessionIdxs);
0113   
0114   
0115   %use the earliest session that this subject participated in to determine age
0116   useSessDatenum = min(sessDatenums);
0117   
0118   %sort sessions for this sub by start_time to find session order
0119   [sortedSessDatenums,sortedIdxs] = sort(sessDatenums);
0120   sortedSessEndDatenums = sessEndDatenums(sortedIdxs);  
0121   
0122   nSessThisSub = length(sortedIdxs);
0123   for iSess = 1:nSessThisSub
0124     
0125     serialSessDuration = sortedSessEndDatenums(iSess) - sortedSessDatenums(iSess);
0126     sessDurations(isub,iSess) = serialSessDuration * 24 * 60;
0127     
0128   end
0129   
0130   serialAge = useSessDatenum - dobDatenum;
0131   subAges(isub) = floor(serialAge/365);
0132   
0133   % If the age is somehow set to zero, e.g. if subject accidentally entered
0134   % current day as birthday, enter NaN
0135   if subAges(isub) == 0
0136     subAges(isub) = NaN;
0137   end
0138   
0139 end
0140 
0141 %replace zeros in sessDurations with NaNs. These are sessions that were not
0142 %recorded for a subject (e.g. all subjects completed three sessions, except for
0143 %one subject that only completed two sessions).
0144 sessDurations(sessDurations == 0) = NaN;
0145 
0146 %find mean duration per session
0147 nMaxSess = size(sessDurations,2);
0148 for iSess = 1:nMaxSess
0149   sessMeanDur(iSess) = nanmean(sessDurations(:,iSess));
0150 end
0151 
0152 meanAge = nanmean(subAges);
0153 stdAge = nanstd(subAges);
0154 ageRange = [nanmin(subAges) nanmax(subAges)];
0155 
0156 if(all(diff(nSess) == 0))
0157   nSessPerSub = nSess(1);
0158 else
0159   nSessPerSub = [min(nSess) max(nSess)];
0160 end
0161 
0162 
0163 outData = ensemble_init_data_struct;
0164 outData.name = 'summary_subject_stats';
0165 outData.type = 'summary_stats';
0166 outData.vars = {'nsubs','mean_age','std_age','age_range','num_female','num_male','num_gender_no_report' ...
0167        'sessions_per_sub' 'mean_session_dur_minutes'};
0168 outDataCols = set_var_col_const(outData.vars);
0169 outData.data{outDataCols.nsubs} = nsubs;
0170 outData.data{outDataCols.mean_age} = meanAge;
0171 outData.data{outDataCols.std_age} = stdAge;
0172 outData.data{outDataCols.age_range} = ageRange;
0173 outData.data{outDataCols.num_female} = nFemales;
0174 outData.data{outDataCols.num_male} = nMales;
0175 outData.data{outDataCols.num_gender_no_report} = nGenderNoReport;
0176 outData.data{outDataCols.sessions_per_sub} = nSessPerSub;
0177 outData.data{outDataCols.mean_session_dur_minutes} = sessMeanDur;

Generated on Sat 25-May-2019 04:00:51 by m2html © 2003